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
Beyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud Learning
Builds a rules-first error-diagnosis pipeline on 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: 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 CloudSAP HANA CloudThe managed database under most of this: CAP's default target, the store Datasphere and Analytics Cloud sit on, and a service with plans and components.sap official, btp, 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.
Where it sits
Explains
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 integrationBTPLLM 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.Data maskingBTPData maskingReplacing the personal or confidential values in a prompt with placeholders before it leaves for a model, and putting them back in the answer. Anonymisation, where the values are gone for good, and pseudonymisation, where they return, are the two forms; which fields count as sensitive is the application's question, not the module's.
Source
reachable
Who is behind it
Krishna_Karthikauthor
Properties
About this work
For llm-integration
Applies in
For data-masking
Applies in
Group by77 of 77 pieces
Piece, what it offersStill applies
🟣 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.SAP Developers, published 2026-10-01
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
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.SAP Developers, published 2026-09-23
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 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
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
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
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.
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 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
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
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
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
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
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
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
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
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
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
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.
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
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
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
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
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
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
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
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.SAP Developers
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.SAP Developers
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.
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.
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.
Details
Graph
Integration flowscapability, core only
LLM integrationcapability, core and community
Data maskingcapability, core only
SAP Communitypublishing source
SAP Communityhana-cloud-tag
SAP Communityintegration-suite-tag
Source
Type
blog
Published on
Host
community.sap.com
First seen
History
- explains → applies_to on capability:llm-integration (btp); capability:data-masking (btp)Door scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).
- Entered the atlasDiscovered via SAP Community · hana-cloud-tag, SAP Community · integration-suite-tag.
For your agent
- Ref
content:beyond-basic-ai-error-handling-in-sap-cpi-a-rules-first-architecture-with-hana-c- JSON
- /content/beyond-basic-ai-error-handling-in-sap-cpi-a-rules-first-architecture-with-hana-c.json
- MCP
- Connecting an agent