BlogBlogA post on somebody's own site or a community platform. Nobody edits it after publication, so it dates from the day it was written.See every one →SAP Community
What an AI infra engineer sees when opening SAP's AI stack (1/3): the model gateway
A first look at SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp's Generative AI Hub 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@sap-ai-sdk/orchestrationThe Orchestration Service client of SAP's AI SDK, which applies templating, grounding, filtering and masking around a model call rather than in the application.sap official, cap 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.
Where it sits
Explains
LLM integrationCAPABAPBTPLLM integrationCalling a language model from application code with the tenant, destination and credential handling already solved instead using an SDK call with a hand-rolled key.SAP AI CoreCAPABAPBTPSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.@sap-ai-sdk/orchestrationCAP@sap-ai-sdk/orchestrationThe Orchestration Service client of SAP's AI SDK, which applies templating, grounding, filtering and masking around a model call rather than in the application.
Since then
No major release of @sap-ai-sdk/orchestration since this was published
Source
reachable
Who is behind it
amishkushauthor
Properties
About this work
Group by66 of 66 pieces
Piece, what it offersStill applies
CAP in the age of AI #7 - vector embeddings wrap-upCAP in the age of AI #7 - vector embeddings wrap-upThe same embeddings model taken from SQLite to SAP HANA Cloud, then handed to an agent. Locally it is @cap-js/ai that adds the vector functions SQLite lacks and downloads an all-MiniLM L6v2 ONNX model on first start; on HANA natural language processing has to be switched on, the model name is a mandatory argument, the vectors it returns are 768 dimensions, and dimensions must match on both sides of a comparison. HANA itself can be given SAP AI Core as a remote source for other embedding models, which a CDS.ql expression has to inject because the postfix notation only takes what the CDS model holds, and the hour ends with a search function over cosine similarity exposed over @cap-js/mcp, so an agent asked about low output from solar panels calls semantic search instead of writing the query itself.published 2026-10-16
Unlocking Tabular Foundation Models: From Experimentation to ProductionUnlocking Tabular Foundation Models: From Experimentation to ProductionA Devtoberfest 2026 session (AI-41) on taking tabular prediction from a playground to a deployment. It sets tabular foundation models against a model trained per use case and against language models reading rows as text, explains in-context learning as examples plus the rows whose target column is missing, and tries SAP RPT 1.6 on a train-delay dataset in the RPT playground, including the column and row importance it returns with the prediction. The same prediction is then rebuilt on SAP AI Core, where the tabular orchestration service plays the part the orchestration service plays for language models: a data destination, a table artifact with its CSN schema and a scenario configuration registered once at design time, after which a predict call passes only the query rows, the scenario configuration and a context-selection strategy. The last demo runs those same calls in natural language through the aicore-skills plugin in a coding agent, and one of them only resolves once the agent is told which scenario configuration to use.SAP Developers, published 2026-10-15
CAP in the age of AI #6 - vector embeddingsCAP in the age of AI #6 - vector embeddingsVector embeddings put to work in the incident management sample, answering whether this problem has been seen before. An embedding element of type Vector is calculated and stored from the vector_embedding function, so the database refreshes it whenever the text behind it changes, and cosine_similarity compares it with a freshly embedded string; because a title says little, a scheduled action first summarises each incident's conversation through a model on SAP AI Core and the embedding is taken from that summary. The similar-incidents list is a view joining incidents to themselves, with order and limit set in a before handler on the expanded query, and the vector element excluded from the service, since OData knows nothing about vectors — on SAP HANA Cloud the function is native, while SQLite needs packages added to the project.published 2026-10-09
Building Code-Based AI Agents on the BAIPBuilding Code-Based AI Agents on the BAIPA Devtoberfest 2026 session on writing the agent yourself rather than configuring one, which is the agent tooling edge: an agent is a model with tools, skills, memory and context around it, and the session reads the code of one built in CAP as a LangGraph state graph, with an agent node that calls the model, a tools node holding the MCP clients, and the edge between them looping until no tool is needed. It then shows the shorter route, a CDS service annotated for the agent protocol with its instructions and skills in an agent.md file. SAP AI Core carries both, with the CAP service in front of it as middleware so the credentials never reach the browser, and that is what cap-agent-ui5-webui is demonstrated against: added as a dependency, it gives the annotated service a UI5 chat interface that can be deployed rather than only previewed. A Python multi-agent application on Cloud Foundry, where an orchestrator delegates to per-stack specialists so no single model sees every tool, closes the session.published 2026-10-09
