BrowseAll ecosystems
Everything in the atlas
220 of 2341
Domain: AI & Agents
Signals
Content: Nothing recorded
More
Group by: Capability
EntryBySignalsLast activity
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.
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
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
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.
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.
How to Use n8n for Agentic Integrations and Cool InsightsHow to Use n8n for Agentic Integrations and Cool InsightsA Devtoberfest 2026 session on one use case built with n8n, the workflow automation tool SAP announced a partnership with in May 2026: judging the attachments of an automotive warranty claim. A Fiori upload table carries named evidence rows — this line is the invoice, this one the quote — and each uploaded file goes as base64 to an n8n webhook together with the claim context: the position and diagnosis codes, the parts, the amounts and the conversation with the dealer. The flow splits PDF from image, tries text extraction before falling back to a vision prompt, and calls Anthropic's Sonnet with a prompt that names the role, the input, the scoring rules and the response shape; the demo shows a matching invoice scoring 95%, an unrelated dent-removal invoice scoring 5% with the mismatches listed, and a photograph of a rusted suspension arm accepted while an engine bay is rejected against the same claim. The second half is the n8n editor itself — nodes, credentials, the test trace with each node's input and output — and the closing advice is human-in-the-loop flows at the edges of a process rather than automatic adjudication inside it.SAP Developers, published 2026-09-25
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
Integrate Document Information Extraction into UI5 applicationIntegrate Document Information Extraction into UI5 applicationUploading an invoice from a UI5 application and getting the extracted fields back on screen, with a destination pointing at the Document Information Extraction API and a Refresh button polling until the job finishes. The polling is the honest part: extraction is asynchronous, and the post does not pretend otherwise. From 2022, so the service has since been renamed and the API moved, but the shape — upload, poll, map the result — is the shape it still is.published 2022-05-31
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
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
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
Use Free Tier to Create a Service Instance for SAP Document AIUse Free Tier to Create a Service Instance for SAP Document AIFour steps in the SAP BTP cockpit that end with a service key for SAP Document AI: open the cockpit, check the subaccount's entitlements and add the service on the free tier plan if it is not listed, create the instance, then create the key. It names the plans to use in production instead, blocks_of_100, embedded_edition and premium_edition, and stops at the credentials, before any document is uploaded.
Use Free Tier to Subscribe to SAP Document AI Basic UIUse Free Tier to Subscribe to SAP Document AI Basic UIEight steps from an entitled subaccount to the SAP Document AI basic UI open in a browser, and most of them are identity work rather than document work: getting a tenant for Cloud Identity Services, which the basic UI requires, activating the account and establishing trust with the subaccount, then subscribing, creating a user and assigning the Document_Information_Extraction_UI_Templates_Admin role collection. Using the UI to read a document is the subject of Use Machine Learning to Extract Information from Documents with the SAP Document AI Basic UI, which this tutorial names as what to read next.
Using BTP Document Extraction Service into actual App developmentUsing BTP Document Extraction Service into actual App developmentWalks through calling SAP Document AI's REST API directly: getting a client-credentials bearer token from the service key's UAA, then POSTing to /document/jobs with a file and an options body naming the document type and the header fields and line items to extract (paymentTerms, documentDate, taxId, description for an invoice), and polling the returned job id until the status resolves. Covers the trial-account booster and its own UI for uploading a document and testing extraction before moving to Postman and a small Python script that lists jobs over the same bearer token.Ace_D, published 2024-07-31
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
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’s compositional design system: Craft enterprise UIs with AI on the flySAP’s compositional design system: Craft enterprise UIs with AI on the flySAP's compositional design system is the engine behind the generated interface in Joule Work, the front of SAP Joule: SAP's abstract says AI assembles the UI at runtime from primitives and composites under a body of design knowledge, inside a brand-safe design system, and that the session covers the architecture that keeps the result consistent. A third shape of Generative UI beside the two the capability describes, since here the model composes the interface at runtime. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Philip Miseldine and Sophia Levens, written here from SAP's abstract; the recording is not yet published.
