BlogBlogA post on somebody's own site or a community platform. Nobody edits it after publication, so it dates from the day it was written.See every one →SAP Community
Generative AI-Powered Document Processing in SAP Integration Suite
Builds an SAP Cloud Integration iFlow that splits PDF email attachments (invoices, sales orders), sends each one to SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp's Generative AI Hub orchestration service with Claude as the selected model, and routes the classified result into downstream SAP S/4HANA processing. Cloud IntegrationCloud IntegrationBuilds and runs integration flows that process, route and map messages between cloud and on-premise systems, SAP and non-SAP, through prebuilt adapters; available only under an SAP Integration Suite plan.sap official, btp in SAP Integration SuiteSAP Integration SuiteSAP's integration service on BTP: Cloud Integration for orchestration, API Management in front of it, and an MCP gateway that serves a managed API to agents.sap official, btp does the extraction, splitting, the orchestration request and the router with a Groovy script and a General Splitter shown in full, while the model returns structured fields such as invoice number or sales order total through tool-calling instead of a document-specific parsing template. A human-approval step and a document-classification check (approved, sensitive, restricted) sit between the AI result and the S/4HANA posting.
Where it sits
Explains
Document extractionCAPBTPDocument extractionGetting structured data out of a document somebody sent you — an invoice, a purchase order, a scanned form — instead of having a person key it in. The mirror image of document output, and a different problem from reading a service: the input is a file, the shape is unknown until something reads it, and the answer arrives with a confidence rather than a guarantee.Integration flowsBTPIntegration flowsMoving and transforming messages between systems in middleware instead of in application code: an integration flow with its adapters and mappings, and the runtime it executes on. Reaching a remote system from application code is [destinations](capability:destinations), and brokering events between systems is [Event Mesh](capability:event-mesh).LLM integrationCAPABAPBTPLLM integrationCalling a language model from application code with the tenant, destination and credential handling already solved instead using an SDK call with a hand-rolled key.Cloud IntegrationBTPCloud IntegrationBuilds and runs integration flows that process, route and map messages between cloud and on-premise systems, SAP and non-SAP, through prebuilt adapters; available only under an SAP Integration Suite plan.SAP Integration SuiteBTPSAP Integration SuiteSAP's integration service on BTP: [Cloud Integration](artifact:btp-cloud-integration) for orchestration, [API Management](artifact:btp-api-management) in front of it, and an MCP gateway that serves a managed API to agents.SAP AI CoreCAPABAPBTPSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.
Who is behind it
sapcpidsauthor
Properties
About this work
Published
Published on
Group by187 of 187 pieces
Piece, what it offersStill applies
CAP in the age of AI #7 - vector embeddings wrap-upCAP in the age of AI #7 - vector embeddings wrap-upThe same embeddings model taken from SQLite to SAP HANA Cloud, then handed to an agent. Locally it is @cap-js/ai that adds the vector functions SQLite lacks and downloads an all-MiniLM L6v2 ONNX model on first start; on HANA natural language processing has to be switched on, the model name is a mandatory argument, the vectors it returns are 768 dimensions, and dimensions must match on both sides of a comparison. HANA itself can be given SAP AI Core as a remote source for other embedding models, which a CDS.ql expression has to inject because the postfix notation only takes what the CDS model holds, and the hour ends with a search function over cosine similarity exposed over @cap-js/mcp, so an agent asked about low output from solar panels calls semantic search instead of writing the query itself.published 2026-10-16
Unlocking Tabular Foundation Models: From Experimentation to ProductionUnlocking Tabular Foundation Models: From Experimentation to ProductionA Devtoberfest 2026 session (AI-41) on taking tabular prediction from a playground to a deployment. It sets tabular foundation models against a model trained per use case and against language models reading rows as text, explains in-context learning as examples plus the rows whose target column is missing, and tries SAP RPT 1.6 on a train-delay dataset in the RPT playground, including the column and row importance it returns with the prediction. The same prediction is then rebuilt on SAP AI Core, where the tabular orchestration service plays the part the orchestration service plays for language models: a data destination, a table artifact with its CSN schema and a scenario configuration registered once at design time, after which a predict call passes only the query rows, the scenario configuration and a context-selection strategy. The last demo runs those same calls in natural language through the aicore-skills plugin in a coding agent, and one of them only resolves once the agent is told which scenario configuration to use.published 2026-10-15
CAP in the age of AI #6 - vector embeddingsCAP in the age of AI #6 - vector embeddingsVector embeddings put to work in the incident management sample, answering whether this problem has been seen before. An embedding element of type Vector is calculated and stored from the vector_embedding function, so the database refreshes it whenever the text behind it changes, and cosine_similarity compares it with a freshly embedded string; because a title says little, a scheduled action first summarises each incident's conversation through a model on SAP AI Core and the embedding is taken from that summary. The similar-incidents list is a view joining incidents to themselves, with order and limit set in a before handler on the expanded query, and the vector element excluded from the service, since OData knows nothing about vectors — on SAP HANA Cloud the function is native, while SQLite needs packages added to the project.published 2026-10-09
Building Code-Based AI Agents on the BAIPBuilding Code-Based AI Agents on the BAIPA Devtoberfest 2026 session on writing the agent yourself rather than configuring one, which is the agent tooling edge: an agent is a model with tools, skills, memory and context around it, and the session reads the code of one built in CAP as a LangGraph state graph, with an agent node that calls the model, a tools node holding the MCP clients, and the edge between them looping until no tool is needed. It then shows the shorter route, a CDS service annotated for the agent protocol with its instructions and skills in an agent.md file. SAP AI Core carries both, with the CAP service in front of it as middleware so the credentials never reach the browser, and that is what cap-agent-ui5-webui is demonstrated against: added as a dependency, it gives the annotated service a UI5 chat interface that can be deployed rather than only previewed. A Python multi-agent application on Cloud Foundry, where an orchestrator delegates to per-stack specialists so no single model sees every tool, closes the session.published 2026-10-09
How Have SAP Customers Adopted n8nHow Have SAP Customers Adopted n8nA Devtoberfest 2026 session on what SAP customers are building with the standalone edition of n8n, from a partner who maintains an SAP OData node for it: use cases across purchase-to-pay, sales, finance and IT service, two live workflows, and the rules he works to — released SAP APIs only, no LLM in the decision path, exceptions to a person. The tool-choice half is where the edges hold: SAP Integration Suite is placed as the job for governed, high-volume system-to-system integration, and its MCP server is what the agent in the second demo reads SAP data through, while process automation is the concern the session sorts between document intake, approvals and the bot inventory that stays with RPA. The first demo is an order-confirmation check that reads a PDF, compares the lines against the purchase order over OData, asks a person, then writes the confirmation back.published 2026-10-08
Building Agentic Workflows with n8n in Joule StudioBuilding Agentic Workflows with n8n in Joule StudioA Devtoberfest 2026 session, JS-31, on SAP-managed n8n inside Joule Studio, shown as a labs preview on a blocked-invoice scenario: a solution made of assets, an intent refined by the web agent into requirements and then a specification, and the generated workflow opened in the n8n editor that Joule Studio connects to its own n8n tenant, with the generated files committed through GitHub. The nodes carry the other edges — the human-in-the-loop node is built on SAP Task Center, and SAP AI Core is where model providers are configured centrally instead of per developer. It ends in Joule chat, where the approval task the workflow created is listed, opened and completed.published 2026-10-08
Powering Enterprise-Ready Agentic AI with SAP Integration SuitePowering Enterprise-Ready Agentic AI with SAP Integration SuiteA Devtoberfest 2026 session (INT-31) from SAP Integration Suite product management on the MCP gateway. The demo creates an MCP server in a design package from an API already deployed on the tenant, exposes two of its 300-odd resources as tools, attaches authentication and quota policies on a policies tab, and publishes the deployed endpoint as an AI product in Developer Hub of API Management, where an agent subscribes and receives a token, URL, key and secret; the calls then show up in monitoring, in message processing logs and in the analytics dashboard, which is the MCP exposure and the tool governance the edges rest on. Three AI features inside Cloud Integration follow: a content migration agent that converts a PI/PO Java mapping into a Groovy script and generates a second integration flow for its lookup, memory profiling during a flow simulation, and root-cause analysis on a failed message processing log.published 2026-10-07
How to implement business AI capabilities in ABAP CloudHow to implement business AI capabilities in ABAP CloudA Devtoberfest 2026 session (ABA-32) on embedding AI in an ABAP Cloud application and on making SAP Joule aware of what that application can do. The first demo implements two features of a RAP travel app with the ABAP AI SDK: a determination on an uploaded receipt that sends the image together with the allowed categories and transaction types to a model reached through an intelligent scenario, then writes the extracted description, category, currency and amount back to the expense entity; and a recommendation function, triggered by a side effect on the trip title, that proposes a trip type with a score the Fiori UI sorts the proposals by and leaves the business user to accept — which is LLM integration from ABAP code. The second demo builds a capability for SAP Joule in the Joule Studio code editor in VS Code, with a scenario that extracts a trip title from the user's intent and calls an OData service in the ABAP backend through a BTP destination, deploys it and asks the Joule test UI for the trip's details; the session states that agents reach ABAP only over governed remote APIs — OData, SQL and MCP — and that automatic grounding of custom OData services in the knowledge graph is upcoming rather than available.published 2026-10-05
CAP in the age of AI #5 - agents wrap-upCAP in the age of AI #5 - agents wrap-upThe agents topic closed out on what sits around the agent rather than inside it, now that the documentation has moved into capire. The chat preview's session is persisted in the database rather than kept in memory, traces go out through @cap-js/telemetry to a self-hosted MLflow under the OpenTelemetry conventions for generative AI, and the panel is explicit that @agent reuses the MCP adapter's code programmatically without serving an MCP endpoint. It ends in the xtravels sample, where a travel agent delegates to a hotel-service sub-agent and reaches a separately started flight service over MCP through the service binding CAP resolves anyway. Earlier in the hour the same agent answers from a model running on the presenter's laptop, reached as an OpenAI-compatible endpoint.published 2026-10-02
🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and Compliance🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and ComplianceDevtoberfest 2026 session AI-21. A cross product owner on the SAP AI Core team gives the reasons an AI application ends up on more than one model — a model down at the hyperscaler, a data centre that is not allowed to run it, a version being deprecated — and runs a joke app that answers from Gemini 2.5 Flash in EU10 and from Claude 4.5 Haiku in Asia-Pacific. The walk through AI Core's parts is where the edges hold: prompts kept as templates in the prompt registry, imported through the launchpad and the APIs or synced as YAML from a git repository (Prompt management); the evaluation service scoring one prompt across up to four models per run on built-in or model-as-judge metrics, and the prompt optimizer generating variants against one metric (Agent evals); and the orchestration service harmonising the providers behind one message format with a priority-sorted fallback list (LLM integration). The session also states where a metric has to be designed rather than picked: an exact-JSON match scores an email generator at zero, so the joke app's custom metric judges topic and family-appropriateness instead.published 2026-10-01
SAP CPI Integration with Microsoft Graph API: OAuth 2.0, HTML Emails, and File AttachmentsSAP CPI Integration with Microsoft Graph API: OAuth 2.0, HTML Emails, and File AttachmentsBuilds an integration flow on Cloud Integration that sends an HTML email with a Base64-encoded attachment through the Microsoft Graph API instead of SMTP: an OAuth 2.0 Authorization Code credential configured for Microsoft 365, a Content Modifier and Base64 Encoder preparing the mail body and attachment, a Groovy script reading the access token from the SecureStoreService, and a Request-Reply step calling the Graph sendMail endpoint over its HTTP receiver adapter. It lists the HTTP 400/401/403 failures to check against the request body, the token and the Graph mail permissions.pooja_tiwari3, published 2026-09-30
What an AI infra engineer sees when opening SAP's AI stack (1/3): the model gatewayWhat an AI infra engineer sees when opening SAP's AI stack (1/3): the model gatewayA first look at SAP AI Core's Generative AI Hub from someone who builds gateways outside SAP for a living: the orchestration service harmonizes provider calls onto one API (a model name string switches providers, and SAP Note 3437766 carries the current model list, token rates and deprecation dates), runs a fixed, non-reorderable module pipeline — templating, masking through SAP Data Privacy Integration, grounding, content filtering, then the model call — and retries down an ordered fallback list whose entries can each carry their own model and rules. It places @sap-ai-sdk/orchestration among the official JavaScript, Java and Python SDKs, and notes SAP's own LiteLLM provider as a way to put a different gateway in front of it.amishkush, published 2026-09-30
🔴 Your Agent Wants to Call SAP. Now What?🔴 Your Agent Wants to Call SAP. Now What?Devtoberfest 2026 session INT-23, on what belongs between an agent and an SAP system. A solution advisor and an enterprise architect point Joule Desktop extensions at MCP servers built on API Management inside SAP Integration Suite, and ask it for business partners, orders and line items from an S/4HANA demo system; asked for the ten largest customers it answers from a sample of 200 orders rather than reading the whole table. They then open the API proxy behind it, where a spike arrest policy caps the backend at ten calls per second and the MCP server is configured to expose only the GET resources of the business-partner API so that an agent cannot create one, which is where the edges to Serve your application over MCP and Rate limiting hold. For totals across all sales orders they send the agent to SAP Business Data Cloud instead of the transactional system, since it aggregates and is read-only, and back through Integration Suite for writes such as journal entries.published 2026-09-30
Automating Learning Enrollment Communication with External Training Providers from LMS Using CPIAutomating Learning Enrollment Communication with External Training Providers from LMS Using CPIWalks through a CPI integration flow built to notify external training providers once an SAP SuccessFactors Learning enrollment is approved: an SFTP sender adapter picks up a daily custom LMS report, a Groovy script renames its CSV headers, message mapping concatenates first, middle and last name into a display name, a splitter processes each learner's record, and a Mail Receiver adapter sends an individual email per record with the training team in CC. Built in Cloud Integration on SAP Integration Suite, the flow is assembled from the editor's own adapters, a script step and a mapping step rather than custom code calling an API.Bhuvaneswari__A, published 2026-09-28
Bring "developers.sap.com" Into Your Dev Environment: SAP Developer Context for AI Coding AgentsBring "developers.sap.com" Into Your Dev Environment: SAP Developer Context for AI Coding AgentsDevtoberfest 2026 session FA-11: a tour of the rebuilt developers.sap.com by the team that runs it, from the administration screens behind the home page to the agent interfaces in front of it. The site is a CAP application on SAP HANA Cloud and SAP BTP, open-sourced in full, and the half of the session that places it here is how its content reaches an agent: every tutorial is also served as markdown, a coding agent is detected and given that version instead of the HTML, a well-known agent card advertises what the site offers, and SAP Developers MCP answers questions about tutorials, news and a reader's own completion history in Claude Code and Joule Desktop, over OAuth or a personal access token. Behind the answers sit two things working together: a knowledge graph in the HANA database over 1400 tutorials and 11,000 concepts, and SAP AI Core for the Joule interactions and the embeddings, with the agent harness written for the site rather than taken off a shelf. Where neither MCP nor A2A is available, the same content is published as skills.published 2026-09-25
🟣 Bring AI into Your ABAP Applications with ISLM: Build, Integrate, and Consume AI Natively🟣 Bring AI into Your ABAP Applications with ISLM: Build, Integrate, and Consume AI NativelyDevtoberfest 2026 session AI-11, from the product manager and product owner of Intelligent Scenario Lifecycle Management: ISLM as the place an AI use case is registered, deployed and operated inside an SAP S/4HANA system, and what has been added to it for generative AI. The demo builds a custom scenario end to end — an intelligent scenario of type generative AI, a connection to SAP AI Core, a GPT-5 mini model, an orchestration flow template that configures data masking, input and output filtering and translation into the user's logged-in language, then prompts with a grounding query over five companies' return-policy documents — and consumes it from an ABAP report through the ABAP AI SDK, which calls the orchestration API and returns the summary as JSON. Two newer pieces follow: SAP RPT, the relational pre-trained transformer for tabular prediction, called with context rows and query rows and answering with a confidence value and no training step; and system-triggered agents, where an application job in the ABAP system starts a billing-creation agent that reaches S/4HANA OData APIs as tools through the agent gateway with principal propagation. The closing availability matrix states the generative AI capabilities for on-premise and private cloud from the 2021 release, with SAP notes to implement on lower ones.published 2026-09-24
Expose RFCs as MCP Tools in Integration SuiteExpose RFCs as MCP Tools in Integration SuiteWalks through creating an MCP server in SAP Integration Suite from an RFC source: an on-premise RFC destination labelled for Integration Cell inclusion, a search over the backend's function modules (minimum seven characters), and up to 50 selected modules each becoming a tool. Covers the resulting server's configuration (Source, Tools and Prompts, with no Resources section for this source) and the two scopes an RFC-based server's policy adds beyond an API-sourced one, API.invoke and ESBMessaging.send, plus the RFC receiver adapter used at runtime. Demonstrates the flow with a purchase-order scenario where an AI client calls BAPI_PO_CREATE1 and BAPI_PO_GETDETAIL1 as MCP tools.ronit199666, published 2026-09-24