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
How to implement business AI capabilities in ABAP CloudHow to implement business AI capabilities in ABAP CloudA Devtoberfest 2026 session (ABA-32) on embedding AI in an ABAP Cloud application and on making SAP Joule aware of what that application can do. The first demo implements two features of a RAP travel app with the ABAP AI SDK: a determination on an uploaded receipt that sends the image together with the allowed categories and transaction types to a model reached through an intelligent scenario, then writes the extracted description, category, currency and amount back to the expense entity; and a recommendation function, triggered by a side effect on the trip title, that proposes a trip type with a score the Fiori UI sorts the proposals by and leaves the business user to accept — which is LLM integration from ABAP code. The second demo builds a capability for SAP Joule in the Joule Studio code editor in VS Code, with a scenario that extracts a trip title from the user's intent and calls an OData service in the ABAP backend through a BTP destination, deploys it and asks the Joule test UI for the trip's details; the session states that agents reach ABAP only over governed remote APIs — OData, SQL and MCP — and that automatic grounding of custom OData services in the knowledge graph is upcoming rather than available.published 2026-10-05
CAP in the age of AI #5 - agents wrap-upCAP in the age of AI #5 - agents wrap-upThe agents topic closed out on what sits around the agent rather than inside it, now that the documentation has moved into capire. The chat preview's session is persisted in the database rather than kept in memory, traces go out through @cap-js/telemetry to a self-hosted MLflow under the OpenTelemetry conventions for generative AI, and the panel is explicit that @agent reuses the MCP adapter's code programmatically without serving an MCP endpoint. It ends in the xtravels sample, where a travel agent delegates to a hotel-service sub-agent and reaches a separately started flight service over MCP through the service binding CAP resolves anyway. Earlier in the hour the same agent answers from a model running on the presenter's laptop, reached as an OpenAI-compatible endpoint.published 2026-10-02
🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and Compliance🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and ComplianceDevtoberfest 2026 session AI-21. A cross product owner on the SAP AI Core team gives the reasons an AI application ends up on more than one model — a model down at the hyperscaler, a data centre that is not allowed to run it, a version being deprecated — and runs a joke app that answers from Gemini 2.5 Flash in EU10 and from Claude 4.5 Haiku in Asia-Pacific. The walk through AI Core's parts is where the edges hold: prompts kept as templates in the prompt registry, imported through the launchpad and the APIs or synced as YAML from a git repository (Prompt management); the evaluation service scoring one prompt across up to four models per run on built-in or model-as-judge metrics, and the prompt optimizer generating variants against one metric (Agent evals); and the orchestration service harmonising the providers behind one message format with a priority-sorted fallback list (LLM integration). The session also states where a metric has to be designed rather than picked: an exact-JSON match scores an email generator at zero, so the joke app's custom metric judges topic and family-appropriateness instead.SAP Developers, published 2026-10-01
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
🟣 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
UI5 AI Features library is now an npm PackageUI5 AI Features library is now an npm PackageThe release note for a demo turning into a dependency, and it is explicit about why that matters: the earlier version worked, but using it meant cloning the repo and copying both halves, which stops working the moment one of them changes. The post walks through what shipping the CAP plugin and the be.wl.ai control library in one npm version buys — a client and server contract that cannot drift — then lists the eleven controls by group, shows the two-line configuration that activates each half, and notes that this version is actually deployed on BTP behind both a standalone approuter and Work Zone. It closes on the demo repository, written with no library source in it as the test that the package stands alone.published 2026-08-31
UI5 AI Features library is now an npm Package
cds 8, line ended. Affects Runnable code.