UI5 Has Entered the Chat: Building Interactive MCP Apps for SAPUI5 Has Entered the Chat: Building Interactive MCP Apps for SAPMCP Apps let an MCP tool point at a ui:// resource that a compatible host renders in a sandboxed iframe, and the post walks through the five samples of UI5con_2026_MCPApps, built with Mike Zaschka for UI5con, from a plain HTML time tool through UI5 Web Components and UI Integration Cards to UI5 lint findings from @ui5/mcp-server and an ARC-1 transport review. In the samples the model selects the tool and does not generate the interface, the prebuilt kind of generative UI, and the subject is the server side of MCP servers: register the resource, link it from the tool's _meta.ui.resourceUri, return text content as a fallback beside structuredContent, call callServerTool() only for tools of the server that owns the app, and send a message to the host when another server such as ARC-1 has to act. It stops at the host, whose support differs by client and whose iframe sandbox is not a complete security model, and Joule support for MCP Apps could not be verified at the time of writing.published 2026-07-13
🟣 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.SAP Developers, published 2026-09-24
🟣 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
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.SAP Developers
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 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
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.
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.
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.
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
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
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.
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
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.SAP Developers, published 2026-09-25
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.
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.
Build Your AI Agent prototype for free using SAP CAP, LangChain and Ollama cloudBuild Your AI Agent prototype for free using SAP CAP, LangChain and Ollama cloudA CAP Node.js service action calls an Ollama-hosted model through LangChain's ChatOllama, with the API key read from a .env file instead of any destination or credential binding — the hand-rolled-key route SAP's own SDK call exists to avoid. The same handler then builds a LangChain agent with createAgent and one mock tool, so a question about restaurants triggers a tool call and any other question does not, independent of the @cap-js/agents plugin's A2A-served harness.rajeevgoswami1, published 2026-08-29
Building a Pro-Code Agent on SAP BTP — Part 2: The Agent (LangGraph + GenAI Hub)Building a Pro-Code Agent on SAP BTP — Part 2: The Agent (LangGraph + GenAI Hub)Part 2 of a three-part series builds a separate, non-CAP Node/TypeScript agent that calls the Part 1 CAP service's MCP tools and reasons through SAP AI Core via @sap-ai-sdk/orchestration, using LangGraph's createAgent ReAct loop for provider-agnostic model calls across GPT, Claude and Gemini deployments. It explains why the tool's Zod schema and model-facing description are the agent's actual contract, the gotcha between a foundation-models deployment and an orchestration-scenario one, and how edge-case testing replaced date inference with a server-computed daysOverdue field after the agent wrongly called a delayed order 'on schedule'.rodfior, published 2026-08-20
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.
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.SAP Developers, published 2026-10-08
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
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
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
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
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
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
CAP: The Road Ahead - Simplicity in an AI EraCAP: The Road Ahead - Simplicity in an AI EraDevtoberfest 2026 session CAP10, from the head of SAP's Cloud Application Programming Model: forty minutes of live building rather than slides, on the argument that the cheapest code in an AI project is code nobody has to generate. Claude Code builds an invoice-matching workspace from cds init onwards, and each step is one the framework answers rather than the agent: a 42-line domain model that @sap/cds serves as OData and Fiori elements with a status flow, data privacy and change-tracking annotations that produce audit log entries in the console and would reach the SAP Audit Log service once deployed, an imported S/4HANA supplier data product, and semantic matching from a local embedding model after @cap-js/ai is added. The last three steps are annotations: @mcp beside @odata turns the service into an MCP server that a second Claude session queries through @cap-js/mcp, an agent annotation adds the A2A protocol with an agent card and an audit log entry for the agent task, and a skill file gives the agent the matching policy.SAP Developers, published 2026-09-25
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
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
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.
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
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.
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
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
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
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
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.
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
HANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingHANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingTwo ways to produce the same embedding, run side by side: HANA Cloud's own VECTOR_EMBEDDING function against Azure OpenAI through the CAP LLM plugin. The CDS side is short — an element of type cds.Vector maps to REAL_VECTOR on deploy — so what remains is the comparison, which is the thing you cannot get from either product's documentation alone.lalitmohan, published 2025-04-09
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
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
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
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.
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.