From opportunity to decision: Intelligent Credit Checks with AI Adapter in SAP Cloud IntegrationFrom opportunity to decision: Intelligent Credit Checks with AI Adapter in SAP Cloud IntegrationDevtoberfest 2026 session INT-12, in which an integration consultant builds two scenarios around the AI adapter in Cloud Integration. The first integration flow is triggered by a Salesforce opportunity event, reads that customer's history from S/4HANA over its OData APIs and calls a sales agent through the AI adapter, which writes a credit status and a credit rating band back onto the opportunity for the sales representative to act on; the second calls an operations agent from an exception subprocess and raises a Jira ticket carrying the suggested resolution, the related past tickets and the average resolution time recorded for the issue. The session places the adapter among the HTTP, Open Connectors and application-specific adapter routes, names its SAP Generative AI Hub, OpenAI and Claude variants, and gives the build effort as roughly 50 to 60 hours for the OData calls against the adapter configuration's two tabs.published 2026-09-23
From APIs to Agent Tools: How MCP Gateway changes what Integration meansFrom APIs to Agent Tools: How MCP Gateway changes what Integration meansThe opening session of the Devtoberfest 2026 integration track, in which two product managers for SAP Integration Suite set out why the suite puts an MCP gateway between agents and backend systems, and then build one. The demo turns an HTTP endpoint and its OpenAPI specification into MCP tools on the integration cell runtime, does the same on top of an existing API-centric integration, and shows the policies tab where authentication through an external provider, quotas, spike arrest and IP filtering sit, plus the trace of the JSON-RPC calls in monitoring and the agent they are earmarked against in analytics. That is where the serve your application over MCP and tool governance edges hold; RFCs and BAPIs as sources are stated as supported, and MCP federation, custom domains and edge integration cell as roadmap.published 2026-09-23
Supercharge Joule Desktop: Connect Any SAP API in Minutes with MCP GatewaySupercharge Joule Desktop: Connect Any SAP API in Minutes with MCP GatewayDevtoberfest 2026 session INT-13, in which an SAP solution advisor connects a live S/4HANA system to the desktop experience of Joule Work through the MCP gateway in SAP Integration Suite. One OpenAPI specification covering business partners, sales orders, material stock, billing and purchase requisitions is uploaded as an MCP server artifact, deployed to integration cell with XSUAA inbound authentication, and registered as an MCP connector; the destination behind it is then switched from basic authentication to principal propagation, and the Cloud Connector monitor shows the same question arriving as the presenter's own user. That demonstration is the serve your application over MCP edge, and the second half is Joule Work itself: a Markdown skill that fixes the steps and format of a customer briefing, and a Space the skill rebuilds with each run.published 2026-09-23
Version Control and Backup of SAP Cloud Integration Artifacts with Git - Step-by-Step GuideVersion Control and Backup of SAP Cloud Integration Artifacts with Git - Step-by-Step GuideA step-by-step walkthrough of SAP Integration Suite's built-in Git connection for Cloud Integration: creating a GitHub repository and a fine-grained personal access token, wiring it up under Settings > Integrations > GIT Access, then using a package's Git Push and Git Pull actions to back up its design-time artifacts and pull them back, including importing a pushed package into a different tenant. The commit history in the repository is the version record kept outside the tenant, and the guide confirms a pull by tracing an edited Groovy script back into the iflow.Nikhil_Gursal, published 2026-09-17
SAP Just Became AI-Agent Ready — Here's a Step-by-Step MCP WalkthroughSAP Just Became AI-Agent Ready — Here's a Step-by-Step MCP WalkthroughBuilds an MCP Server on SAP Integration Suite's Integration Cell, in front of a Cloud Integration flow that passes an OData V4 backend through untouched, with three tools generated from an OpenAPI spec. Secures it with OAuth 2.0 on SAP BTP client_credentials against XSUAA, and walks through the scope mismatch — the service key issues ESBMessaging.send, not the server's default API.invoke — that returns 403 until corrected; the finished server is then registered as a tool in Claude Code.published 2026-09-04
Why Our First Document AI Exercise Was a Résumé, Not an InvoiceWhy Our First Document AI Exercise Was a Résumé, Not an InvoiceWorking through a SAP Document AI workshop, the author explains why its exercises teach extraction on a résumé before an invoice: a résumé has no stable layout to map fields against, so it forces the point that the tool extracts from a written description of a schema rather than from position-matched templates. Describing the schema is shown to carry real judgment — what a missing end date should become, what a vague field name like "number" costs the model, who in a company should decide these things — and the piece argues that preparing for a project is chiefly a business task of writing down knowledge that otherwise stays in people's heads.Mariano_BacaStorni, published 2026-09-03
SAP Integration Suite + MCP: A Practical Architecture for AI Agents and SAPSAP Integration Suite + MCP: A Practical Architecture for AI Agents and SAPLays out the runtime chain for exposing S/4HANA APIs to an AI agent through SAP Integration Suite: the agent calls a tool on the MCP Gateway, which is built from a governed API Artifact, which still runs on Cloud Integration for mapping, routing and error handling before reaching the backend. It states that the API-artifact approach requires the Integration Cell runtime rather than the normal CPI message-processing runtime, an OAuth-secured REST or OData artifact on OpenAPI 3.0.0-3.0.3, and an entitlement that is service-plan dependent (citing SAP Note 2903776) — so the architecture question is whether the landscape already has the right MCP entitlement, runtime and API foundation.aayushaggarwal, published 2026-09-02
UI5 AI Features library is now an npm PackageUI5 AI Features library is now an npm PackageThe release note for a demo turning into a dependency, and it is explicit about why that matters: the earlier version worked, but using it meant cloning the repo and copying both halves, which stops working the moment one of them changes. The post walks through what shipping the CAP plugin and the be.wl.ai control library in one npm version buys — a client and server contract that cannot drift — then lists the eleven controls by group, shows the two-line configuration that activates each half, and notes that this version is actually deployed on BTP behind both a standalone approuter and Work Zone. It closes on the demo repository, written with no library source in it as the test that the package stands alone.published 2026-08-31
UI5 AI Features library is now an npm Package
cds 8, line ended. Affects Runnable code.
What a Second Document AI Workshop Taught Me About GovernanceWhat a Second Document AI Workshop Taught Me About GovernanceFrom questions raised at a second SAP Document AI workshop: the retention period for extracted data is a setting in the service's administration rather than a fixed property, with the source file deleted after processing and the decommissioning period for the extracted data configured to the customer's own policy. It also draws a boundary readers kept merging: Document AI extracts across languages but does not translate, so turning a document into a reviewer's own language is a separate step, pointing on BTP at SAP Translation Hub.Nicolas_BacaStorni, published 2026-08-25
Connecting SAP Integration Suite with SAP Document AI and SAP Business AIConnecting SAP Integration Suite with SAP Document AI and SAP Business AIWalks through a Cloud Integration flow in SAP Integration Suite that pulls PDF purchase orders from a Gmail mailbox, extracts header and line-item fields through SAP Document AI's job-submission and polling API, and validates the result with SAP AI Core's generative AI hub using GPT-5-mini as a quality check rather than the source of the extracted values. Groovy steps combine the Document AI confidence score and the model's score into one figure that routes low-scoring purchase orders to manual review, with no S/4HANA posting performed.subhojitSaha, published 2026-08-24
CAP in the age of AI #3 - from MCP to A2ACAP in the age of AI #3 - from MCP to A2AThe episode that finishes @cap-js/mcp with authorisation and then crosses to agents. @requires and @restrict are the same annotations CAP already has, and the plugin reads them to filter the tool list and the describe output per user and per request, so a model is not told about entities the caller cannot reach — where the OData metadata of the same service lists every exposed entity regardless. The second half annotates a service with @agent from @cap-js/agents, which serves it over A2A with an agent card and a chat preview, runs first against a mocked response and then against SAP AI Core bound with cds bind and a hybrid profile, and reuses the MCP adapter's tools rather than defining new ones.published 2026-08-21
SAP Datasphere Integration Patterns: Lessons Learned from Two Years of ImplementationsSAP Datasphere Integration Patterns: Lessons Learned from Two Years of ImplementationsTwo years of production SAP Datasphere integrations across SAP and non-SAP sources, settling on Replication Flows over remote access for high-volume Finance analytics because remote queries added latency at query time, then tuning the copy with Datasphere-side partitioning, source-side CDS view optimisation and Cloud Connector sizing. For file-based and Kafka sources, SAP Integration Suite iFlows did work a direct connection could not — flattening nested JSON, PGP decryption and orchestrating the SAP Ariba extraction built on SAP's own BTP Procurement Data Extractor content.saikrishna_kalivarapu2, published 2026-08-17
SAP API Management for Beginners – Part 1: What Is APIM & A Complete Features TourSAP API Management for Beginners – Part 1: What Is APIM & A Complete Features TourA features tour of SAP Integration Suite's API Management capability, opening a five-part beginner series: what a governed API proxy adds over calling a backend directly, and a walkthrough of API Providers, Proxy and Target Endpoints, the Policy Editor and Policy Templates, Products, the Developer Hub, and Key Value Maps. It names rate limiting's two complementary policies as APIM implements them: Spike Arrest, which caps requests per second or minute against bursts, and Quota, which caps total calls per day, week or month against overuse.Rudhra, published 2026-08-03
SAP BTP - CI - EventSmartKafka - Custom Kafka Adapter - Part V FINALSAP BTP - CI - EventSmartKafka - Custom Kafka Adapter - Part V FINALEventSmartKafka is an open-source Kafka Consumer/Sender adapter for SAP Cloud Integration in SAP Integration Suite, built with the SAP Adapter Development Kit; it reaches Apache Kafka over SASL, SASL_SSL and mutual TLS, with on-premise brokers reached through Cloud Connector. This final release adds Avro-to-JSON/XML conversion, schema registry integration, message recovery by timestamp and Kafka producer support. The author reports the consumer validated past 6.5 million processed messages with zero failures and the producer run continuously for more than 20 hours, with deployment lifecycle testing — deleting, upgrading and redeploying the adapter — showing no runtime interruption.rhviana, published 2026-07-28
RFC/BAPIs Meet AI Agents: Why SAP Integration Suite MCP Server MattersRFC/BAPIs Meet AI Agents: Why SAP Integration Suite MCP Server MattersExplains that SAP Integration Suite's MCP Server artifact can expose RFC-enabled BAPIs, alongside API artifacts and HTTP endpoints, as MCP tools — letting BAPIs on SAP ECC or on-premise S/4HANA participate in agentic workflows without rewriting business logic or waiting for a full ERP transformation. Frames RFC support as a bridge for organisations still modernising rather than a recommendation to build new RFC-based integrations, and notes the exposed BAPIs inherit the server's existing authentication, rate limiting and IP filtering. A demo built against an SAP ECC backend shows an MCP client discovering and invoking several read-only BAPIs from natural-language prompts, with no custom wrapper code.arunmaarirajha_kv, published 2026-07-28
Cloud Integration- Activating Enterprise Messaging Capabilities for JMS Queue - CFCloud Integration- Activating Enterprise Messaging Capabilities for JMS Queue - CFTraces a JMS iFlow deployment failure on Cloud Integration (Cloud Foundry) — ERROR_MISSING_SERVICE_KEY — to the Message Queues (Enterprise Messaging) capability being switched off on the tenant rather than a missing service key, since an edition upgrade does not turn it on by itself. Resolves it by enabling Message Queues under Manage Capabilities, which restarts the tenant, then redeploying the affected iFlows.Pavan_Koppula1, published 2026-07-21
MCP Servers on SAP Integration Suite : Build Your First MCP Server from an APIMCP Servers on SAP Integration Suite : Build Your First MCP Server from an APIWalks through building an MCP server on SAP Integration Suite from an existing managed API — SAP S/4HANA's Purchase Order API — rather than from an HTTP endpoint or an RFC, which the same creation wizard supports but a later post in the series is left to cover. Selected API operations become MCP Tools with generated input and output schemas, the server inherits its Authentication policy from the source API, and a Process Integration Runtime service instance supplies the OAuth credentials an external client needs to invoke it. Ends by connecting the deployed server to Cline in VS Code and having it chain tool calls to answer a natural-language purchase-order query.published 2026-07-15
Turn SAP APIs into MCP Tools for AI Agents using SAP Integration Suite Free TrialTurn SAP APIs into MCP Tools for AI Agents using SAP Integration Suite Free TrialWalks through building an MCP server on SAP Integration Suite's free trial from an existing API artifact — the Business Partner API against a public S/4HANA Cloud sandbox — rather than from an HTTP endpoint with an OpenAPI specification or from RFC-enabled function modules, the creation wizard's other two source types, left unexplained here. Covers the API artifact's Content Modifier policy that injects the Business Accelerator Hub API key before the backend call, and the "Trust Upstream MCP Authorization" setting that lets the MCP server delegate authorization checks to that source API instead of duplicating them. Ends by fetching an OAuth token from a Process Integration Runtime service key and pointing an MCP client at the deployed server over streamable HTTP.published 2026-07-13
Principal Propagation from BTP Web App to S/4HANA via SAP Integration SuitePrincipal Propagation from BTP Web App to S/4HANA via SAP Integration SuiteWalks through configuring principal propagation from a BTP web app, through SAP Integration Suite and Cloud Connector, to an on-premise S/4HANA system, so the backend receives calls as the logged-in user rather than a shared service account. The BTP Destination service uses OAuth2JWTBearer to exchange the user's Cloud Identity Services JWT for an Integration Suite token, and the iFlow's OData V2 receiver adapter reaches S/4HANA through Cloud Connector with Principal Propagation authentication. The Cloud Connector Subject Pattern builds the outbound certificate's CN from the token's user_name claim, which is populated from the IAS email rather than the sub claim, so identity resolution on S/4HANA hinges on that email matching a resolvable logon name.Joni, published 2026-07-10
Autonomous Diagnostics on Kyma Unplugged: Goose + LiteLLM + KRO + SAP AI Core in ProductionAutonomous Diagnostics on Kyma Unplugged: Goose + LiteLLM + KRO + SAP AI Core in ProductionAn in-cluster autonomous diagnostic pipeline on Kyma Unplugged (open-source Kyma, noted to also run on SAP BTP, Kyma runtime): a Goose agent with kubectl access calls SAP AI Core through a LiteLLM proxy, and most of the post is about the quirks of that route — drop_params silently swallowing unrecognised parameters and beta headers, streaming that has to be off when tools are attached, and prompt caching that sits on the Orchestration V2 API rather than the foundation-model path the LiteLLM provider hits. A second Node.js proxy reaches that API, and the author reports caching unconfirmed at production scale, which leaves the roughly $0.004 per static run a target rather than a measured figure. Spend metrics reach SAP Cloud Logging over OTLP through Kyma's Telemetry MetricPipeline while the health analysis itself lands in Kubernetes custom resources read in Busola, and the stack is declared as KRO Resource Group Definitions applied with one Terraform command.quovadis, published 2026-07-09
Building MCP Servers with SAP Integration Suite: What to Design, Not Just How to ConnectBuilding MCP Servers with SAP Integration Suite: What to Design, Not Just How to ConnectArgues that the tool design, not the connection, is the hard part of putting an API in front of an agent. Works one request — create a customer — through eight endpoint-shaped tools, where the agent carries ids between calls and rebuilds the business rules each run, then through a single intent-shaped create_customer that hides the sequence; and says what separates the two: a business operation for a name, parameters a caller can supply without a lookup, the rules in the server rather than the prompt, and a description written for an agent choosing a tool. The SAP Integration Suite half is short — three creation paths, an iFlow behind the API artifact when a tool has to cross systems — and it closes on a checklist to run before publishing.published 2026-07-07
SAP BTP - CI - EventSmartKafka - Custom Kafka Adapter From .ESA v1.1.0 - Validated Runtime - Part IVSAP BTP - CI - EventSmartKafka - Custom Kafka Adapter From .ESA v1.1.0 - Validated Runtime - Part IVPart IV of a series on EventSmartKafka, an open-source Kafka Consumer adapter for SAP Cloud Integration in SAP Integration Suite, built with the SAP Adapter Development Kit. The v1.1.0 release adds mutual TLS client-certificate authentication against the broker, fixes an OSGi classloader bug where a redeployed bundle's static registry lost track of a still-open relay socket from the previous classloader (fixed with a JVM-wide System-property registry instead), replaces infinite retry loops on fatal configuration errors with a fail-fast stop, corrects two offset-handling bugs in timestamp-based message recovery, adds a parallel-consumer option, and drops a planned OAuth2 strategy because no tier of the tested broker services (Confluent Cloud, Redpanda Cloud, Aiven) exposed it for testing on a free plan. The author reports the release validated across 3,000,000 messages over four simultaneous listeners (PLAINTEXT, SASL, SASL_SSL, mTLS) on an SAP BTP Trial tenant with zero failures, closing the adapter's Consumer side before a planned Producer adapter.rhviana, published 2026-06-29
Natural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesNatural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesThe division of labour is the argument, and it is in the subtitle: the model turns English into a CDS query and CDS runs it, so nothing generates SQL and nothing hallucinates a join. Schema annotations do the resolving. Long, with the package, the repository and the MCP registry entry all linked.Shahid, published 2026-06-25
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackBanking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackThe risk it is chasing is a graph problem stated in banking terms: a borrower who looks safe alone and is the linchpin of a group ten times the size. Multi-agent, mixed AI stack, on BTP and CAP.Shahid, published 2026-06-24
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI Stack
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects A recipe, Runnable code.
Beyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBeyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBuilds a rules-first error-diagnosis pipeline on Cloud Integration in SAP Integration Suite: a Groovy classifier resolves known failures — auth, timeout, malformed payload — deterministically, and only genuinely novel errors reach an LLM through the AI Adapter, after a sanitizer script replaces every payload leaf value with a typed placeholder before it leaves the tenant. SAP HANA Cloud, reached over JDBC, holds a fingerprinted dedup cache and an accumulating table of past diagnoses. It also documents the AI Adapter configuration — Advanced mode, a Bearer-prefixed Secure Parameter, and a connection/processing URL split — needed to reach a non-SAP OpenAI-compatible endpoint, found by the author to be undocumented.Krishna_Karthik, published 2026-06-11
Building an LLM Agent in CAP Java with Spring AIBuilding an LLM Agent in CAP Java with Spring AIThe Java counterpart to the author's own Node.js post, and written as one: connecting to AI Core with the SAP AI SDK, then calling an agent and a tool through Spring AI. Opens with a section on libraries and workflows — which framework does what, and what is left to you — before any code.published 2026-06-08
Building an LLM Agent in CAP Java with Spring AI
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
Calling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioCalling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioA proof of concept wiring SAP AI Core's Claude deployment directly into ABAP with no CAP layer between them: two SM59 HTTP destinations, a hand-written OAuth 2.0 client-credentials exchange, and a regex to unwrap Claude's system/messages response envelope. Most of the effort goes into a system prompt that constrains the model to return one fixed JSON schema of filter fields, which ABAP deserialises with /UI2/CL_JSON and exposes through a RAP custom action so a Fiori search field can drive an OData V4 filter.PranayGaroo, published 2026-06-04
SAP Document AISAP Document AISAP's reference architecture for SAP Document AI, first as SAP composes the service on BTP for document extraction: OCR, pretrained models, customer-defined schemas and LLM calls through SAP AI Core and its Prompt Registry in one pipeline, with tenant-isolated persistence in SAP HANA Cloud, PostgreSQL and an object store. Its scenario pages then lay out a solution in three layers: intake through Outlook and SharePoint inbound channels, the workspace UI, the Joule Work mobile app or the upload API; classification and extraction with a confidence score per field, automatic confirmation above a threshold and review of the rest in the workspace; and posting through outbound channels, directly to a REST API, through an SAP Integration Suite flow, or through a CAP service that maps the fields and calls SAP S/4HANA over OData. Enrichment beyond the service's own master data lookup is left to a CAP application or an Integration Suite flow triggered from an outbound channel, and direct API posting leaves error handling, retries and monitoring to the application.published 2026-06-03
SAP BTP - CI - Building Open-Source Custom Adapter EventSmartKafka from Zero with SAP ADK - Part IISAP BTP - CI - Building Open-Source Custom Adapter EventSmartKafka from Zero with SAP ADK - Part IIPart II of a series on EventSmartKafka, an open-source Kafka adapter for Cloud Integration in SAP Integration Suite built with the SAP Adapter Development Kit, walks through the runtime behind a custom adapter: how metadata.xml's fields map onto Java Endpoint properties, how the Component class creates the Endpoint, and how the Consumer's doStart() and doPoll() poll Apache Kafka, convert Avro payloads and dispatch the record into the iFlow pipeline. Its central point is that the Kafka offset must be committed only after the pipeline has processed the message successfully, with a worked table of which failure scenarios (missing Confluent magic byte, invalid schema ID, payload over the configured limit) withhold the commit versus let it through, to avoid poison-pill loops and silent message loss. The adapter is published as a community demo and not SAP-certified or production-validated; Part III covers building the SAP ADK project itself.rhviana, published 2026-06-03
Managing JMS Queues Programmatically with the new SAP Cloud Integration JMS OData APIManaging JMS Queues Programmatically with the new SAP Cloud Integration JMS OData APIThe new JMS OData API on Cloud Integration exposes MessagingQueues and MessagingMessages entities, letting a client list, inspect, retry and move JMS messages without opening the monitoring UI, from Cloud Integration 7.52.x on Cloud Foundry and 8.41 on the Edge Integration Cell runtime. It works through OAuth 2.0 client-credentials authentication against a Process Integration Runtime service instance, a fixed row cap with time-window slicing used in place of offset paging because queues change between requests, and a consistent OData error envelope for the codes the surface returns.MarcoKoch, published 2026-06-01
SAP BTP - CI - How I Built an Open-Source Enterprise Custom Kafka Adapter from Scratch - Part ISAP BTP - CI - How I Built an Open-Source Enterprise Custom Kafka Adapter from Scratch - Part IPart I of a series on EventSmartKafka, an open-source Apache Kafka adapter the author built with the SAP Adapter Development Kit to extend SAP Cloud Integration in SAP Integration Suite past the standard adapter's offset management, security options and Avro handling. It covers the architecture: granular offset control via seek(), a security UI that switches between SASL, mutual TLS and OAuth profiles, native Avro-to-JSON/XML conversion against a Schema Registry, configurable resilience policies, and on-premise reach through Cloud Connector. The adapter already runs against a live Confluent Cloud Kafka topic in a real tenant; the source code follows from Part II onward.rhviana, published 2026-05-29
Building an LLM Agent using CAPBuilding an LLM Agent using CAPThe argument is that CAP is already most of what an agent framework wants — services, handlers, a typed model — so the agent is built inside it rather than beside it. AI Core through sap-ai-sdk, then Langchain for the agent and its tools. Long, with a TLDR at the top for people who want the shape without the walk.published 2026-05-27
Building an LLM Agent using CAP
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
SAP BTP - CI - Immutable Event Routing per Domain with Metadata-Driven Consumer OrchestrationSAP BTP - CI - Immutable Event Routing per Domain with Metadata-Driven Consumer OrchestrationDescribes a metadata-driven "Smart Router" pattern for Cloud Integration in SAP Integration Suite: one Kafka Sender Adapter per domain reads a wildcard topic, and a single immutable router iFlow resolves single, multiple or both consumers at runtime from Value Mapping entries and a Groovy script, instead of one adapter and iFlow per consumer added. It compares three candidate architectures — a two-layer router/dispatcher split, the recommended single-layer router, and a rejected global cross-domain router — and covers AVRO payload handling through Base64 and an externalized schema parameter, and consolidating the routing logic into one cached Groovy class to limit JVM class-loading overhead. The piece continues the author's earlier immutable Kafka topic routing post and names SAP Event Mesh as one of several broker-agnostic alternatives to the Kafka adapter used here.rhviana, published 2026-05-25
SAP Cloud Integration (CI/CPI) - Reusable Script Collection Pattern for Sensitive Data MaskingSAP Cloud Integration (CI/CPI) - Reusable Script Collection Pattern for Sensitive Data MaskingOpens with the question compliance teams ask about Cloud Integration, whether an integration team based outside Europe with Message Monitoring access can read the personal data in a logged payload, and answers that in most standard configurations it can. The pattern against it is a reusable Groovy script collection plus one global variable holding the masking rules: a script near the start of an iFlow AES-encrypts the original payload into a header or property and replaces values in the body by value pattern first and field-name keyword second, a second script restores the original just before the sender, so a Log Payload step anywhere in the flow captures the masked body while the target system still receives the real data. The post names its own limits, that pattern-based masking is heuristic and that CPI trace can capture the payload before the scripts run, and grounds the pattern in GDPR Articles 5(1)(f), 25, 32 and 44-49, reading the EDPB's Guidelines 05/2021 to mean that access from a country without an EU adequacy decision, uncovered by Standard Contractual Clauses or another valid transfer mechanism, can itself constitute a cross-border transfer.AdarshRao, published 2026-05-25
Intelligent Error Handling in SAP CPI Using AI AdapterIntelligent Error Handling in SAP CPI Using AI AdapterAdds an AI Receiver Adapter to an Exception Subprocess in Cloud Integration, so a failed iFlow sends its captured exception text to an LLM over a chat-completions endpoint and gets back an error summary, cause and resolution for the sender. The walkthrough is concrete about the flow's own mechanics — Security Material for the API key, the adapter's address and request body, a Content Modifier to extract and return the response — which is why it explains Integration flows rather than only the AI feature riding on top of them.Jayesh8909, published 2026-05-21
SAP Integration Suite - External logging to Datadog Using OpenTelemetrySAP Integration Suite - External logging to Datadog Using OpenTelemetrySoftware version update 8.42 of SAP Cloud Integration added OpenTelemetry as an external logging destination for Message Processing Logs, so a tenant can stream them straight to an OTLP-compatible platform such as Datadog. The post walks the full path on Cloud Integration: a BTP HTTP destination carrying the Datadog API key as a header property, a Process Integration Runtime service instance holding the ExternalLoggingActivate role, and the activateExternalLogging API call that turns the stream on, down to parsing the resulting log bodies in Datadog's pipelines. It also records a known limitation: custom-header timestamps arrive at Datadog unset, so only Run Events carry a usable time.Santhosh_Vellingiri, published 2026-05-18
Batch File Pickup and Dynamic ZIP Creation in SAP Integration SuiteBatch File Pickup and Dynamic ZIP Creation in SAP Integration SuiteWalks through configuring a Cloud Integration flow that polls an SFTP server for batches of ten files, using a Content Modifier to preserve each file's name and body before appending them into one temporary file. A Router and Poll Enrich step detect when the batch is complete, a General Splitter breaks the combined payload back into individual messages, and a Gather step reassembles them into a dynamically named ZIP archive that keeps the original filenames, before the archive is sent on to a target SFTP server.sahilminhas, published 2026-05-07
Agentic AI on BTP: a Multi‑Agent App with Pydantic AIAgentic AI on BTP: a Multi‑Agent App with Pydantic AISplits a single CAP/TypeScript agent that had grown to juggle five BTP MCP servers behind one bloated tool list into btp-multiagent-app, a Python and Pydantic AI rewrite where the Cloud Foundry and BTP Core MCP servers each get a dedicated specialist agent, with an audit log specialist scaffolded but left disabled, behind an orchestrator whose only tools are delegation calls to those specialists, which is the agent-tooling pattern the piece works through. Each specialist authenticates to its MCP server over Streamable HTTP with OAuth 2.1, and a shared module centralises the SAP AI Core GenAI Hub model setup behind two credential layouts, one for local runs and one for the Cloud Foundry service binding, the LLM integration side of the rewrite. Tool lists per agent drop from well over a hundred to a dozen or two, and routing failures become separable from tool-misuse failures by reading the trace.published 2026-05-03
Agentic AI on BTP: a Single Agent with LangGraphAgentic AI on BTP: a Single Agent with LangGraphA CAP TypeScript agent puts a LangGraph StateGraph in front of AzureOpenAiChatClient from @sap-ai-sdk/langchain, reaching SAP AI Core's Generative AI Hub, and lets its tool-calling loop draw on five deployed MCP servers — OData MCP Proxy, CI MCP Server, AI Core MCP Server, BTP MCP Server and BTP CF MCP Server — through @langchain/mcp-adapters' MultiServerMCPClient. Because agent, servers and APIs share one XSUAA tenant, the chat service forwards the signed-in user's own JWT instead of a service account, so each downstream server enforces that user's own authorizations. Past roughly a hundred combined tools the single prompt slows down and stops separating concerns, which is why the author's next post splits it into one specialist agent per MCP server behind an orchestrator.published 2026-05-03
Enhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginEnhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginStarts from the blank form nobody wants to fill in, and asks what an enterprise application should do about it. The AI is in service of that rather than the subject of it.published 2026-04-29
What Happens to Your Data When You Enable SAP's AI Features?What Happens to Your Data When You Enable SAP's AI Features?Traces where a prompt goes when Joule, the Generative AI Hub or the orchestration service calls a third-party model through SAP AI Core: the prompt and the business context around it travel to a model such as GPT-4o, Claude or Gemini for inference, and masking through SAP Data Privacy Integration is an optional orchestration module rather than a default, so with no masking block in the @sap-ai-sdk/orchestration client config nothing is masked. On the masking options, which the author says he confirmed with SAP AI Core product management, anonymization discards the original value and pseudonymization keeps it reversible; DPI recognizes person names, email addresses and phone numbers, plus custom entities defined by regex, which leaves commercially sensitive non-PII such as a revenue forecast or a project codename to pass through unless someone writes a pattern for it, and whether that data is covered at all is one of three answers the post marks as still pending. The "no training" assurance for third-party providers is read as contractual rather than technical, and models hosted and managed by SAP, Mistral among them, are named as a path other than a US-hyperscaler-hosted one.jaripie, published 2026-04-23