Connecting SAP Integration Suite with SAP Document AI and SAP Business AIConnecting SAP Integration Suite with SAP Document AI and SAP Business AIWalks through a Cloud Integration flow in SAP Integration Suite that pulls PDF purchase orders from a Gmail mailbox, extracts header and line-item fields through SAP Document AI's job-submission and polling API, and validates the result with SAP AI Core's generative AI hub using GPT-5-mini as a quality check rather than the source of the extracted values. Groovy steps combine the Document AI confidence score and the model's score into one figure that routes low-scoring purchase orders to manual review, with no S/4HANA posting performed.subhojitSaha, published 2026-08-24
CAP in the age of AI #3 - from MCP to A2ACAP in the age of AI #3 - from MCP to A2AThe episode that finishes @cap-js/mcp with authorisation and then crosses to agents. @requires and @restrict are the same annotations CAP already has, and the plugin reads them to filter the tool list and the describe output per user and per request, so a model is not told about entities the caller cannot reach — where the OData metadata of the same service lists every exposed entity regardless. The second half annotates a service with @agent from @cap-js/agents, which serves it over A2A with an agent card and a chat preview, runs first against a mocked response and then against SAP AI Core bound with cds bind and a hybrid profile, and reuses the MCP adapter's tools rather than defining new ones.published 2026-08-21
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
Natural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesNatural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesThe division of labour is the argument, and it is in the subtitle: the model turns English into a CDS query and CDS runs it, so nothing generates SQL and nothing hallucinates a join. Schema annotations do the resolving. Long, with the package, the repository and the MCP registry entry all linked.Shahid, published 2026-06-25
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackBanking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackThe risk it is chasing is a graph problem stated in banking terms: a borrower who looks safe alone and is the linchpin of a group ten times the size. Multi-agent, mixed AI stack, on BTP and CAP.Shahid, published 2026-06-24
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI Stack
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects A recipe, Runnable code.
Beyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBeyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBuilds a rules-first error-diagnosis pipeline on Cloud Integration in SAP Integration Suite: a Groovy classifier resolves known failures — auth, timeout, malformed payload — deterministically, and only genuinely novel errors reach an LLM through the AI Adapter, after a sanitizer script replaces every payload leaf value with a typed placeholder before it leaves the tenant. SAP HANA Cloud, reached over JDBC, holds a fingerprinted dedup cache and an accumulating table of past diagnoses. It also documents the AI Adapter configuration — Advanced mode, a Bearer-prefixed Secure Parameter, and a connection/processing URL split — needed to reach a non-SAP OpenAI-compatible endpoint, found by the author to be undocumented.Krishna_Karthik, published 2026-06-11
Building an LLM Agent in CAP Java with Spring AIBuilding an LLM Agent in CAP Java with Spring AIThe Java counterpart to the author's own Node.js post, and written as one: connecting to AI Core with the SAP AI SDK, then calling an agent and a tool through Spring AI. Opens with a section on libraries and workflows — which framework does what, and what is left to you — before any code.published 2026-06-08
Building an LLM Agent in CAP Java with Spring AI
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
Calling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioCalling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioA proof of concept wiring SAP AI Core's Claude deployment directly into ABAP with no CAP layer between them: two SM59 HTTP destinations, a hand-written OAuth 2.0 client-credentials exchange, and a regex to unwrap Claude's system/messages response envelope. Most of the effort goes into a system prompt that constrains the model to return one fixed JSON schema of filter fields, which ABAP deserialises with /UI2/CL_JSON and exposes through a RAP custom action so a Fiori search field can drive an OData V4 filter.PranayGaroo, published 2026-06-04