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
Michael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceMichael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceA pipeline that listens to a song, identifies the historical events it references, retrieves knowledge about each and builds an emotional arc across the whole track. Not an enterprise use case, and useful precisely for that: the plumbing — CAP, HANA, Solace, Claude, ElevenLabs — is doing something the vendor demos never ask of it.Shahid, published 2026-05-18
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
Out-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalOut-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalWalks through SAP AI Core's document grounding: a default 'help.sap.com' data repository that is already grounded, queried either directly through /retrieval/search after labelling a resource group for grounding, or through the orchestration service's grounding_module_config paired with llm_module_config and templating_module_config to inject the retrieved chunks into a prompt. Shows the orchestration service as a unified interface for swapping LLM providers by changing a configuration parameter rather than application code.Joni, published 2025-04-15
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.
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
RAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPRAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPThe end-to-end version: a CAP service exposing the vector engine and the AI hub behind a couple of endpoints, answering where a CodeJam is on a given date. It has aged in a way the author has marked in the page itself — the section on the CAP LLM plugin now carries "(Outdated)" in its own heading — so read the embedding preparation and the retrieval shape, and check the plugin part against the package.KevinR, published 2024-05-21
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.
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
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.
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.
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.
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.
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
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.SAP Developers, published 2026-10-15
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
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
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.
Decision Logic Modernization in SAP Integrations: Using SAP-RPT-1 for Intelligent Routing DecisionsDecision Logic Modernization in SAP Integrations: Using SAP-RPT-1 for Intelligent Routing DecisionsWalks through embedding SAP-RPT-1 — SAP's foundation model for classification and regression over tabular ERP data, hosted on SAP AI Core — into a Cloud Integration flow that picks the optimal 3PL logistics partner for an outbound delivery. The iflow sends historical deliveries from SAP HANA Cloud plus the new delivery as context rows to the model's in-context learning, with no training step, and routes on the returned prediction and confidence score, the mechanism predictive models's core coverage describes for SAP-RPT-1. The author is explicit that SAP-RPT-1 differs from general-purpose language models trained on text, which keeps this apart from an LLM-integration scenario.arunmaarirajha_kv, published 2026-02-16
Federated Machine Learning with SAP DatasphereFederated Machine Learning with SAP DatasphereSAP's design for training predictive models on an external machine learning platform against SAP Datasphere data that is not replicated to that platform. The open-source FedML Python library runs in the platform's notebook, connects to Datasphere over Python/SQLDBC and reads the analytic models in which Datasphere unifies SAP and non-SAP sources; a trained model can then be deployed to SAP AI Core, or in several sub-pages to SAP BTP, Kyma runtime, which is the predictive models path where training happens outside SAP. Sub-pages cover Amazon SageMaker, Azure Machine Learning, Google Vertex AI, Databricks, NVIDIA RAPIDS on GPUs and IBM watsonx.published 2025-01-23
Get hands on with tabular AI and forecasting models in SAP HANA CloudGet hands on with tabular AI and forecasting models in SAP HANA CloudPrediction and forecasting as predictive models inside SAP HANA Cloud, worked through hands-on: tabular AI models such as SAP-RPT-1 for on-the-fly predictions, time series foundation models for ad hoc forecasts, and the AutoML in the predictive analysis library. The abstract names the model kinds and the library and does not say how a model is called from SQL or from an application. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Christoph Morgen, Markus Fath, Ritty Joseph and Tanuja Jadhav, written here from SAP's abstract; the recording is not yet published.
How We Make Tabular Predictions in 2026 with TabPFNHow We Make Tabular Predictions in 2026 with TabPFNA Devtoberfest 2026 session, AI-32, on why a table needs a model of its own: a language model reasons its way to a plausible number, while a tabular foundation model takes the table as context in one forward pass and learns from its features statistically. That is predictive models from both ends — a scikit-learn-shaped fit and predict in a notebook over a heart-disease data set, predicted class probabilities and SHAP values for which features drove the outcome, then the same model reached as an MCP tool by a coding agent that is asked which current customers are most likely to churn. The presenter is from the lab that publishes TabPFN; the Q&A puts it beside SAP's own tabular foundation model, which she says she has not used.SAP Developers, published 2026-10-08
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.