Integrate CAP application as outbound channel for SAP Document AIIntegrate CAP application as outbound channel for SAP Document AIDocument AI will call you back when extraction finishes, and the callback is where this goes wrong: the CAP application has to accept an unauthenticated POST from outside without dropping CSRF protection for everything else. The answer is a middleware hooked into the CAP bootstrap, and the post spends its length on the token lifecycle rather than on the extraction.sdeissenboeck, published 2026-04-22
End to End Currency Conversion Integration using SAP Integration Suite (SAP CPI)End to End Currency Conversion Integration using SAP Integration Suite (SAP CPI)A hands-on build of a currency-conversion integration flow in Cloud Integration: an HTTPS sender adapter takes JSON input, a Request-Reply step calls an external exchange-rate API, and a Groovy script converts the amount and formats it as an HTML table before a Mail Adapter delivers the result. Most of the walkthrough is the Exception Subprocess added after hitting HTTP 500 and 429 errors in testing, which captures the error message, response code and message-processing-log ID and turns them into a readable response instead of a raw stack trace.shahabaz, published 2026-04-09
Message Mapping in SAP Integration Suite - Custom Scripts and Conditional MappingMessage Mapping in SAP Integration Suite - Custom Scripts and Conditional MappingWalks through two ways to extend a message mapping step in SAP Integration Suite's Cloud Integration: a custom Groovy function added in the Mapping Expression editor's Scripts section, and a graphical equals/if node pair built from the standard function library, each suited to logic the other cannot express cleanly. Shows the Simulate tool's Generate button building a test payload from the source structure, then editing individual field values to exercise both the true and false branch of a condition before deployment.jirifridrich, published 2026-04-03
Building a Real‑Time Currency Conversion iFlow using SAP Cloud Integration (CPI)Building a Real‑Time Currency Conversion iFlow using SAP Cloud Integration (CPI)A step-by-step build of a currency-conversion integration flow in Cloud Integration: an HTTPS sender adapter accepts JSON, a content modifier stores the currencies and amount as exchange properties, and a Request-Reply step calls an external rate API before a Groovy script renders the result as an HTML table. A Global Exception Subprocess centralizes error handling for the whole flow, turning the MPL ID, error type and message into HTML and mailing it as a notification to a support address.RajeshwerRao_G_1, published 2026-04-01
Centralized Error Handling in SAP Cloud IntegrationCentralized Error Handling in SAP Cloud IntegrationBusiness integration flows in Cloud Integration route their runtime errors to a shared Central Error Logger flow through an Exception Subprocess and a ProcessDirect adapter, instead of each flow handling failures on its own. The logger normalises the incoming error data — flow name, message ID, correlation ID, timestamps — and formats it into an HTML email sent through a Mail Receiver Adapter. The author validated the same logger flow, unchanged, against a second, more complex business flow with routers and multiple email notifications.vishaladhikari, published 2026-03-27
Integrating a Custom AI Model into SAP CAP Using AI LaunchpadIntegrating a Custom AI Model into SAP CAP Using AI LaunchpadYour own model rather than a hosted one: deployed to AI Core, made callable through AI Launchpad, then reached from CAP. The case a lot of companies ask about and few posts cover.egeAksoyek, published 2026-03-20
Integrating a Custom AI Model into SAP CAP Using AI Launchpad
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
End-to-End Mail Adapter Setup in SAP CPI Using Gmail (Step-by-Step Guide)End-to-End Mail Adapter Setup in SAP CPI Using Gmail (Step-by-Step Guide)Walks through configuring Cloud Integration's Mail Receiver Adapter against a personal Gmail account: enabling 2-Step Verification and an app password in Gmail, storing it as CPI security material user credentials, and testing the SMTP connection (smtp.gmail.com, port 587, STARTTLS) before wiring the adapter into an integration flow. A content modifier builds the message body, and a Postman call triggers the flow to send mail through the configured Gmail account.srivallivasamsetti, published 2026-03-09
SAP Integration Suite: Intelligent Integration with AI AdapterSAP Integration Suite: Intelligent Integration with AI AdapterThe AI Adapter adds generative AI as a receiver step inside a Cloud Integration flow, connecting through either AICore-GenAIHub — a single API onto SAP AI Core's Generative AI Hub and its foundation models — or Custom-OpenAI-Rest, a plain REST call out to a provider such as OpenAI. SAP Integration Suite starts the call from the iFlow and feeds the model's response into the next step, which is the mechanics behind the sentiment-analysis, summarisation and routing use cases the piece lists without walking through any one of them.meena_choudhary, published 2026-01-28
cds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPcds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPNames a cost most CAP-plus-LLM writing ignores: every JSON payload streamed to a model is billed by its verbosity, in latency as well as money. The plugin brings TOON — Token-Oriented Object Notation — to a CAP service so the wire format changes without the service code doing so, in a REST variant and an OData one, with token counts reported on both sides.published 2026-01-25
UI5 MCP Server Got Extended for UI Integration Cards GenerationUI5 MCP Server Got Extended for UI Integration Cards GenerationVersion 0.2.1 of the UI5 MCP Server adds three tools for UI Integration Cards: get_integration_cards_guidelines feeds an agent current best practices and API versions, create_integration_card scaffolds a new card project, and run_manifest_validation checks the generated manifest against the schema. The post frames these as closing the same gaps as the server's existing tools — an LLM's outdated or wrong card API knowledge — this time for scaffolding and validating a card rather than a full app.daniel_vladinov, published 2026-01-22
Stop Building From Scratch: Unlocking SAP Cloud Integration’s Standard ContentStop Building From Scratch: Unlocking SAP Cloud Integration’s Standard ContentArgues against building integrations from scratch by pointing to the Discover space of Cloud Integration: over 700 prebuilt integration packages and nearly 4000 iFlows, covering common scenarios such as S/4HANA-to-Salesforce business-partner and order sync, included at no extra cost under an SAP Integration Suite licence. Walks through where to find and copy a package, and the support trade-off it creates: SAP keeps supporting the standard baseline, but once a flow is directly modified the customer owns the lifecycle of that change, which the author sets against patterns like overlay mappings and wrapper orchestrators that preserve support.Punith_Oswal, published 2025-12-19
Enhancing Business Processes with SAP BTP AI in SAP Integration SuiteEnhancing Business Processes with SAP BTP AI in SAP Integration SuiteWalks through a post-exit iflow in SAP Integration Suite that calls an LLM through SAP AI Core's Generative AI Hub to turn a customer's free-text return comment into one of a fixed set of SAP rejection-reason codes, so an inbound ORDERS05 IDoc carries a decision (E1EDP01-ABGRU) the ERP can act on without pausing for manual review. The worked example is a Commerce Cloud returns flow into S/4HANA; the piece argues the same bounded-classification pattern fits other narrative fields — delivery-exception remarks, expense-claim justifications — where the cost of an LLM call is repaid by removing a human review step, and points to a colleague's post on the Generative AI Hub orchestration workflow for the guardrailing (prompt templating, data masking) it only names.arunmaarirajha_kv, published 2025-12-15
Prompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesPrompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesA user story in, a scaffolded full-stack CAP application out, through SAP Build Code and Joule. The question it is actually asking is how much of the foundational code is worth generating, and it answers by generating all of it.AnuradhaDhingan, published 2025-12-11
Parallel Data Filtering and Dropbox Integration Using SAP Cloud IntegrationParallel Data Filtering and Dropbox Integration Using SAP Cloud IntegrationA step-by-step build of an integration flow in Cloud Integration: a Start Timer triggers the flow, a Parallel Multicast splits student records by gender through XPath filters, and each branch uploads its file to Dropbox over a Receiver Adapter authorized against a Dropbox app's OAuth2 credentials. An Exception Subprocess captures the error message and a Mail Adapter sends it over SMTP, centralizing error handling and an email notification for the whole flow.Vurumind03, published 2025-12-10
Microsoft GRAPH API - Read and extract attachments of Outlook email from Cloud IntegrationMicrosoft GRAPH API - Read and extract attachments of Outlook email from Cloud IntegrationBuilds an integration flow in Cloud Integration that authenticates to the Microsoft Graph API with an OAuth2 Client Credentials credential and an HTTP Receiver Adapter, then calls the Outlook inbox by MessageID to retrieve an email's attachment. A Groovy script using the pdfbox and fontbox libraries extracts the text from a PDF attachment, as an alternative to placing the attachment on SFTP unchanged or fetching the whole message with its attachment through the $value query.ChaithraShanmugam, published 2025-12-09
SAP Neo Retires – Integration Developers Must Know Before Migrating from Neo to CFSAP Neo Retires – Integration Developers Must Know Before Migrating from Neo to CFWalks through what changes when Cloud Integration moves from the Neo environment to Cloud Foundry under SAP Integration Suite: custom adapters move from an Eclipse-plugin deployment to Integration Adapter artifacts managed in Cloud Integration's Design and Monitor applications, Neo's environment variables (HC_APPLICATION, HC_HOST, HC_REGION and others) map to Cloud Foundry's TENANT_NAME, VCAP_SERVICES and PORT, and OAuth clients for API access move from Neo administration tools to XSUAA under Integration Suite. Covers the same shift for security materials, transport management and monitoring, ahead of Neo's end of maintenance on 31 December 2028.SivaS, published 2025-12-03
SAP EHS Public Cloud: Extending Your Existing Landscape Side-by-Side - Guidebook (Part 4)SAP EHS Public Cloud: Extending Your Existing Landscape Side-by-Side - Guidebook (Part 4)Two custom iFlows in SAP Integration Suite subscribe over AMQP to Event Mesh queues, triggered by SAP S/4HANA On-Premise's Enterprise Event Enablement channels publishing Equipment and Functional Location changes; each flow calls the on-premise OData API, maps the result, and pushes it into SAP S/4HANA Cloud Public Edition through the SAP_COM_0395 communication scenario. The synchronized Plant Maintenance data feeds SAP EHS Public Cloud's risk management, incident management and emissions management processes, which otherwise have no asset master data of their own.duynguyendeloitte, published 2025-11-28
Use Datastore to avoid too many duplicate MPL attachments in exception retriesUse Datastore to avoid too many duplicate MPL attachments in exception retriesWalks through an Integration flows design on Cloud Integration: an exception subprocess that writes the source and in-flight payloads to a DataStore entry, keyed by the message's correlation header and overwritten on each retry, instead of a Groovy script attaching both payloads to the message processing log on every run. With unrestricted retries left in place, one interface the author retried 14 times produced two DataStore entries instead of up to 28 message processing log attachments; the post also notes that deleting the DataStore entry for a retrying message marks it Cancelled in monitoring without stopping the retries.pdimri, published 2025-11-26
Streaming LLM Output with CAP and WebSocketsStreaming LLM Output with CAP and WebSocketsTokens arriving from the AI SDK's orchestration module, forwarded to the browser as they come rather than after the model finishes. Covers all four pieces — enabling WebSocket support in CAP, a service with actions and events, the streaming itself, and a frontend on the native WebSocket API — which is what makes it the clearest case for why a CAP service would want a socket at all.RobinP, published 2025-11-18
Streaming LLM Output with CAP and WebSockets
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A recipe, Runnable code.
Joule in SAP Build Code can now create freestyle UI5 appsJoule in SAP Build Code can now create freestyle UI5 appsJoule in SAP Build Code adds a new slash command, /ui5-create-app, that scaffolds a freestyle UI5 app outside any existing UI5 project. Typed inside a CAP workspace, it offers sample prompts built from that project's own entities and services, with the property list and service URL extracted by deterministic code rather than asked of the LLM, to avoid hallucinated property names; the 30-plus files of the resulting app come from predefined templates rather than model-written code. The LLM is left free to refine the setup afterward, understanding informal follow-up requests and declining ones the template cannot fulfil.AndreasKunz, published 2025-11-13
How to Reduce Prompt Token Costs Using Toon = Save MoneyHow to Reduce Prompt Token Costs Using Toon = Save MoneyToken spend treated as a running cost rather than a detail, and TOON as the lever. Companion reading to the CAP adapter for the same format that is indexed here.Yogananda, published 2025-11-12
How to Reduce Prompt Token Costs Using Toon = Save Money
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A recipe, Runnable code.