Building an LLM Agent using CAPBuilding an LLM Agent using CAPThe argument is that CAP is already most of what an agent framework wants — services, handlers, a typed model — so the agent is built inside it rather than beside it. AI Core through sap-ai-sdk, then Langchain for the agent and its tools. Long, with a TLDR at the top for people who want the shape without the walk.published 2026-05-27
Building an LLM Agent using CAP
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
Agentic AI on BTP: a Multi‑Agent App with Pydantic AIAgentic AI on BTP: a Multi‑Agent App with Pydantic AISplits a single CAP/TypeScript agent that had grown to juggle five BTP MCP servers behind one bloated tool list into btp-multiagent-app, a Python and Pydantic AI rewrite where the Cloud Foundry and BTP Core MCP servers each get a dedicated specialist agent, with an audit log specialist scaffolded but left disabled, behind an orchestrator whose only tools are delegation calls to those specialists, which is the agent-tooling pattern the piece works through. Each specialist authenticates to its MCP server over Streamable HTTP with OAuth 2.1, and a shared module centralises the SAP AI Core GenAI Hub model setup behind two credential layouts, one for local runs and one for the Cloud Foundry service binding, the LLM integration side of the rewrite. Tool lists per agent drop from well over a hundred to a dozen or two, and routing failures become separable from tool-misuse failures by reading the trace.published 2026-05-03
Agentic AI on BTP: a Single Agent with LangGraphAgentic AI on BTP: a Single Agent with LangGraphA CAP TypeScript agent puts a LangGraph StateGraph in front of AzureOpenAiChatClient from @sap-ai-sdk/langchain, reaching SAP AI Core's Generative AI Hub, and lets its tool-calling loop draw on five deployed MCP servers — OData MCP Proxy, CI MCP Server, AI Core MCP Server, BTP MCP Server and BTP CF MCP Server — through @langchain/mcp-adapters' MultiServerMCPClient. Because agent, servers and APIs share one XSUAA tenant, the chat service forwards the signed-in user's own JWT instead of a service account, so each downstream server enforces that user's own authorizations. Past roughly a hundred combined tools the single prompt slows down and stops separating concerns, which is why the author's next post splits it into one specialist agent per MCP server behind an orchestrator.published 2026-05-03
Enhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginEnhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginStarts from the blank form nobody wants to fill in, and asks what an enterprise application should do about it. The AI is in service of that rather than the subject of it.published 2026-04-29
What Happens to Your Data When You Enable SAP's AI Features?What Happens to Your Data When You Enable SAP's AI Features?Traces where a prompt goes when Joule, the Generative AI Hub or the orchestration service calls a third-party model through SAP AI Core: the prompt and the business context around it travel to a model such as GPT-4o, Claude or Gemini for inference, and masking through SAP Data Privacy Integration is an optional orchestration module rather than a default, so with no masking block in the @sap-ai-sdk/orchestration client config nothing is masked. On the masking options, which the author says he confirmed with SAP AI Core product management, anonymization discards the original value and pseudonymization keeps it reversible; DPI recognizes person names, email addresses and phone numbers, plus custom entities defined by regex, which leaves commercially sensitive non-PII such as a revenue forecast or a project codename to pass through unless someone writes a pattern for it, and whether that data is covered at all is one of three answers the post marks as still pending. The "no training" assurance for third-party providers is read as contractual rather than technical, and models hosted and managed by SAP, Mistral among them, are named as a path other than a US-hyperscaler-hosted one.jaripie, published 2026-04-23
Integrating a Custom AI Model into SAP CAP Using AI LaunchpadIntegrating a Custom AI Model into SAP CAP Using AI LaunchpadYour own model rather than a hosted one: deployed to AI Core, made callable through AI Launchpad, then reached from CAP. The case a lot of companies ask about and few posts cover.egeAksoyek, published 2026-03-20
Integrating a Custom AI Model into SAP CAP Using AI Launchpad
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