SAP-RPT-1.5 Is Now Generally Available: More Accurate Predictions, Better Explainability, What's NewSAP-RPT-1.5 Is Now Generally Available: More Accurate Predictions, Better Explainability, What's NewAnnounces general availability of SAP-RPT-1.5, the next release of SAP's foundation model for predictive models over tabular enterprise data: in-context classification and regression with no training step, now with stronger accuracy on high-cardinality columns, a maximum API batch of 512 rows (up from 128), and an "explain by example" mode that surfaces the historical rows that most influenced a prediction rather than ranking feature importance alone. Two variants ship, a default model and a -large model recommended past 100 columns or where accuracy is the priority, and the post previews a coming "tabular orchestration" workflow, targeted for general availability in August 2026, that is meant to select the relevant context rows from millions of historical records automatically.RanjeetKr, published 2026-08-14
Transforming Enterprise Data Strategy with SAP Business Data CloudTransforming Enterprise Data Strategy with SAP Business Data CloudSAP's layered picture of SAP Business Data Cloud, from lake storage and compute up to a knowledge core and agents, with eight sub-pages that each work one part through. The data products page is the cataloguing and lineage part: datasets described by Open Resource Discovery metadata, listed in the BDC catalog and shared over Delta Sharing to SAP Databricks and SAP HANA Cloud, with SAP Datasphere as a consumer on the intelligent content page; other pages install intelligent content, bring SAP BW data in through the Data Product Generator, provision groups by SCIM from Cloud Identity Services into SAP Databricks, which is identity provisioning, and train predictive models in SAP Databricks that SAP AI Core then serves for batch and real-time scoring. The main page states direction more than mechanism, and the BW page marks SQL Share for derived and OData for analytical data products as to be available.published 2026-05-12
Unlock predictive and generative AI with your data in SAP HANA CloudUnlock predictive and generative AI with your data in SAP HANA CloudThe AI features SAP lists for SAP HANA Cloud: the function libraries for tabular prediction and forecasting, where predictive models run inside the database, the vector engine, the knowledge graph engine, which is graph, spatial and document data put to generative use, and SQL to LLM calls. The abstract names the engines and the use cases they are meant for and gives no detail of any one of them. A TechEd 2026 session (Tuesday 27 October, Berlin; also DA204V, virtual), presented by Christoph Morgen and Javier Martin, written here from SAP's abstract; the recording is not yet published.
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.SAP Developers, published 2026-10-15
🟣 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
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.
🟣 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.SAP Developers, published 2026-09-24
A Use Case for HANA Cloud Knowledge Graph: AI‑Driven Tender AnalysisA Use Case for HANA Cloud Knowledge Graph: AI‑Driven Tender AnalysisMatching unstructured text against internal data, using both HANA engines at once — the Knowledge Graph for the relationships and the Vector Engine for similarity — with CAP holding the application and its data. Notes that the Knowledge Graph Engine is off by default and has to be enabled when the instance is created, which is the kind of thing that stops a weekend.giacomo_dantonio, published 2026-03-19
Building a Generative AI-powered Inventory Assistant with SAP CAP, RAG, and Vector DatabaseBuilding a Generative AI-powered Inventory Assistant with SAP CAP, RAG, and Vector DatabaseAn existing CAP stock application turned into a question-answering one, and the part worth reading is the schema: three tables, not one — the products, an archive of the text that was embedded, and a separate lookup table holding the vectors. Retrieval finds candidate products by similarity and then reads the real rows, so the answer is grounded in records rather than in the embedded text.furkan5, published 2025-11-07
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.
CAP in the age of AICAP in the age of AISeven live episodes of Hands-on SAP Dev in which DJ Adams works through CAP's AI features with the people who build them, each one a screen-share against a sample project. The first three are @cap-js/mcp: the @mcp annotation on a service, the describe, query and call tools, CQL as the query format, and what authorisation takes out of the tool list. From episode three the run moves to A2A and @cap-js/agents — human approval of an action, agents.md and skills, session persistence, telemetry and sub-agents — and the last two episodes are vector embeddings in CDS, local on SQLite and native on SAP HANA Cloud.published 2026-08-07
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
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
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.
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.
HANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingHANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingTwo ways to produce the same embedding, run side by side: HANA Cloud's own VECTOR_EMBEDDING function against Azure OpenAI through the CAP LLM plugin. The CDS side is short — an element of type cds.Vector maps to REAL_VECTOR on deploy — so what remains is the comparison, which is the thing you cannot get from either product's documentation alone.lalitmohan, published 2025-04-09
Michael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceMichael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceA pipeline that listens to a song, identifies the historical events it references, retrieves knowledge about each and builds an emotional arc across the whole track. Not an enterprise use case, and useful precisely for that: the plumbing — CAP, HANA, Solace, Claude, ElevenLabs — is doing something the vendor demos never ask of it.Shahid, published 2026-05-18
Multi-modal RAG Proof of Concept: facilitating tech supportMulti-modal RAG Proof of Concept: facilitating tech supportA report on a customer proof of concept rather than an implementation guide — there is no code in it. The reason it is here is the architecture paragraph: CAP holds the backend and the use-case logic, the LLM plugins and the SAP Cloud SDK for AI sit inside it, and gpt-4o is one of two nodes in a small langgraph. It opens with a disclaimer that SAP's own Grounding service is due to gain multi-modal features, which dates the whole thing on purpose.maxlienhardt, published 2025-06-03
Out-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalOut-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalWalks through SAP AI Core's document grounding: a default 'help.sap.com' data repository that is already grounded, queried either directly through /retrieval/search after labelling a resource group for grounding, or through the orchestration service's grounding_module_config paired with llm_module_config and templating_module_config to inject the retrieved chunks into a prompt. Shows the orchestration service as a unified interface for swapping LLM providers by changing a configuration parameter rather than application code.Joni, published 2025-04-15
RAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPRAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPThe end-to-end version: a CAP service exposing the vector engine and the AI hub behind a couple of endpoints, answering where a CodeJam is on a given date. It has aged in a way the author has marked in the page itself — the section on the CAP LLM plugin now carries "(Outdated)" in its own heading — so read the embedding preparation and the retrieval shape, and check the plugin part against the package.KevinR, published 2024-05-21
Semantic search in CAP (Node.js): vector embeddings and cosine similaritySemantic search in CAP (Node.js): vector embeddings and cosine similarityFinding the best semantic match for a prompt inside an entity, using local vector embeddings and cosine similarity — and the finding the author leads with is that it works without a vector database at all. Reported as experiments rather than as a pattern, which is the honest register for it: the interesting claim is how little infrastructure the simple case needs.published 2025-12-09
Using HANA Cloud’s "VECTOR_EMBEDDING" Function in CAPUsing HANA Cloud’s "VECTOR_EMBEDDING" Function in CAPEmbeddings generated inside the database rather than fetched from AI Core or an external model — a Q4 2024 HANA Cloud function, used from CAP. The shift it describes is where the embedding step lives, which changes what has to be deployed and what has to be called.published 2025-03-02
Vector RAG vs Graph RAGVector RAG vs Graph RAGA section introduction rather than the comparison itself: it states that the choice between Vector RAG and Graph RAG depends on the domain and the task, and that Vector RAG is the one to use when the subject area has a clear description and the model must be held to specific data structures and attribute values. The four sub-pages it introduces, two on vector-based and two on graph-based RAG, carry the comparison. It sits on the same retrieval question retrieval-augmented generation answers, without naming CDS, CAP or a store.