Beyond REST: Exploring GraphQL API Integration in SAP BTP Integration SuiteBeyond REST: Exploring GraphQL API Integration in SAP BTP Integration SuiteBecause Cloud Integration in SAP Integration Suite ships no native GraphQL adapter, the author builds a GraphQL integration flow on the standard HTTP adapter: a Groovy script assembles the query or mutation payload and sets the JSON content type, and a JSON-to-XML converter turns the response into something message mapping can consume. The walkthrough uses the public Countries API to stand in for a real order-synchronisation flow between an e-commerce platform and SAP S/4HANA.Avinash_Vaidya, published 2025-11-11
SAP集成套件中的Cloud Integration云集成功能概况介绍SAP集成套件中的Cloud Integration云集成功能概况介绍An overview of Cloud Integration within SAP Integration Suite: it positions Cloud Integration as the execution engine that processes and moves messages between systems, working alongside Integration Advisor, Trading Partner Management and API Management. It walks through building an integration flow in the low-code editor — connecting over HTTP/OData or RFC with built-in connectors and prebuilt content, transforming and mapping messages, then deploying and monitoring the flow — and closes by naming PI/PO Move, SAP's tooling to assess and migrate existing PI/PO integration content into the suite.ArthurYang, published 2025-10-28
DIY JDBC Sender Adapter for SAP Integration SuiteDIY JDBC Sender Adapter for SAP Integration SuiteSimulates the JDBC Sender Adapter that SAP Integration Suite dropped from SAP PO by polling a source database with a Request/Reply step, triggered by a configurable scheduler or a manual HTTP call, and writing the result to a DataStore or JMS Queue to decouple polling from mapping and insertion. Retries run against a configured maximum, a failed batch escalates to a Dead Letter Queue once they are exhausted, and a mapping failure skips retries and escalates straight away from its own local subprocess. The author reports migrating several SAP PO scenarios onto this flow design and offers a reusable template on request.lanza, published 2025-10-21
Designing Scalable Integration Flows in SAP BTP Using Pallets and AdaptersDesigning Scalable Integration Flows in SAP BTP Using Pallets and AdaptersExplains two building blocks of integration flows in SAP Integration Suite: a pallet, a reusable group of flow steps built as its own integration flow and called from another over the ProcessDirect adapter for loose coupling, with logging, transformation, error-handling, notification and security pallets as examples; and the adapters Cloud Integration ships to reach other systems — REST, SOAP, OData, IDoc, JDBC, ProcessDirect and SFTP — each with the protocols and authentication it supports. Written as a design pattern for reuse across flows rather than a single worked example.Saksham-Mutneja, published 2025-10-16
Integrating SAP Document Information Extraction (Document AI) with SAP CAP – Step by StepIntegrating SAP Document Information Extraction (Document AI) with SAP CAP – Step by StepThe forward direction, in full: a PDF or scan arriving at a CAP service, sent to Document Information Extraction, and the fields coming back into the model. Long, and step-by-step in the literal sense — the service binding and the request shapes are all written out.furkan5, published 2025-10-09
New CI Pipeline Restart Extension features: supporting new Pipeline package and improved Restart JobNew CI Pipeline Restart Extension features: supporting new Pipeline package and improved Restart JobA restart extension for Cloud Integration pipelines, in version 1.0.1: a Value Mapping or a technical-ID prefix check resolves which pipeline stage a failed message belongs to, so a custom receiver IFlow copy can be linked to the right stage even when its ID does not follow the standard naming, and a Generic Job Profile restarts every scenario resolved through the Alternative Partner approach instead of only the interfaces named in a fixed list. A new RestartJobLog parameter stores each run's log as a Message Processing Log attachment, in the database, or via a custom IFlow, and a companion "Pipeline API – Restart Job Log" Integration Flow retrieves that log or the Restart Job's own MPL details. The walkthrough is concrete about the Integration Flows, Value Mapping and Script Collection that make up the package, which is why it explains Integration flows rather than only the restart feature riding on top of them.slava_kuzyakin, published 2025-10-02
Service Interfaces and ABAP Proxy generation support in SAP Integration SuiteService Interfaces and ABAP Proxy generation support in SAP Integration SuiteWalks through importing Service Interface artifacts from an on-premise ES Repository into Cloud Integration in SAP Integration Suite: configuring Cloud Connector and the ES Repository connection, then a wizard that lists and imports the repository's interfaces with their dependent resources. It also covers generating ABAP Proxies so an SAP R/3 or S/4HANA system can reach the Integration Suite tenant, pointing to a companion post for the SM59 destination side of that setup.radhika_javvaji, published 2025-09-18
Lessons Learned: Fetching Learning History from SuccessFactors LMS Using OData APIsLessons Learned: Fetching Learning History from SuccessFactors LMS Using OData APIsA walkthrough of pulling SuccessFactors LMS Learning History records through its OData V4 API: the mandatory criteria/targetUserID filter, the errors that appear without it, and the $metadata endpoint used to confirm entity names, since the API returns one student at a time and never in bulk. Builds the integration flow in Cloud Integration as a Groovy script that loops over a list of student IDs, calls the API with a bearer token per student and aggregates the JSON responses into one payload.aayushaggarwal, published 2025-09-17
Exploring SAP Salesforce Adapter - retry mechanism with JMS queueExploring SAP Salesforce Adapter - retry mechanism with JMS queueBuilds a retry design for Salesforce update failures in Cloud Integration on SAP Integration Suite: a Parent iFlow triggered by a Salesforce push topic calls a Child iFlow, whose Exception Subprocess routes specific Salesforce errors to a separate JMS Retry PD iFlow over a ProcessDirect target address. The retry iFlow stores the failed payload in a JMS queue (Enterprise Edition), retries up to five times with exponential backoff, moves exhausted messages to the dead-letter queue, and mails the Application Maintenance team; the author notes the queue's 10 GB size limit and that polling may pause under load.Shailaja, published 2025-09-05
Generative AI on SAP BTPGenerative AI on SAP BTPThe reference shape for a generative AI application on BTP: a CAP backend, SAP HANA Cloud holding data and embeddings for similarity search through its vector engine, and the Generative AI Hub in SAP AI Core as the single access point to foundation models. It shows retrieval-augmented generation on that stack and names the CAP plugins and SDKs that connect the pieces, for both Cloud Foundry and Kyma.published 2025-09-02
Generative AI on SAP BTP
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A reference.
Cloud Integration with Document AICloud Integration with Document AIWalks through connecting Cloud Integration to SAP Document AI: an iFlow posts a prescription PDF to Document AI's job API, polls the job endpoint until it completes, and a groovy script reads back the result, keeping only the fields above a stated 60% confidence threshold. The scenario is a hospital extracting a new patient's past illnesses, allergies and blood group from uploaded prescriptions, matched against a custom extraction schema.PriyankaChak, published 2025-08-10
Optimized IDoc Routing in SAP CI with Value Mapping and Groovy-Based Receiver DeterminationOptimized IDoc Routing in SAP CI with Value Mapping and Groovy-Based Receiver DeterminationShreyasShenoy07 replaces SAP PI/PO's single shared IDoc destination with a receiver-determination pattern built in Cloud Integration: a generic iFlow reads the IDoc's EDI_DC40 header, looks up the sender identifier and the receiver list in two Value Mapping tables keyed by sender system and IDoc type, and a Groovy script evaluates each receiver's XPath condition before routing the message to a receiver-specific iFlow over the ProcessDirect adapter. Adding or changing a receiver becomes a Value Mapping edit instead of an iFlow redeployment, and the same IDoc can fan out to several receivers when more than one condition matches.ShreyasShenoy07, published 2025-08-08
How to use Cloud SDK for AI in an existing CAP NodeJS Project in CommonJSHow to use Cloud SDK for AI in an existing CAP NodeJS Project in CommonJSA dependency that is ESM-only inside a project that is CommonJS, and the author's judgement that converting the project was too risky. What follows is the esbuild workaround, which is the honest answer when the ecosystem has moved and your codebase has not.Jacky_Liu1, published 2025-08-01
Process Integration Pipeline Extension - Restart via Data StoreProcess Integration Pipeline Extension - Restart via Data StoreOn SAP Cloud Integration's Process Integration Pipeline, a message that exhausts its JMS retries lands in a Dead Letter Queue with no API to query or move it, and the JMS broker carries a hard size limit. This package, published on SAP Business Accelerator Hub, replaces that path with Data Store entries written through the pipeline's custom exception-handling exit, a scheduled Restart Job Integration Flow, and two optional HTTP APIs for on-demand restarts and Data Store management. Entry names encode the partner ID, the pipeline stage, the message ID and a retry count, so messages can be filtered and restarted by scenario instead of moved one by one in the queue monitor.mate_moricz, published 2025-07-23
Improving Exception Handling using Generative AI in SAP Cloud Integration (SAP CI/CPI)Improving Exception Handling using Generative AI in SAP Cloud Integration (SAP CI/CPI)Wires an Exception Subprocess in Cloud Integration to send a failed iFlow's caught exception text to Google Gemini's generateContent endpoint over the HTTP adapter, then parses the response in Groovy for a user-friendly error message, the likely causes, the steps to try and an HTTP status code to return to the sender. A Content Modifier holds the API key and the prompt as externalised properties, which the post says is what lets another model be put in their place, and a closing Groovy script writes the extracted fields to custom headers and log attachments and rebuilds them as an XML error response. The exception-subprocess wiring is given step by step and so is the Gemini call with its request format, which is why the piece sits on integration flows and on LLM integration.AdarshRao, published 2025-07-20
Automating iFlow Documentation with SAP Integration Suite and Gemini AIAutomating iFlow Documentation with SAP Integration Suite and Gemini AIAn integration flow built from Cloud Integration's own steps — timer start, parallel multicast, process calls, join and gather, and a data store write — retrieves another iFlow's design-time metadata and resources (Groovy scripts, XSLT mappings, EDMX schemas) through the IntegrationDesigntimeArtifacts OData API on SAP Integration Suite. The walkthrough gives each flow step's configuration, the OData endpoints and sample request/response payloads, and an exception subprocess for error logging, before assembling the retrieved XML and posting it to Google's Gemini API to generate a technical specification document stored back in a datastore.Andrew-Fawzy, published 2025-07-18
Using SAP managed iFlows for Time series data Integration in SAP IBP – Part 2 - Writing dataUsing SAP managed iFlows for Time series data Integration in SAP IBP – Part 2 - Writing dataWalks through building a custom integration flow in Cloud Integration that writes time-series and master data into SAP IBP by calling the SAP-managed reusable iFlows behind communication scenario SAP_COM_0931, which consume RFC function modules through a communication user. It details the BTP destination needed to reach them (Type RFC, Proxy Type Internet, and the jco.client.* properties), and the main-flow and local-integration-process design — payload validation in a Groovy script, batch creation, then the XML attributes and payloads for posting master data and key-figure values and for triggering post-processing.Domnic, published 2025-07-18
End-to-End Error Handling with General Splitter and Local FlowsEnd-to-End Error Handling with General Splitter and Local FlowsA Cloud Integration iFlow splits an incoming XML payload with the General Splitter, calls an OData service in parallel for each part and gathers the results, then hands a failed call to an Exception Subprocess, where a Process Call reaches a Local Integration Process that calls a separate exception-handling iFlow over ProcessDirect. In that second flow a Content Modifier puts the interface ID and the stack trace into message headers and the tenant, flow and message ID into exchange properties, a Groovy script saves the message as a plain-text log attachment, and the Mail adapter sends the stack trace as an email; the failure itself is provoked by removing the https prefix from the OData URL. Each step is given with its own configuration, from the splitter's XPath and batch size to the ProcessDirect address format and the headers the exception handler sets.NaveenReddy_06, published 2025-07-02
SAP SOAP Sender & Receiver Adapters: Your Integration Game ChangersSAP SOAP Sender & Receiver Adapters: Your Integration Game ChangersA step-by-step build of two integration flows in Cloud Integration: a SOAP Sender Adapter, bound to an uploaded WSDL, that extracts an order number from an inbound SOAP request via XPath and enriches it with a shipment date fetched from the public Northwind OData service before mapping the result back into the SOAP response. A second flow's SOAP Receiver Adapter takes the reverse path, converting an inbound JSON request to XML and forwarding it to that first flow's SOAP backend, authenticated with Basic auth against a WSDL-derived operation name.Rishikasairi, published 2025-06-24
SFTP Authentication Setup in SAP BTP Integration Suite: A Step-by-Step Guide.SFTP Authentication Setup in SAP BTP Integration Suite: A Step-by-Step Guide.A walkthrough of configuring the SFTP adapter's three authentication modes in Cloud Integration — username/password, public key and dual — each set up through Security Material and a Known Hosts entry generated from an SSH key pair. The sender and receiver integration flows it builds convert an OData response to CSV and move the file over SFTP, exercising the adapter and message-conversion steps the flow editor provides.NaveenReddy_06, published 2025-06-24
New Pipeline for Cloud Integration features with version 1.0.11New Pipeline for Cloud Integration features with version 1.0.11Version 1.0.11 of the Process Integration Pipeline package for Cloud Integration changes two defaults the post says require attention. The "tilde option", which built a partner ID by joining the sender system and interface names, is now switched off: a message whose partner ID cannot be resolved through an alternative partner goes into an error that is resolved by fixing the Partner Directory entry and restarting the message, instead of being constructed under an ID that may not exist there and left on the first JMS queue with no way to correct its partner ID header. Keeping the old behaviour means setting the externalised parameter CustomXPid_SwitchOffTilde to false in the five generic flows that call the partner-ID script; the default inbound processing queue also moves from PIPQ01 to PIPX01 in the generic XI and IDoc inbound flows, so those messages go to the integrated messaging runtime rather than the fully decoupled pipeline.alex_bundschuh, published 2025-05-07
LeanIX Adapter for SAP Integration SuiteLeanIX Adapter for SAP Integration SuiteA walkthrough configures the LeanIX Adapter for SAP Integration Suite's Cloud Integration runtime, wiring its Receiver Adapter with an Address, API Token Alias and LeanIX OAuth authentication inside an integration flow. It demonstrates a REST scenario that creates a FactSheet and fetches one by ID, and a GraphQL scenario that updates a FactSheet through the adapter's Advanced Query operation.Swati_Singh1, published 2025-04-29
Edge Integration Cell on HyperscalersEdge Integration Cell on HyperscalersSAP's architecture for Edge Integration Cell, the runtime of SAP Integration Suite that executes integration flows in a Kubernetes cluster the customer runs, while design, monitoring and governance stay on SAP BTP and the runtime reaches BTP over outbound-only channels. The main page gives the reasons SAP names for it: data residency, security policies that forbid inbound access, and latency to a distant BTP region. Three sub-pages draw the same setup on AWS, Azure and Google Cloud, each with a private network across three availability zones, a managed Kubernetes cluster, managed PostgreSQL and Redis, sizing left to an SAP Note, and each says it outlines a small production deployment to be treated as a starting point.published 2025-04-18
Lets Talk to the Database - CAP & SQLite Powered by Google Gemini-2.5-ProLets Talk to the Database - CAP & SQLite Powered by Google Gemini-2.5-ProNatural language against a CAP service on SQLite, with a non-SAP model doing the translation. Written as a learning exercise rather than a pattern, and the choice of Gemini over anything in the AI hub is the interesting part of it.ShivamShuklaSAP, published 2025-04-16
How to Perform Initial Loads from S/4HANA to Advanced Event Mesh with Odata PollHow to Perform Initial Loads from S/4HANA to Advanced Event Mesh with Odata PollWalks through building a Cloud Integration flow that polls the S/4HANA Business Partner OData API on a timer, splits the response into individual records, and publishes each as an event to Advanced Event Mesh through its adapter, with the topic set dynamically from a grouping property. Selects fields and expands associations with $select/$expand against an EDMX from the API Business Hub, and works around the OData V2 adapter's lack of JSON support by falling back to the HTTP adapter with an XML-to-JSON converter. Flags the trade-off: the pattern needs no backend change beyond activating the API, but the polled payload has to stay aligned with whatever event format the ERP pushes on change.AlexPfeil, published 2025-04-04
Handling File Routing and Alerts in SAP CPI Based on File TypeHandling File Routing and Alerts in SAP CPI Based on File TypeWalks through building a Cloud Integration flow that pulls files from one SFTP server, captures the name and extension with a Content Modifier's ${file:ext} expression, and uses a Router to send XML files on to a second SFTP server while any other extension, or a missing XML file, triggers an alert. The alert is a Mail adapter step authenticated against Gmail's SMTP server with an app password, so the piece covers an adapter, a router condition and a mail step as parts of one flow.harsh__chauhan, published 2025-04-03
Generation of Message Processing logs report for EDI transactions using SAP CI.Generation of Message Processing logs report for EDI transactions using SAP CI.Walks through building an integration flow in Cloud Integration that calls SAP's standard MessageProcessingLogs OData API, plus a second request for custom headers, and converts the combined result to a CSV report of order, order-acknowledgement and invoice status by trading partner for EDI transactions. Getting the trading partner number into that report first requires a Groovy script and exchange property added to each EDI I-Flow so the value is captured as a custom header in message monitoring.NagurBabu, published 2025-03-13
how to create and expose OData APIshow to create and expose OData APIsA step-by-step walkthrough of building an OData API artifact in Cloud Integration: import a service's EDMX metadata, select an entity type, wire an ODATA receiver adapter into an integration flow with a response mapping, then deploy the artifact. The example targets the public Northwind service rather than an SAP backend, and the deployed ProductSet endpoint is tested in Postman with basic auth.SaiPrudhviRajTaduva, published 2025-02-26