SAP Integration Suite: Intelligent Integration with AI AdapterSAP Integration Suite: Intelligent Integration with AI AdapterThe AI Adapter adds generative AI as a receiver step inside a Cloud Integration flow, connecting through either AICore-GenAIHub — a single API onto SAP AI Core's Generative AI Hub and its foundation models — or Custom-OpenAI-Rest, a plain REST call out to a provider such as OpenAI. SAP Integration Suite starts the call from the iFlow and feeds the model's response into the next step, which is the mechanics behind the sentiment-analysis, summarisation and routing use cases the piece lists without walking through any one of them.meena_choudhary, published 2026-01-28
cds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPcds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPNames a cost most CAP-plus-LLM writing ignores: every JSON payload streamed to a model is billed by its verbosity, in latency as well as money. The plugin brings TOON — Token-Oriented Object Notation — to a CAP service so the wire format changes without the service code doing so, in a REST variant and an OData one, with token counts reported on both sides.published 2026-01-25
UI5 MCP Server Got Extended for UI Integration Cards GenerationUI5 MCP Server Got Extended for UI Integration Cards GenerationVersion 0.2.1 of the UI5 MCP Server adds three tools for UI Integration Cards: get_integration_cards_guidelines feeds an agent current best practices and API versions, create_integration_card scaffolds a new card project, and run_manifest_validation checks the generated manifest against the schema. The post frames these as closing the same gaps as the server's existing tools — an LLM's outdated or wrong card API knowledge — this time for scaffolding and validating a card rather than a full app.daniel_vladinov, published 2026-01-22
Enhancing Business Processes with SAP BTP AI in SAP Integration SuiteEnhancing Business Processes with SAP BTP AI in SAP Integration SuiteWalks through a post-exit iflow in SAP Integration Suite that calls an LLM through SAP AI Core's Generative AI Hub to turn a customer's free-text return comment into one of a fixed set of SAP rejection-reason codes, so an inbound ORDERS05 IDoc carries a decision (E1EDP01-ABGRU) the ERP can act on without pausing for manual review. The worked example is a Commerce Cloud returns flow into S/4HANA; the piece argues the same bounded-classification pattern fits other narrative fields — delivery-exception remarks, expense-claim justifications — where the cost of an LLM call is repaid by removing a human review step, and points to a colleague's post on the Generative AI Hub orchestration workflow for the guardrailing (prompt templating, data masking) it only names.arunmaarirajha_kv, published 2025-12-15
Prompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesPrompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesA user story in, a scaffolded full-stack CAP application out, through SAP Build Code and Joule. The question it is actually asking is how much of the foundational code is worth generating, and it answers by generating all of it.AnuradhaDhingan, published 2025-12-11
Streaming LLM Output with CAP and WebSocketsStreaming LLM Output with CAP and WebSocketsTokens arriving from the AI SDK's orchestration module, forwarded to the browser as they come rather than after the model finishes. Covers all four pieces — enabling WebSocket support in CAP, a service with actions and events, the streaming itself, and a frontend on the native WebSocket API — which is what makes it the clearest case for why a CAP service would want a socket at all.RobinP, published 2025-11-18
Streaming LLM Output with CAP and WebSockets
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A recipe, Runnable code.
How to Reduce Prompt Token Costs Using Toon = Save MoneyHow to Reduce Prompt Token Costs Using Toon = Save MoneyToken spend treated as a running cost rather than a detail, and TOON as the lever. Companion reading to the CAP adapter for the same format that is indexed here.Yogananda, published 2025-11-12
How to Reduce Prompt Token Costs Using Toon = Save Money
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A recipe, Runnable code.
Generative AI on SAP BTPGenerative AI on SAP BTPThe reference shape for a generative AI application on BTP: a CAP backend, SAP HANA Cloud holding data and embeddings for similarity search through its vector engine, and the Generative AI Hub in SAP AI Core as the single access point to foundation models. It shows retrieval-augmented generation on that stack and names the CAP plugins and SDKs that connect the pieces, for both Cloud Foundry and Kyma.published 2025-09-02
Generative AI on SAP BTP
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A reference.