A Clearer View of Your SAP Integrations Under the New API PolicyA Clearer View of Your SAP Integrations Under the New API PolicyThe SAP API Policy Evidence Skill assesses one SAP interface or usage pattern at a time against SAP API Policy v.4.2026a, reading evidence from five MCP servers, among them servers for the Business Accelerator Hub and SAP Notes, mcp-sap-docs and a read-only ARC-1, and returns one of four labels with a confidence level, an evidence table, residual risk and questions for SAP. It gives no compliant or not compliant answer on purpose, because SAP's FAQ (Q49) declines to publish a binding decision matrix, and it sends legal, commercial and roadmap questions to SAP and lowers its confidence when a source is not connected. Four sample runs show the method, among them ODP-RFC extraction labelled likely not aligned under SAP Note 3255746 and the same API_SALES_ORDER_SRV assessed differently for an autonomous agent behind a custom gateway and for a Boomi middleware flow; the SAP Notes and Business Accelerator Hub servers read SAP sites through a browser login, which the post says to use at your own risk.published 2026-06-02
ABAP + MCP: Let AI Do Real Development in Your SAP SystemABAP + MCP: Let AI Do Real Development in Your SAP Systemabap-adt-mcp is an open-source MCP server that gives an AI agent full ABAP development capability over ADT: it searches, reads, edits, activates and unit-tests objects, and runs ATC checks, on a connected S/4HANA Cloud or on-premise system, acting as the signed-in developer. It runs on abap-adt-api, the same REST client Eclipse's own ADT tooling uses, and sits beside SAP's own ADT MCP Server, shipped with ADT for VS Code and Eclipse under a different server key, and marianfoo's abap-docs, a read-only server over the ABAP Keyword Documentation and Clean ABAP. Each destination carries a policy — read-only, allowed packages, denied tables and tools — the server checks before every call, and an optional audit file logs each tool call with its outcome and policy gate.Willian_Saez, published 2026-09-03
ABAP and Agentic AI: The Hidden Problem in Real ProjectsABAP and Agentic AI: The Hidden Problem in Real ProjectsAI in SAP development splits on three questions, how the model gets context, where writing happens and who controls the setup: UI5 and CAP work in local files where git, reviews, tests and pipelines already gate a change, while on-stack ABAP writes land directly in a shared development system. Six patterns follow, framed after a paper by Lars Hvam, from AI in the IDE to off-stack development with abapGit, and the post settles on a hybrid where the agent reads the system over ADT or MCP and writes through a gated git flow. Read access alone is put at maybe 80 percent of the work, and what agent access to your code still lacks is named as tool governance: read-only defaults, package restrictions, blocking free SQL, per-user identity and auditing.published 2026-04-22
Agentic AI & AI AgentsAgentic AI & AI AgentsSAP's target picture for AI agents: Joule as the engagement layer — Joule Work, Joule Assistants, Joule Agents — with custom agents from customers, partners and SAP teams connecting through A2A for agent-to-agent collaboration and MCP for tool connectivity, on the SAP Business AI Platform. It says up front that parts are not generally available yet, in particular bidirectional communication with third-party agents through the Agent Gateway, so it reads as direction with the building blocks named rather than a design to copy today.published 2026-08-27
Agentic AI Security & GovernanceAgentic AI Security & GovernanceNames seven threat categories agentic AI introduces beyond ordinary application security: prompt injection, excessive agency, supply-chain and model-integrity compromise, memory poisoning, improper output handling, resource abuse and agent-to-agent communication poisoning. Its answer is a defence-in-depth structure of security controls, input validation, privilege management, supply-chain checks, memory segmentation, output validation, execution quotas, secure communication, paired with governance and oversight: audit logging, explainability, human-in-the-loop review, fairness assessment and continuous monitoring. States the reason plainly: an agent decides, chains actions across turns, keeps memory between them and can act on real systems, a different risk profile from a single request-response call. That is the authorisation and audit-trail question tool governance is named for.
Agentic Engineering for SAP BTP ExtensionsAgentic Engineering for SAP BTP ExtensionsAn agent harness coordinates code generation across isolated Git worktrees, using a skills registry, SAP CAP MCP Server, Fiori MCP Server and UI5 Web Components MCP Server for development context. The diagram shows LiteLLM as a model proxy in front of SAP AI Core, while automated checks and review gate the generated changes. The worked scenario is CAP-based extensions on BTP, with specifications written before generation and reusable skills governed across teams.