Integration Suite: Automating Email Alerts for Failed Interfaces in SAP CPIIntegration Suite: Automating Email Alerts for Failed Interfaces in SAP CPIWalks through building a Cloud Integration iFlow on SAP Integration Suite that polls the Message Processing Logs OData V2 API for failed messages on a timer, groups them by interface with value mapping, and batches the results into one scheduled email per interface instead of an alert per failure. Covers routing recipients per interface, splitting a batch once it passes a configured record count, and excluding interfaces flagged with a custom status so they raise their own real-time alert outside the consolidated flow.Daggolu_PremSai, published 2025-02-18
New Pipeline Concept features: integrated runtimes and supporting landscape stagesNew Pipeline Concept features: integrated runtimes and supporting landscape stagesDescribes version 1.0.9 of the Pipeline Concept package for Cloud Integration in SAP Integration Suite, which the post says can be taken from the SAP Business Accelerator Hub: a new integrated messaging runtime step merges inbound conversion with receiver and interface determination, cutting the JMS queues a scenario needs from four to two, or eight to four counting dead-letter queues, and a synchronous variant replaces queues with the ProcessDirect adapter for Content-Based-Router scenarios. It also maps a sender's actual business system name to an alias held in the Partner Directory, so the same XI and IDoc scenario definitions run across DEV, QA and PRD stages without converting names when transporting between them.alex_bundschuh, published 2025-01-29
How to Configure Retry Mechanism in SAP BTP CI/IS to Handle Only Connectivity Errors when using AEMHow to Configure Retry Mechanism in SAP BTP CI/IS to Handle Only Connectivity Errors when using AEMShows how to configure a Cloud Integration iFlow with an AEM sender so only connectivity errors trigger a retry: a Groovy script reads the CamelHttpResponseCode header and looks it up in a value map, and a router then sends a transient failure such as a 408 timeout down the retry path, where the retry limit set in AEM applies, and an error needing manual intervention, such as a 401, down a path that ends the flow at once and emails the team. It applies only to receiver adapters that return CamelHttpResponseCode, among them HTTP, SOAP, IDoc and OData. It builds on an earlier post of the author's, which this one does not name, where an email goes out after the final retry attempt.Jayabalaji_Sakthivel, published 2025-01-21
SAP PI Migration to BTP Integration Suite Patterns and learning experiencesSAP PI Migration to BTP Integration Suite Patterns and learning experiencesWalks through the integration patterns an SAP PI migration project moved onto SAP Cloud Integration iFlows — API Management proxies fronting calls into on-premise SAP systems over XI/SOAP via Cloud Connector, SFTP transfers, and eventing routes — and the operational lessons from running it: sizing JMS queues, choosing exactly-once JMS queues over Cloud Integration's Data Store for XI receiver adapters and at-least-once JMS for XI sender adapters, and workarounds for gaps in the migration tooling. The API Management proxies handle JWT validation against a non-SAP identity provider, IP filtering and OData-to-OpenAPI conversion in front of the iFlows.saikrishna_kalivarapu2, published 2024-12-04
Integrating SAP CPI with Microsoft SharePoint: Part 2- Creating an API to Upload Files to SharePointIntegrating SAP CPI with Microsoft SharePoint: Part 2- Creating an API to Upload Files to SharePointPart two of a three-part series builds a custom HTTP API in Cloud Integration: an HTTP adapter receives the upload, an exchange property derives a folder path from header values, and the SharePoint receiver adapter writes the file with OAuth2 authorization code authentication. It also covers exposing that flow through API Management and enabling streaming so larger files bypass its default 10 MB payload limit.siddhartha_routh, published 2024-11-05
SFTP File Level Checks in SAP BTP Cloud IntegrationSFTP File Level Checks in SAP BTP Cloud IntegrationFor an SFTP flow in Cloud Integration that an external party triggers, the post recommends polling with SFTP Poll-Enrich rather than relying on the Sender SFTP adapter and its built-in scheduler, and because Poll-Enrich polls one file per trigger, the design is a Main flow whose Looping Process Call repeatedly invokes a Local Integration Process that holds the Poll-Enrich step. On top of that design, it adds four router conditions, each checked against SAP_PollEnrichMessageFound, CamelLoopIndex, CamelFileName or CamelFileLength: no file found on the first poll, no more files left mid-loop, more than one file present when exactly one should be processed, and an empty file, each letting the flow terminate or raise an exception instead of failing on an unhandled read.Srishti_Gupta, published 2024-09-16
Application to Application IntegrationApplication to Application IntegrationSAP's reference architecture for application-to-application integration, where messages carrying transactional data such as sales orders pass between business applications in near real time and each one triggers the next process step. When the sender's and receiver's APIs do not match, Cloud Integration in SAP Integration Suite sits between them to determine receivers, filter, map structures and convert protocols, which is the ground of integration flows; SAP Connectivity service, Cloud Connector and SAP Destination service reach on-premise receivers, and the edge integration cell runtime keeps processing inside a customer-managed landscape where compliance requires it. Direct exchange without middleware is allowed when the two APIs already align, asynchronous communication is the default the page states, and it is drawn at the level of the pattern, following SAP's Integration Solution Advisory Methodology, without designing any one flow.published 2024-08-01
Business to Business IntegrationBusiness to Business IntegrationSAP's reference architecture for business-to-business integration, the exchange of business documents with customers, suppliers and other trading partners over agreed standards such as EDIFACT, ANSI X.12 and IDoc and protocols such as AS2. Its design-time steps are Cloud Integration in SAP Integration Suite, the predefined content of SAP Business Accelerator Hub, and Integration Advisor, which defines message implementation and mapping guidelines and generates runtime artifacts from them; Trading Partner Management then turns partner profiles into agreements pushed to the Partner Directory, and generic integration flows on Cloud Integration read those agreements at runtime to exchange messages with each partner. The alternatives it names are API-based exchange where an industry has standardised its APIs, and SAP Business Network with the managed gateway for spend management in place of connecting partners one by one.published 2024-08-01
Connect Business Processes with SAP Master Data IntegrationConnect Business Processes with SAP Master Data IntegrationSAP's reference architecture for keeping master data such as materials, business partners and cost centres consistent across applications with SAP Master Data Integration, a central hub that stores every change in an event log and distributes it to the solutions that consume it. Cloud Integration in SAP Integration Suite carries what the hub does not reach, SAP solutions it does not yet support and third-party or on-premise systems, through an SAP Master Data Integration adapter, which is where the design meets integration flows; newer SAP S/4HANA releases connect to the hub without it. Consolidation, data quality and central governance are outside the architecture and left to SAP Master Data Governance, and SAP Master Data Integration itself has no entry in the atlas yet.published 2024-08-01
API Managed IntegrationAPI Managed IntegrationSAP's reference architecture for API-managed integration, which puts the API Management capability of SAP Integration Suite in front of business applications as API proxies that intercept each call to apply security policies, transformations and governance and to collect usage metrics. SAP defines it as a pattern that complements the other integration patterns, and draws three routes behind the proxy: a managed API forwarded to its provider for simple transformations and protocol adaptations, the Graph capability exposing data from several sources as one connected API, and Cloud Integration for mediation beyond API Management's scope, with the edge integration cell runtime for managing APIs in a customer-managed Kubernetes environment. SAP states that it delivers no predefined scenarios for this pattern, so the proxies and policies are the customer's or partner's to build.published 2024-08-01
SAP AI Services - DOX - Gen AI with SAP CAP Plugin - Part 3SAP AI Services - DOX - Gen AI with SAP CAP Plugin - Part 3Building on Reusable components for CAP with cds-plugin by Daniel Schlachter, this part walks through a custom CAP plugin — a cds-plugin.js plus a lib_cap_dox.js helper — that authenticates against SAP's Document Information Extraction (DOX) service and calls its schema and job-status APIs to fill an entity from extracted document fields. It covers reading the service key from Cloud Foundry (cf service-key) for the OAuth token endpoint, and dynamically mapping DOX's header and line-item output onto CAP entity properties.sabarna17, published 2024-06-11
Groovy Script to Compare XML Payloads in SAP CPIGroovy Script to Compare XML Payloads in SAP CPIWalks through an integration flow on Cloud Integration that detects which records changed between two XML payloads: two Content Modifier steps store the old and new employee datasets as exchange properties, and a Groovy script step parses both with XmlSlurper, matches employees by EMPLOYEE_ID, compares each child element's text and rebuilds only the changed records with MarkupBuilder. The full script and both sample payloads are shown, and the flow's purpose is to shrink a message to just its updated segments before it moves on downstream.gaganhl, published 2024-03-27
Generative AI Hub using Azure OpenAI GPT-4Generative AI Hub using Azure OpenAI GPT-4The technical half of a two-part post: a SAP Build Process Automation flow watches a support inbox, saves each incoming email's attachments and content, and hands the data to a custom Flask service that submits a service order into SAP S/4HANA. That service reaches two models through SAP AI Core's Generative AI Hub: Azure OpenAI's gpt-4-32k extracts the purchase date, model number, contact details and problem description from the email text, and LLaVA-1.6 describes the attached photos, so the JSON payload sent to the OData service-order and attachments APIs is assembled from both before the order is created.Jonathan-Kong, published 2024-03-15
Information Map – Introduction Series: Graph in SAP Integration SuiteInformation Map – Introduction Series: Graph in SAP Integration SuiteIntroduces Graph, an enhancement to API Management within SAP Integration Suite that gives developers a single API onto an organisation's business systems, modelled as one semantically connected business data graph, later renamed API Composition. Splits the work between an administrator, who enables SAP BTP destinations to the backend systems and builds the business data graph, and a developer, who explores it in the Graph Navigator tool and builds an application against the resulting Graph API.published 2024-02-21
Elevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginElevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginThe question underneath the enthusiasm: what leaves your landscape when a prompt goes to a model. The plugin's answer is to anonymise the sensitive fields through HANA before the prompt is sent, and this is the post that explains why that is the design rather than an option.AkashAmarendra, published 2024-02-02
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIAn Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIA dormant internal app at SAP Japan revived with AI, built to solve a problem the team actually had — colleagues who could not talk to each other. Build Apps on the front, CAP on Kyma behind it, OpenAI in the middle.javieryw, published 2024-01-31
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAI
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
Resend HTTP messages with configured pause and fixed max iteration followed by error handlingResend HTTP messages with configured pause and fixed max iteration followed by error handlingBuilds a retry pattern for a Cloud Integration HTTP Receiver call by splitting the request-reply step into its own local sub-process, which loops on the response code — up to a fixed five iterations, each after a configured pause — and routes to an exception sub-process that attaches the message processing log through Groovy once the count is exceeded or another error occurs. The design is the author's own alternative to the platform's retry pattern and inbuilt HTTP Receiver Adapter retry option, built for cases where neither applies; SAP Event Mesh and SAP Advanced Event Mesh are named only as the queue-based alternative the author considered and set aside.Aman_V, published 2024-01-03
GenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportGenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportA sample application rather than an explainer, and the author says so in the opening — enough talking, here is something that runs. Incoming support mail summarised and categorised through the generative AI hub in AI Core.martinfrick, published 2023-11-15
SAP Event Mesh: S4 HANA On-Prem and SAP CI(BTP IS) through WebSocket and WebhooksSAP Event Mesh: S4 HANA On-Prem and SAP CI(BTP IS) through WebSocket and WebhooksA step-by-step walkthrough of wiring Event Mesh to publish and consume events between an on-premise S/4HANA system and Cloud Integration, contrasting persistent queues (one subscriber, kept until consumed) against unpersisted topics, and WebSocket's AMQP transport against webhook delivery for the same queue. Two tested findings support it: a queue consumer running in continuous consumption mode receives a message ahead of a webhook on the same topic, and a message stays queued and is retried (almost 8770 times in under a minute, in the author's test) until the consumer processes it successfully.FarooqAhmed, published 2023-10-03
Automate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsAutomate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsA process that drafts its own text: ChatGPT writing job postings, SAP Build Process Automation carrying them through approval, and CAP in between. Presented as a generic pattern the author expects to be adapted rather than copied.shivamshukla12, published 2023-08-10
Creating a meal generator application with SAP Build, Cloud Application Programming and openAICreating a meal generator application with SAP Build, Cloud Application Programming and openAIIngredients in, meal suggestions out, assembled from BTP services plus OpenAI and Google APIs. A small application built for the pleasure of it, and useful here as the plainest example of CAP holding the middle of a generative flow.former_member793421, published 2023-07-17
Empowering Your Data Analytics with GPT-3 and SAP CAP IntegrationEmpowering Your Data Analytics with GPT-3 and SAP CAP IntegrationFree text in, SQL out, answer back in a sentence — the model writes the query, CAP runs it, and the model turns the rows into prose. Written in the GPT-3 window, so the model access has dated, but the three-step shape has not, and it is a different bet from retrieval: nothing is embedded, the schema is the context.Former Member, published 2023-03-10
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3The SAPUI5 frontend of the sample, and mostly an argument for writing UI5 in TypeScript: ES imports in place of sap.ui.define, a class with real private members in place of the underscore convention, and the service types generated from the CDS model copied into the UI package, so one IChats interface types the OData object the controller reads. The second half is structure — a formatter class and a singleton LayoutManager called from the XML view through core:require, a confirmation helper taking a callback, a dialog class resolving a promise, a generic createEntity<T> on a service class — all of it to keep every controller under 100 lines. What it says about arranging a UI5 app holds whatever model sits behind the chat; the tooling around it is of its date, and the post calls UI5's TypeScript support experimental.published 2023-02-27
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3
cds2types. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3The backend: CAP with TypeScript, the entities holding chats and personalities, and the service that talks to the API. This is where the streamed completion and the repositories behind the handler come from, which is the part of the sample still worth lifting even though the model access has since been superseded by AI Core.published 2023-02-24
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3
cap-ui5-gpt-chat: no published releases, repository quiet for 42 months. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3The concepts before the code: what the GPT model and its API actually offer, and what the finished chat application looks like — personalities included. Written in the weeks when the ground was moving under it, and the post carries its own change log to prove it: GPT-3.5 added on 1 March, GPT-4 on 15 March, and an admission that a series planned as two posts became three.published 2023-02-22
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3
cap-ui5-gpt-chat: no published releases, repository quiet for 42 months. Affects Runnable code.
How SAP Document AI brings agentic intelligence to business documentsHow SAP Document AI brings agentic intelligence to business documentsSAP Document AI as SAP's abstract now describes it: composable, agent-ready skills for schemaless extraction, classification and summarisation of business documents, so Joule Agents can read and act on unstructured content, plus new document foundation models and agentic validation in its workflow engine. That widens document extraction past the fixed-schema fields the atlas entry records; the abstract names the features and not their release state. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Dheeraj Diwan, Soeren Leibach and Tomasz Janasz, written here from SAP's abstract; the recording is not yet published.
Hands on SAP Document AI: Next-generation intelligent document processingHands on SAP Document AI: Next-generation intelligent document processingSAP Document AI configured and run by hand: schema design, splitting and classifying documents, enriching the extracted data and custom prompting are the exercises SAP's abstract names. Document extraction from the configuring side, with the schema the participant's own; which document types or models the exercises use is not stated. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Christoph Lenschow, Tobias Weller and Tomasz Janasz, written here from SAP's abstract; no recording is announced.
SAP Cloud Integration chamber of horrorsSAP Cloud Integration chamber of horrorsA Devtoberfest 2026 integration-track session that goes through anti-patterns in Cloud Integration iFlows: scripts that re-implement flow steps or make external calls, the ESB_Messaging.send role on every sender channel, default flow-step names, dependence on undocumented platform internals, code that rewrites what the Groovy and Java libraries already hold, XML namespaces stripped to simplify XPath, HTTP calls between iFlows on one tenant where ProcessDirect would stay inside it, externalised parameters too few or too many, and MPL attachments left switched on in production. Each one comes with how to spot it — long scripts, jar files for SFTP communication, the design guidelines and upgrade readiness checks, or a rule in the presenter's own CPILint run locally or in a pipeline — and that pass over flow steps, sender roles, adapters and the message processing log is what the Integration flows edge rests on. The questions afterwards cover the GitHub integration in Cloud Integration, the absence of an official MCP server for building iFlows, and whether generated code shifts the choice between mapping, XSLT and scripting.