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
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
Elevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginElevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginThe question underneath the enthusiasm: what leaves your landscape when a prompt goes to a model. The plugin's answer is to anonymise the sensitive fields through HANA before the prompt is sent, and this is the post that explains why that is the design rather than an option.AkashAmarendra, published 2024-02-02
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIAn Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIA dormant internal app at SAP Japan revived with AI, built to solve a problem the team actually had — colleagues who could not talk to each other. Build Apps on the front, CAP on Kyma behind it, OpenAI in the middle.javieryw, published 2024-01-31
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAI
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
GenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportGenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportA sample application rather than an explainer, and the author says so in the opening — enough talking, here is something that runs. Incoming support mail summarised and categorised through the generative AI hub in AI Core.martinfrick, published 2023-11-15
Automate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsAutomate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsA process that drafts its own text: ChatGPT writing job postings, SAP Build Process Automation carrying them through approval, and CAP in between. Presented as a generic pattern the author expects to be adapted rather than copied.shivamshukla12, published 2023-08-10
Creating a meal generator application with SAP Build, Cloud Application Programming and openAICreating a meal generator application with SAP Build, Cloud Application Programming and openAIIngredients in, meal suggestions out, assembled from BTP services plus OpenAI and Google APIs. A small application built for the pleasure of it, and useful here as the plainest example of CAP holding the middle of a generative flow.former_member793421, published 2023-07-17
Empowering Your Data Analytics with GPT-3 and SAP CAP IntegrationEmpowering Your Data Analytics with GPT-3 and SAP CAP IntegrationFree text in, SQL out, answer back in a sentence — the model writes the query, CAP runs it, and the model turns the rows into prose. Written in the GPT-3 window, so the model access has dated, but the three-step shape has not, and it is a different bet from retrieval: nothing is embedded, the schema is the context.Former Member, published 2023-03-10
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3The SAPUI5 frontend of the sample, and mostly an argument for writing UI5 in TypeScript: ES imports in place of sap.ui.define, a class with real private members in place of the underscore convention, and the service types generated from the CDS model copied into the UI package, so one IChats interface types the OData object the controller reads. The second half is structure — a formatter class and a singleton LayoutManager called from the XML view through core:require, a confirmation helper taking a callback, a dialog class resolving a promise, a generic createEntity<T> on a service class — all of it to keep every controller under 100 lines. What it says about arranging a UI5 app holds whatever model sits behind the chat; the tooling around it is of its date, and the post calls UI5's TypeScript support experimental.published 2023-02-27
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3
cds2types. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3The backend: CAP with TypeScript, the entities holding chats and personalities, and the service that talks to the API. This is where the streamed completion and the repositories behind the handler come from, which is the part of the sample still worth lifting even though the model access has since been superseded by AI Core.published 2023-02-24
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3
cap-ui5-gpt-chat: no published releases, repository quiet for 41 months. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3The concepts before the code: what the GPT model and its API actually offer, and what the finished chat application looks like — personalities included. Written in the weeks when the ground was moving under it, and the post carries its own change log to prove it: GPT-3.5 added on 1 March, GPT-4 on 15 March, and an admission that a series planned as two posts became three.published 2023-02-22
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3
cap-ui5-gpt-chat: no published releases, repository quiet for 41 months. Affects Runnable code.
Access to Generative AI ModelsAccess to Generative AI ModelsSets out the plain way to call a deployed generative AI model on SAP BTP: a request that carries the prompt, the model and the parameters that control generation, with the same code able to switch between models. It lists data masking, prompt templating and filtering as features that come with the access rather than as code the caller writes, which is the shape LLM integration takes on the BTP door; the page's implementation sections sit behind its steps and were not read.