Building an Enterprise-Ready SAP AI Agent with Open SourceBuilding an Enterprise-Ready SAP AI Agent with Open SourceA self-hosted chat agent for SAP systems: LibreChat as UI and orchestrator with Entra ID sign-in and SharePoint connected, a local LLM through Ollama, and two MCP servers, mcp-sap-docs for public documentation and the ADT MCP server vibing-steampunk for the system itself. The ADT server runs in its read-only mode under a technical user with display authorisations only, so the agent can find a function module and pull its source, or locate a RAP business object with its behaviour definition and projection view, but cannot change anything. Two workflows show it, explaining what BAPI_DISPUTE_CREATE does in one system and planning a RAP action from a PDF specification, where the generated ABAP is copied into Eclipse by hand; the full setup is in the marianfoo/llm-client-sap-system-integration-sharepoint repository.published 2026-03-03
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
Building trusted applications on SAP Business AI Platform by designBuilding trusted applications on SAP Business AI Platform by designBuilding cloud applications on SAP Business AI Platform with security and compliance built in: the identity, connectivity, governance and security services SAP groups under the platform, secure-by-design development, and authorisation and access controls for AI agents. The edges are to Authorization and to Tool governance, the concern of what an agent may call with which authorisations; the abstract names the service categories and no service by name. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Christian Cohrs and Regine Schimmer, written here from SAP's abstract; the recording is not yet published.
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.SAP Developers, published 2026-09-23
From SAP Integration Suite iFlow to MCP Tools: Exposing OData APIs to AI AgentsFrom SAP Integration Suite iFlow to MCP Tools: Exposing OData APIs to AI AgentsBuilds an MCP Server artifact inside SAP Integration Suite's Integration Cell runtime that fronts a Northwind OData V4 API through a Cloud Integration iFlow, turning each OpenAPI operation into a tool an agent can call. Walks through the OAuth2 client-credentials flow against XSUAA and the authorization policy scope — ESBMessaging.send in place of the default API.invoke — that gates access to the MCP server, then tests the server from Claude Code.published 2026-07-14
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.
HANA AI Toolkit — Local MCP ServerHANA AI Toolkit — Local MCP ServerAn MCP server that turns the hana-ml Python library into governed tools an agent can call against a HANA Cloud instance, shipped in the hana-ai toolkit and exposed over stdio, SSE and streamable HTTP. Its one firm rule is attributable execution: an audit module writes the MCP-side identity — agent, model, session, tool, redacted arguments — into the HANA connection before any SQL runs, and fails the call if that write fails. A worked example of governance on an MCP tool surface, from SAP's data side rather than CAP's.published 2026-06-15
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.
Introducing ARC-1: A Secure ADT MCP Server for Enterprise SAP DevelopmentIntroducing ARC-1: A Secure ADT MCP Server for Enterprise SAP DevelopmentWhy ARC-1 exists beside earlier ADT MCP servers such as vibing-steampunk, fr0ster/mcp-abap-adt and dassian-adt: one centrally deployed instance per SAP system instead of a server on each developer laptop, with the MCP client to ARC-1 hop and the ARC-1 to SAP hop authenticated separately. It sets out the restrictive defaults (read-only, no free SQL or named table preview, writes confined to $TMP), the layering in which ARC-1's configuration, the user's role and SAP's own authorisation must all allow an action, Principal Propagation so SAP sees the real user, and audit events to the SAP Audit Log service; that is tool governance as much as agent access to your code. It leaves the BTP setup to the next part, and places ARC-1 beside SAP's ADT MCP Server, which SAP's configuration guide describes as a local HTTP server hosted by the IDE, and beside SAP API Policy 4.2026a, where ARC-1's stated position is to stay close to documented ADT behaviour and ask SAP before production use.published 2026-04-27
MCP Servers are the New Z-TablesMCP Servers are the New Z-TablesA single CAP service exposed as three overlapping MCP servers tools, queried by the same prompt nineteen times, returned the same tool every time — evidence, the author argues, that tool selection rests on the resemblance between a prompt and a tool's description rather than on any binding a where-used list could enumerate before retiring it. It contrasts that setup with @cap-js/mcp, which exposes a whole service as three generic tools instead of one per operation, and quotes the adapter's own beta documentation admitting no rate limiting, audit logging, input validation or approval workflow, and no use as a gateway to SAP Application APIs. From there it names four small Tool governance practices it has adopted: an owner recorded in the tool's own metadata, logging every invocation, deprecating inside the description, and exposing fewer tools.published 2026-08-21
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.
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.
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.SAP Developers, published 2026-10-07
Third-Party MCP Server Access to SAP Solutions on BTPThird-Party MCP Server Access to SAP Solutions on BTPDescribes external MCP servers and custom servers on BTP, 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 BTP does not automatically supply its governance controls.Dhawal Joshi, Harut Ter-Minasyan, Mirko Günther