Edge Integration Cell - what's new?Edge Integration Cell - what's new?A Devtoberfest 2026 integration-track session (INT-41) on Edge Integration Cell, the runtime of SAP Integration Suite a customer runs on their own Kubernetes cluster while design, configuration and monitoring stay in the cloud tenant. It names what the customer has to provide — a supported Kubernetes platform, SAP HANA or PostgreSQL, Redis or Valkey as data store, a load balancer — then the Edge Lifecycle Management cockpit with its monthly rolling updates, the inbuilt and the external Cloud Connector options and why a DMZ placement calls for the second, and the adapters available only on Edge: RFC sender, NFS, OFTP2 and UNF. The demo deploys an OFTP-to-file flow to the Edge runtime and shows the same flow rejected when its runtime profile is switched to cloud, which is where the Integration flows edge holds.
Rethinking security for modern SAP solution landscapesRethinking security for modern SAP solution landscapesWhere risk goes when clean core moves custom logic out of SAP S/4HANA: into integration flows, CAP extensions, ABAP Cloud code and platform configuration, told through real attack stories, then scanning code, modelling attack paths, adding security gates to CI/CD pipelines and automating safely with Terraform. The scanning edge is to static analysis, the atlas's concern for security findings in ABAP code; the abstract lists the four surfaces and the four practices and describes none of them. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Tsovinar Chugaszyan, written here from SAP's abstract; the recording is not yet published.
Build integrations faster with AI-assisted design and operationsBuild integrations faster with AI-assisted design and operationsAI-assisted integration development in SAP Integration Suite: the abstract names embedded generative AI tools that speed up building integrations, agent-ready APIs and event-driven architectures that connect SAP and third-party systems. The Integration Suite edge holds because it is the subject; the Integration flows edge rests on the phrase integration development alone, since the abstract names no tool, no capability area and no feature. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Finny Babu and Shilpa Vij, written here from SAP's abstract; the recording is not yet published.
Build an integration scenario from scratch with AI assistance at every stepBuild an integration scenario from scratch with AI assistance at every stepBuilds an integration scenario in SAP Integration Suite from nothing and takes it through design, deployment, optimisation, monitoring and resolution with AI assistance at each step, which is the Integration flows concern worked end to end. The abstract names the phases and the kinds of help, development, analysis, troubleshooting and continuous improvement, and no feature or tool that gives them. A TechEd 2026 hands-on session (Tuesday 27 October, Berlin), presented by Craig Stasila, Finny Babu, Prashant Gautam and Shilpa Vij, written here from SAP's abstract; the recording is not yet published.
Access to Generative AI ModelsAccess to Generative AI ModelsSets out the plain way to call a deployed generative AI model on SAP BTP: a request that carries the prompt, the model and the parameters that control generation, with the same code able to switch between models. It lists data masking, prompt templating and filtering as features that come with the access rather than as code the caller writes, which is the shape LLM integration takes on the BTP door; the page's implementation sections sit behind its steps and were not read.
ABAP AI SDK powered by ISLM - How to implement your own AI use cases in ABAPABAP AI SDK powered by ISLM - How to implement your own AI use cases in ABAPA Devtoberfest 2026 ABAP-track session (ABA-44) on the ABAP AI SDK: an intelligent scenario development object holds the model and its version, so the ABAP code asks for an API, sends a prompt and reads the completion with its token counts and finish reason, and swapping the model is a change to that object rather than to the code. Four demos go through the ABAP line by line — a bare completion, a system prompt with the temperature set to 0.2, tool calls where the model asks for order details and the result goes back into the message container, and a JSON response schema that returns category, severity and goodwill as fields a program can act on — and a fifth replaces the API with the SDK's own mocks so unit tests run with no network call, which is what the LLM integration edge on the ABAP door rests on. The closing availability matrix separates base scenarios, available across SAP S/4HANA on-premise, private edition, public cloud and the SAP BTP ABAP environment, from the orchestration service and SAP RPT, shown for on-premise and private cloud with transport-based correction instructions back to release 2022 and not yet for the public cloud editions.
Agentic CAP: Build MCP servers and enterprise AI agentsAgentic CAP: Build MCP servers and enterprise AI agentsCAP applications become AI agents over the Model Context Protocol and the Agent2Agent protocol, which is the serve your application over MCP concern, and SAP AI Core is the LLM integration through which AI is embedded in a CAP app, with recommendations from the SAP-RPT-1 model as the abstract's example. The abstract names the two protocols and the one model and does not say which packages carry them. A two-hour TechEd 2026 session in a hands-on room (Tuesday 27 October, Berlin), presented by Daniel Hutzel, Daniel Schlachter, Marc Huber and Sami Lechner, written here from SAP's abstract; the recording is not yet published.
AI-enabled administration: Automating log analysis with generative AI hubAI-enabled administration: Automating log analysis with generative AI hubA log analysis tool for incident work, built in SAP Business Application Studio with the generative AI hub feature, which SAP AI Core ships as its LLM integration by its own documentation: it automates root-cause analysis over system errors and masks sensitive data. SAP's abstract states the tool's jobs and not how the hub is called, what the masking covers or which model answers. A TechEd 2026 session (Wednesday 28 October, Berlin), with no speaker listed in the catalogue at the time of writing, written here from SAP's abstract; the recording is not yet published.
Stop guessing, start counting: How generative AI fixed an inventory messStop guessing, start counting: How generative AI fixed an inventory messAn inventory-counting application a business built on SAP Business AI Platform with SAP HANA Cloud and generative AI, to replace recount lists kept by gut feel across SAP ERP Central Component, SAP S/4HANA and Microsoft Excel; the talk promises the app, its architecture and what went wrong. The generative AI part is LLM integration from application code; the abstract names HANA Cloud and generative AI as the two building blocks and says nothing about how either is used. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Ranjeet Kumar, written here from SAP's abstract; the recording is not yet published.
Conversational search for the Cloud Integration capabilityConversational search for the Cloud Integration capabilityCloud Integration content becomes searchable in natural language through three architectures SAP's abstract names: MCP servers, retrieval-augmented generation and knowledge graphs, set against the work of analysing and governing a growing SAP Integration Suite tenant. The abstract names the three and does not say which is built or how they compare. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Vadim Klimov, written here from SAP's abstract; the recording is not yet published.
Explore version control and automation with GitHub in Cloud IntegrationExplore version control and automation with GitHub in Cloud IntegrationGitHub access set up in Cloud Integration: integration flows committed and versioned from Cloud Integration's own tools, several people working on the same artifacts, and a commit that triggers a CI/CD pipeline. The abstract states what the GitHub connection does and stops before the branch model, the pipeline's steps or which pipeline service runs them. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Marco Ertel, Morten Wittrock, Patrick Kelleher, Shivani Borkar and Tobin Sydneysmith, written here from SAP's abstract; the recording is not yet published.
Governance, automation, and observability in Cloud IntegrationGovernance, automation, and observability in Cloud IntegrationGovernance controls in Cloud Integration for developers and architects, automations written against its public OData API, and monitoring across Cloud Integration and SAP Cloud ALM with AI-assisted error analysis. The abstract names the OData API as the automation surface and does not list the controls or the operations the API exposes. A TechEd 2026 session (Wednesday 28 October, Berlin; also IN208V, virtual), presented by Morten Wittrock and Sunny Kapoor, written here from SAP's abstract; the recording is not yet published.
Evolution of the Code10 CI Accelerator add-on for SAP Integration SuiteEvolution of the Code10 CI Accelerator add-on for SAP Integration SuiteThe Code10 CI Accelerator, a partner add-on that puts a process monitor over pipeline concepts and patterns in Cloud Integration, the Edge Integration Cell runtime and more of SAP Integration Suite, and how it has changed as the suite has. The add-on is not in the atlas, so the edges rest on the Integration Suite capabilities it monitors; the abstract names no pipeline pattern and no feature of the add-on. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Antonio Valladares Fernandez, written here from SAP's abstract; the recording is not yet published.
Third-Party MCP Access to SAP SolutionsThird-Party MCP Access to SAP SolutionsDescribes external MCP servers and custom servers on a customer-managed subaccount on SAP Business AI Platform, assigning their operators responsibility for authentication, scoped identity, API limits, logging and lifecycle. The permitted use remains conditional on the SAP API Policy, while SAP Integration Suite and Joule Studio are described as SAP-provided paths. Hosting a server on such a subaccount does not automatically supply its governance controls.
Model Context Protocol (MCP)Model Context Protocol (MCP)Frames the Model Context Protocol as the answer to an M-times-N integration problem: one shared protocol turns M agents and N tools into M plus N connections, and one server can be called by any compliant agent. On SAP BTP its implementation section lists an SAP MCP Hub as a no-code way to expose enterprise tools, SAP Integration Suite's MCP Gateway as what it calls the governed path for exposing SAP and non-SAP APIs as MCP-compliant tools, custom SDK-based servers, SAP's MCP servers for development, and an MCP adapter for CDS as a CAP plugin marked coming soon. That is the ground MCP servers covers; for security it points at a separate page.
MCP Gateway in Practice: Architecture, configuration, and hands-onMCP Gateway in Practice: Architecture, configuration, and hands-onA Devtoberfest 2026 integration-track session (INT-21) on the MCP gateway of SAP Integration Suite: curated enterprise APIs served to agents as MCP tools over JSON-RPC, behind the authentication, authorization and traffic policies an API artifact already carries, with the existing API layer left in place. The hands-on half composes S/4HANA plant, material-stock and supplier data with a non-SAP location-risk source into one business data graph, downloads its OpenAPI specification, creates an MCP server artifact with tools, prompts and a surge-protection policy over that endpoint, and publishes it as a product in Developer Hub of API Management, where an agent developer subscribes and gets OAuth credentials. An MCP client then asks for 15 brake pads and ranks plants by stock, location risk and distance from Walldorf, which is what the agent access to your systems edge rests on; the Q&A covers principal propagation to the backend, how errors reach the model, and which Integration Suite editions carry the gateway.
MCP Server — SAP Integration SuiteMCP Server — SAP Integration SuiteSAP's own page for the MCP Server artifact in SAP Integration Suite, and where the gateway that runs it is described: MCP clients and API clients reach the same backends through two gateways that share security, traffic management and multi-protocol connectivity. Sets out the three primitives a server may expose — tools derived from API operations with an input and output schema, resources addressed by URI for context rather than action, and prompts as reusable interaction patterns. Says availability depends on the Integration Suite service plan, and points at the three creation paths as separate pages.
OData entity as a governed query surface for agents, not a toolOData entity as a governed query surface for agents, not a toolAn OData entity, generated from the annotations a service already carries, as the surface an agent queries over SAP data: filterable, selectable and sortable fields, authorisation injected on the server side, and a bound query cost, instead of the entity as a tool. SAP's abstract sets this against the MCP gateway in SAP Integration Suite, where exposing an API is the easy part and getting an agent to pick the right one is not, which is the tool governance concern read through OData. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Aleksandr Ivanov and Evgenii Shirokikh, written here from SAP's abstract; the recording is not yet published.
Build an AI-assisted known error database with SAP Integration SuiteBuild an AI-assisted known error database with SAP Integration SuiteThe AI adapter in SAP Integration Suite builds a known error database for integration support: runtime exceptions are captured, analysed by a model, matched against past incidents, and a resolution is proposed, so the base grows with each case. SAP's abstract names the adapter and the four steps, and claims shorter troubleshooting time without a figure. A TechEd 2026 session (Wednesday 28 October, Berlin), with no speaker listed in the catalogue at the time of writing, written here from SAP's abstract; the recording is not yet published.
More than 100 trading partners, one platform: Scalable B2B at Algoma SteelMore than 100 trading partners, one platform: Scalable B2B at Algoma SteelB2B integration at Algoma Steel on SAP Integration Suite: more than 100 trading partners served through Trading Partner Management and one generic integration flow architecture, ML-assisted mapping for the documents, and EDI at that scale after a move from SAP Process Integration and SAP Process Orchestration. The abstract names the three pieces, which is the trading partner agreements model, and not the partner standards or the mapping tooling behind them. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Jagesh Lakdawala and Marco Ertel, written here from SAP's abstract; the recording is not yet published.
Onboard a trading partner from agreement to live monitoringOnboard a trading partner from agreement to live monitoringOne trading partner onboarded from scratch in Trading Partner Management: a trading partner agreement configured, a business document mapped with ML-assisted mapping proposals, which is B2B message mapping, and a transaction run and monitored live, all inside SAP Integration Suite with no EDI tooling outside it. The abstract names the steps and not the document standard or the partner's protocol. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Claudia Carabineiro, Marco Ertel, Marton Luptak and Tobias Griebe, written here from SAP's abstract; the recording is not yet published.
Building API-centric integration flows with SAP Integration SuiteBuilding API-centric integration flows with SAP Integration SuiteAn API-first way of working in SAP Integration Suite: one integration case, its API artifacts built, configured and run, then reused in other scenarios, with the abstract putting the gain in reuse and lifecycle management for teams used to point-to-point integration. It does not say which Integration Suite capability holds the API artifact or how it sits beside an integration flow. A two-hour hands-on TechEd 2026 session (Wednesday 28 October, Berlin), presented by Karsten Strothmann, Kathrin Widenmann, Marton Luptak, Nils Lorenz and Shivani Borkar, written here from SAP's abstract; the recording is not yet published.
Govern AI-supported actions across enterprise systemsGovern AI-supported actions across enterprise systemsGoverning what an AI agent may do once it takes business actions across enterprise systems, which is the Tool governance concern, with SAP Integration Suite as the place it is enforced. The abstract lists the mechanisms, scoped APIs, event-driven workflows, runtime policy enforcement, exception handling and observability across SAP and third-party systems, and names no Integration Suite feature behind any of them. A TechEd 2026 session (Tuesday 27 October, Berlin; also IN200V, virtual), presented by Finny Babu and Piyush Gakhar, written here from SAP's abstract; the recording is not yet published.
Accelerate your migration to SAP Integration SuiteAccelerate your migration to SAP Integration SuiteMigrating from SAP Process Integration and SAP Process Orchestration to SAP Integration Suite, which is the Platform migration concern on the integration side. The abstract promises the services and tools available for the move, new AI-assisted innovations among them, and guidance for a migration project; it names none of the tools, so what the session covers beyond the migration path itself is not stated. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Morten Wittrock and Nils Lorenz, written here from SAP's abstract; the recording is not yet published.
Mercedes-Benz’s journey to SAP Integration SuiteMercedes-Benz’s journey to SAP Integration SuiteMercedes-Benz's move from SAP Process Integration and SAP Process Orchestration to a centrally governed integration platform on SAP Integration Suite, run for several business domains at global scale, which is a Platform migration case told by the customer. The abstract promises the architectural and operational decisions behind it and states none of them. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Oliver Weng and Sebastian Buhlinger, written here from SAP's abstract; the recording is not yet published.
Modern integration at TÜV Rheinland: APIs, events and cloud transformationModern integration at TÜV Rheinland: APIs, events and cloud transformationTÜV Rheinland's migration from SAP Process Orchestration to SAP Integration Suite with API-led connectivity and event-driven architecture, told through business cases. The abstract names what was used: the SAP Integration Suite, Event Mesh capability, API Management, generative AI for faster development and SAP Cloud ALM for monitoring. It states nothing about how any of them was used, so the edges rest on the names and on the Platform migration the story starts from. A TechEd 2026 session (Wednesday 28 October, Berlin), written here from SAP's abstract; the recording is not yet published.