ABAP AI SDK powered by ISLM - How to implement your own AI use cases in ABAPABAP AI SDK powered by ISLM - How to implement your own AI use cases in ABAPA Devtoberfest 2026 ABAP-track session (ABA-44) on the ABAP AI SDK: an intelligent scenario development object holds the model and its version, so the ABAP code asks for an API, sends a prompt and reads the completion with its token counts and finish reason, and swapping the model is a change to that object rather than to the code. Four demos go through the ABAP line by line — a bare completion, a system prompt with the temperature set to 0.2, tool calls where the model asks for order details and the result goes back into the message container, and a JSON response schema that returns category, severity and goodwill as fields a program can act on — and a fifth replaces the API with the SDK's own mocks so unit tests run with no network call, which is what the LLM integration edge on the ABAP door rests on. The closing availability matrix separates base scenarios, available across SAP S/4HANA on-premise, private edition, public cloud and the SAP BTP ABAP environment, from the orchestration service and SAP RPT, shown for on-premise and private cloud with transport-based correction instructions back to release 2022 and not yet for the public cloud editions.SAP Developers
Agentic CAP: Build MCP servers and enterprise AI agentsAgentic CAP: Build MCP servers and enterprise AI agentsCAP applications become AI agents over the Model Context Protocol and the Agent2Agent protocol, which is the serve your application over MCP concern, and SAP AI Core is the LLM integration through which AI is embedded in a CAP app, with recommendations from the SAP-RPT-1 model as the abstract's example. The abstract names the two protocols and the one model and does not say which packages carry them. A two-hour TechEd 2026 session in a hands-on room (Tuesday 27 October, Berlin), presented by Daniel Hutzel, Daniel Schlachter, Marc Huber and Sami Lechner, written here from SAP's abstract; the recording is not yet published.
AI-enabled administration: Automating log analysis with generative AI hubAI-enabled administration: Automating log analysis with generative AI hubA log analysis tool for incident work, built in SAP Business Application Studio with the generative AI hub feature, which SAP AI Core ships as its LLM integration by its own documentation: it automates root-cause analysis over system errors and masks sensitive data. SAP's abstract states the tool's jobs and not how the hub is called, what the masking covers or which model answers. A TechEd 2026 session (Wednesday 28 October, Berlin), with no speaker listed in the catalogue at the time of writing, written here from SAP's abstract; the recording is not yet published.
Stop guessing, start counting: How generative AI fixed an inventory messStop guessing, start counting: How generative AI fixed an inventory messAn inventory-counting application a business built on SAP Business AI Platform with SAP HANA Cloud and generative AI, to replace recount lists kept by gut feel across SAP ERP Central Component, SAP S/4HANA and Microsoft Excel; the talk promises the app, its architecture and what went wrong. The generative AI part is LLM integration from application code; the abstract names HANA Cloud and generative AI as the two building blocks and says nothing about how either is used. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Ranjeet Kumar, written here from SAP's abstract; the recording is not yet published.
Content FilteringContent FilteringContent filtering screens a large language model's input and output for low-quality, irrelevant or unsafe content: the four categories it names being hateful, violent, sexual and vulgar content, checking a request once on the way in and once on the way back. The page states smaller models can do this filtering efficiently, reading perplexity scores to flag anomalies, with the aim that SAP AI Core produces content meeting a stated safety standard, which is the ground content filtering covers on the BTP door.
Data MaskingData MaskingData masking replaces identifiable or confidential text in a prompt with placeholders such as <Person_0> or <Organization_1> before it reaches a large language model, using pattern matching and machine learning to find what to replace. The page states SAP AI Core supports it as a feature and sets out five steps for applying it, defining the masking scope, choosing a technique, preserving the prompt's intent, checking compliance and risk, then testing and monitoring the result. That is the shape data masking takes on the BTP door.