Modernisation and migration to SAP Integration Suite made simpleModernisation and migration to SAP Integration Suite made simpleA hands-on platform migration of SAP Process Integration and SAP Process Orchestration scenarios into SAP Integration Suite: the migration assessment run against a legacy landscape to see what converts automatically, the migration tooling in Integration Suite run on the scenarios, and the resulting integration flows adjusted and deployed. What the assessment classifies a scenario by, and which adapters convert, is not stated. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Claire Tseng, Craig Stasila, Nils Lorenz and Sunny Kapoor, written here from SAP's abstract; the recording is not yet published.
Model context protocol (MCP) unlocked: Enable governed access to AI agentsModel context protocol (MCP) unlocked: Enable governed access to AI agentsThe MCP Gateway in SAP Integration Suite: the place policy, security and analytics are applied to a curated set of MCP tools before an AI agent reaches enterprise tools and APIs through it, tool governance done in the integration layer and agent access to your systems routed through one gateway. The abstract names the gateway and its three functions and does not say how tools are curated, which policies exist or how the agent authenticates. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Bruno Renzo, Emily Mui, Markus Winter and Sunny Kapoor, written here from SAP's abstract; the recording is not yet published.
Road map for SAP Integration Suite: What ships next across all capabilitiesRoad map for SAP Integration Suite: What ships next across all capabilitiesSAP's road map for SAP Integration Suite across its capability areas: API Management, event-driven integration, business process and trading partner integration, and hybrid runtimes for SAP and third-party systems. The abstract promises recent deliveries and the planned innovations that make the platform agent-ready within SAP Business AI Platform; it names the areas and no shipping item, so the edges rest on the product and the one area it names by a product name. A TechEd 2026 session (Thursday 29 October, Berlin; also IN804V, virtual), written here from SAP's abstract; the recording is not yet published.
Roadmap to upgrade from SAP Process Orchestration: Agentic era preparationRoadmap to upgrade from SAP Process Orchestration: Agentic era preparationThe road map for moving from SAP Process Orchestration to SAP Integration Suite, a platform migration with two named items: AI-supported migration tooling in Integration Suite that takes manual effort out of the conversion, and the Edge Integration Cell runtime as the governed hybrid runtime for secure deployments, in the abstract's words. Neither is described beyond its name, so what the tooling converts and what Edge Integration Cell runs is not stated. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Arti Gopalan, Shilpa Vij and Udo Paltzer, written here from SAP's abstract; the recording is not yet published.
Intelligent, governed, and agentic integrations with SAP Integration SuiteIntelligent, governed, and agentic integrations with SAP Integration SuiteSAP Integration Suite positioned as the control plane that connects and governs agentic workflows across SAP and third-party systems, set against the abstract's claim that exposing back ends directly to AI brings security, compliance and cost risks. That governing role is the Tool governance concern; the abstract promises recent innovations and names none. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Finny Babu and Piyush Gakhar, written here from SAP's abstract; the recording is not yet published.
B2B integration factory: How Versuni verified more than 200 EDI interfacesB2B integration factory: How Versuni verified more than 200 EDI interfacesHow Versuni prepared its EDI landscape for a migration to SAP Integration Suite using Int4 Suite: automated validation across more than 200 interfaces, trading partner dependencies removed from the test, issues found earlier, and a repeatable approach for large B2B programmes. Int4 Suite is not in the atlas, so the piece enters on Integration Suite as the migration target and on the Platform migration concern; what was validated and how is not stated beyond the count. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Henk Wouda and Michal Ibrom, written here from SAP's abstract; the recording is not yet published.
Integrating automation with agentic AI and complex file transfer needsIntegrating automation with agentic AI and complex file transfer needsDeterministic automation around SAP's agentic offerings, Joule Agents among them, with SAP Integration Suite on the automation side and new managed file transfer capabilities in it that SAP's abstract names without describing. A panel of automation practitioners and the suite's product managers; the abstract states that the file transfer feature exists and nothing of its shape. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Morten Wittrock, Sven Kohlhaas and Udo Paltzer, written here from SAP's abstract; the recording is not yet published.
SAP Integration Suite as the foundation for enterprise agentic AISAP Integration Suite as the foundation for enterprise agentic AISAP Integration Suite as the way an agent reaches systems: SAP's abstract says it gives agents governed access to APIs, events, applications, trading partners and processes across SAP and third-party landscapes, with AI assistance in the design, deployment and operation of the integrations. That is agent access to your systems through middleware; the abstract names no protocol and no gateway. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST104V, virtual), presented by Markus Winter and Udo Paltzer, written here from SAP's abstract; the recording is not yet published.
AkzoNobel: Modernizing integration at enterprise scaleAkzoNobel: Modernizing integration at enterprise scaleAkzoNobel moving webMethods, SAP Process Orchestration and Microsoft BizTalk onto SAP Integration Suite, with Rojo Consultancy: SAP's abstract states more than 100 third-party applications on the new platform and the preparation for event-driven and AI-enabled integration. A platform migration told by the customer; the abstract names the three source platforms and not the tooling used to convert them. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Oussama Zoubairi, Piyush Gakhar and Sander Kool, written here from SAP's abstract; the recording is not yet published.
Build real-time event-driven integrations for your enterpriseBuild real-time event-driven integrations for your enterpriseEvent-driven integration with SAP Integration Suite, advanced event mesh inside SAP Integration Suite: where events beat request-response, how publish and subscribe decouple systems, and what a phased move to event-driven integration looks like. Event Mesh as architecture; the abstract names no broker protocol and no CDS mapping. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Daniel Dorst and Karsten Strothmann, written here from SAP's abstract; the recording is not yet published.
Content FilteringContent FilteringContent filtering screens a large language model's input and output for low-quality, irrelevant or unsafe content: the four categories it names being hateful, violent, sexual and vulgar content, checking a request once on the way in and once on the way back. The page states smaller models can do this filtering efficiently, reading perplexity scores to flag anomalies, with the aim that SAP AI Core produces content meeting a stated safety standard, which is the ground content filtering covers on the BTP door.
Data MaskingData MaskingData masking replaces identifiable or confidential text in a prompt with placeholders such as <Person_0> or <Organization_1> before it reaches a large language model, using pattern matching and machine learning to find what to replace. The page states SAP AI Core supports it as a feature and sets out five steps for applying it, defining the masking scope, choosing a technique, preserving the prompt's intent, checking compliance and risk, then testing and monitoring the result. That is the shape data masking takes on the BTP door.
Document GroundingDocument GroundingDocument Grounding is a managed retrieval-augmented-generation service under the Generative AI Hub on BTP, which SAP's page on SAP AI Core places inside that service: it ingests documents from Amazon S3, SharePoint, SAP Document Management Service, SAP Work Zone or an SFTP server, and handles chunking, embedding and retrieval itself, refreshing content automatically when a source document changes. The page states this managed path is recommended for most enterprise scenarios because it covers the whole lifecycle end to end, and offers a separate Document Grounding Vector API for data that is already chunked and embedded, for cases that need finer control over chunking and metadata.
Prompt TemplatingPrompt TemplatingPrompt templating replaces a static prompt with a structured, reusable template whose placeholders are filled in at runtime, which the page says helps LLM responses stay consistent and lets the same instructions be adapted across tasks. On SAP AI Core this is implemented through the Prompt Registry, and the page states that storing prompts as plain strings in code is possible but not recommended. That is prompt management as a stored and managed object rather than a string embedded in the caller.
Enriching AI models with SAP AI Core in SAP Business Data CloudEnriching AI models with SAP AI Core in SAP Business Data CloudThe integration between SAP Business Data Cloud and SAP AI Core, through which data products with their semantics feed AI models for benchmarking, custom AI development and agentic analytics and applications. The abstract names the two products and the three uses and states nothing about how the data reaches AI Core or what the integration consists of. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by San Tran and Sandy Tran, written here from SAP's abstract; the recording is not yet published.
Build AI agents and applications natively on SAP HANA CloudBuild AI agents and applications natively on SAP HANA CloudSAP HANA Cloud as the base for agentic applications on SAP Business AI Platform: the session goes through CAP, the SAP HANA Cloud vector engine and SAP AI Core, with architecture patterns and lessons learned from building AI-supported applications. SAP's abstract names the three parts of that stack and the vector engine as the database's feature in it, and describes none of the patterns. A TechEd 2026 session (Wednesday 28 October, Berlin; also DA113V, virtual), presented by Christoph Morgen and Shraddha Shetty, written here from SAP's abstract; the recording is not yet published.
Building agentic applications with SAP HANA CloudBuilding agentic applications with SAP HANA CloudA CAP application extended with semantic search and agent features on top of SAP HANA Cloud's vector engine and SAP AI Core, built in a hands-on workshop. The abstract names the parts, CAP, the vector engine and AI Core, and the two additions: semantic search, the retrieval half of retrieval-augmented generation, and LLM-supported agent capabilities inside the application, which is agent tooling. Which embedding model, which CAP runtime and how the agent calls its tools are not stated. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Hui Li, Ritty Joseph, Shraddha Shetty and Tanuja Jadhav, written here from SAP's abstract; the recording is not yet published.
Agentic memory: Knowledge graph engine and recall in SAP HANA CloudAgentic memory: Knowledge graph engine and recall in SAP HANA CloudThe knowledge graph engine in SAP HANA Cloud as an agent's memory: what the engine, the graph side of graph, spatial and document data, does in an agentic workflow, how an agent keeps what it learns there, the state agent tooling holds between turns, and the SAP AI Core integration through which the database calls LLMs and tabular foundation models such as SAP-RPT-1. The abstract names the engine, the memory role and the AI Core link and does not say how the memory is written or read. DA263 on Wednesday 28 October is a two-hour hands-on on the same engine with a different cast. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Markus Fath and Shraddha Shetty, written here from SAP's abstract; the recording is not yet published.
Knowledge graph and agent memory: Build an agent that remembersKnowledge graph and agent memory: Build an agent that remembersThe knowledge graph engine in SAP HANA Cloud as an agent's memory: what the engine, the graph side of graph, spatial and document data, does in an agentic workflow, how an agent keeps what it learns there, the state agent tooling holds between turns, and the SAP AI Core integration through which the database calls LLMs and tabular foundation models such as SAP-RPT-1. The abstract names the engine, the memory role and the AI Core link and does not say how the memory is written or read. DA205 on Tuesday 27 October is the 45-minute talk on the same engine, with a near-identical abstract and a different cast. A two-hour hands-on TechEd 2026 session (Wednesday 28 October, Berlin), presented by Christoph Morgen, Jan Zwickel, Markus Fath and Thomas Hammer, written here from SAP's abstract; the recording is not yet published.
SAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core read as the management and orchestration layer of an AI architecture, beyond the model runtime: SAP's abstract lists extending Joule Agents, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. It names the connections and not the APIs behind them. A TechEd 2026 session (Tuesday 27 October, Berlin; also RA107V, virtual), presented by Franziska Dobrigkeit and Hadi Hares, written here from SAP's abstract; the recording is not yet published.
Joule and SAP Knowledge Graph: Context-aware AI across SAP solutionsJoule and SAP Knowledge Graph: Context-aware AI across SAP solutionsThe catalogue carries RA107's abstract under this title, and what it describes is SAP AI Core as the management and orchestration layer of an AI architecture: extending Joule Agents in SAP Joule, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. The SAP Knowledge Graph the title names does not appear in that text, so the edges rest on the abstract as published, and whether the session follows the title or the abstract is not known until it is recorded. A TechEd 2026 session (Wednesday 28 October, Berlin; also RA110V, virtual), presented by Jan Portisch and Pavithra G K, written here from SAP's abstract; the recording is not yet published.
Build business differentiation with SAP AI CoreBuild business differentiation with SAP AI CoreSAP AI Core as the orchestration layer for enterprise AI, worked through with SAP's engineers: extend Joule Agents with models from its library, ground them in SAP Business Data Cloud products, embed them in SAP S/4HANA flows, then govern, scale and monitor them from prototype to production. The abstract says what the layer does for an agent and not which services carry each step. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by David Knaack, Franziska Dobrigkeit, Hadi Hares and Jonas Israel, written here from SAP's abstract; the recording is not yet published.
SAP-RPT and TabPFN: Get started with tabular foundation modelsSAP-RPT and TabPFN: Get started with tabular foundation modelsTabular foundation models, SAP-RPT and TabPFN, in a hands-on with SAP and Prior Labs: the model families first, then predictions run through SAP AI Core with a workflow built on tabular orchestration and connected to the participant's own data for real-time predictions. A predictive models session with the models as the subject; the abstract does not name the SDK or API the workflow is built with. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Eliott Kalfon, Janick Zaehringer-Frasch, Johannes Hoehne, Katharina Schell, Nilay Mehta and Sherene Tan, written here from SAP's abstract; no recording is announced.
Behind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain ModelsBehind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain ModelsThe strategy behind SAP Business AI's intelligence layer: SAP Knowledge Graph for enterprise context, SAP Domain Models for SAP-specific expertise and tabular AI for predictions, unified on SAP AI Core with SAP Document AI. Knowledge Graph and Domain Models are not atlas entries, so the edges rest on the two products the abstract names as the infrastructure and on Predictive models for the tabular AI; nothing is stated about what any of them does in the layer. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST103V, virtual), presented by Jan Portisch and Richard Grandpierre, written here from SAP's abstract; the recording is not yet published.
SAP Joule for Consultants: Unified knowledge for requirements and designsSAP Joule for Consultants: Unified knowledge for requirements and designsFit-to-standard analysis as a consultant on a cloud transformation project: connecting an organisation's data to SAP Joule for Consultants through SAP AI Core, getting answers from SAP knowledge and that content, then building an expert, loading project files and running guided prompts. The edges are to SAP Joule, of which Joule for Consultants is a part, and to SAP AI Core, named as the connection path; how the data is grounded is left to the session. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Anantharaman Ravi, Natalie Han, Sachin Kaura and Yi Hsuan Lin, written here from SAP's abstract; the recording is not yet published.
Ship your own sandboxed AI operations agent to Kyma in two hoursShip your own sandboxed AI operations agent to Kyma in two hoursAn operations agent built and then broken on purpose: the abstract has participants deploy a reasoning agent to SAP BTP, Kyma runtime, connect it to SAP AI Core, give it observability over the runtime and cause a failure for it to diagnose, the operations automation concern with an agent doing the diagnosis. Patterns for cost control and monitoring are promised at the end; the agent framework and how the sandbox is drawn are not named. A TechEd 2026 session (Tuesday 27 October, Berlin, two hours), presented by Christian Lechner, Piotr Tesny, Thorsten Sandfuchs and Vipin VijayKumar, written here from SAP's abstract; the recording is not yet published.
Details
Graph
Document extractioncapability, core only
Integration flowscapability, core only
LLM integrationcapability, core and community
Cloud Integrationartifact
SAP Integration Suiteartifact
SAP AI Coreartifact
SAP Communitypublishing source
SAP Communityagentic-ai-tag
SAP Communitycloud-integration-tag
SAP Communityintegration-suite-tag
Source
Type
blog
Published on
Host
community.sap.com
Discovered via
First seen
History
- Entered the atlasDiscovered via SAP Community · agentic-ai-tag, SAP Community · cloud-integration-tag, SAP Community · integration-suite-tag.
For your agent
- Ref
content:generative-ai-powered-document-processing-in-sap-integration-suite- JSON
- /content/generative-ai-powered-document-processing-in-sap-integration-suite.json
- MCP
- Connecting an agent