Document GroundingDocument GroundingDocument Grounding is a managed retrieval-augmented-generation service under the Generative AI Hub on BTP, which SAP's page on SAP AI Core places inside that service: it ingests documents from Amazon S3, SharePoint, SAP Document Management Service, SAP Work Zone or an SFTP server, and handles chunking, embedding and retrieval itself, refreshing content automatically when a source document changes. The page states this managed path is recommended for most enterprise scenarios because it covers the whole lifecycle end to end, and offers a separate Document Grounding Vector API for data that is already chunked and embedded, for cases that need finer control over chunking and metadata.
Prompt TemplatingPrompt TemplatingPrompt templating replaces a static prompt with a structured, reusable template whose placeholders are filled in at runtime, which the page says helps LLM responses stay consistent and lets the same instructions be adapted across tasks. On SAP AI Core this is implemented through the Prompt Registry, and the page states that storing prompts as plain strings in code is possible but not recommended. That is prompt management as a stored and managed object rather than a string embedded in the caller.
Enriching AI models with SAP AI Core in SAP Business Data CloudEnriching AI models with SAP AI Core in SAP Business Data CloudThe integration between SAP Business Data Cloud and SAP AI Core, through which data products with their semantics feed AI models for benchmarking, custom AI development and agentic analytics and applications. The abstract names the two products and the three uses and states nothing about how the data reaches AI Core or what the integration consists of. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by San Tran and Sandy Tran, written here from SAP's abstract; the recording is not yet published.
Build AI agents and applications natively on SAP HANA CloudBuild AI agents and applications natively on SAP HANA CloudSAP HANA Cloud as the base for agentic applications on SAP Business AI Platform: the session goes through CAP, the SAP HANA Cloud vector engine and SAP AI Core, with architecture patterns and lessons learned from building AI-supported applications. SAP's abstract names the three parts of that stack and the vector engine as the database's feature in it, and describes none of the patterns. A TechEd 2026 session (Wednesday 28 October, Berlin; also DA113V, virtual), presented by Christoph Morgen and Shraddha Shetty, written here from SAP's abstract; the recording is not yet published.
Building agentic applications with SAP HANA CloudBuilding agentic applications with SAP HANA CloudA CAP application extended with semantic search and agent features on top of SAP HANA Cloud's vector engine and SAP AI Core, built in a hands-on workshop. The abstract names the parts, CAP, the vector engine and AI Core, and the two additions: semantic search, the retrieval half of retrieval-augmented generation, and LLM-supported agent capabilities inside the application, which is agent tooling. Which embedding model, which CAP runtime and how the agent calls its tools are not stated. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Hui Li, Ritty Joseph, Shraddha Shetty and Tanuja Jadhav, written here from SAP's abstract; the recording is not yet published.
Agentic memory: Knowledge graph engine and recall in SAP HANA CloudAgentic memory: Knowledge graph engine and recall in SAP HANA CloudThe knowledge graph engine in SAP HANA Cloud as an agent's memory: what the engine, the graph side of graph, spatial and document data, does in an agentic workflow, how an agent keeps what it learns there, the state agent tooling holds between turns, and the SAP AI Core integration through which the database calls LLMs and tabular foundation models such as SAP-RPT-1. The abstract names the engine, the memory role and the AI Core link and does not say how the memory is written or read. DA263 on Wednesday 28 October is a two-hour hands-on on the same engine with a different cast. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Markus Fath and Shraddha Shetty, written here from SAP's abstract; the recording is not yet published.
Knowledge graph and agent memory: Build an agent that remembersKnowledge graph and agent memory: Build an agent that remembersThe knowledge graph engine in SAP HANA Cloud as an agent's memory: what the engine, the graph side of graph, spatial and document data, does in an agentic workflow, how an agent keeps what it learns there, the state agent tooling holds between turns, and the SAP AI Core integration through which the database calls LLMs and tabular foundation models such as SAP-RPT-1. The abstract names the engine, the memory role and the AI Core link and does not say how the memory is written or read. DA205 on Tuesday 27 October is the 45-minute talk on the same engine, with a near-identical abstract and a different cast. A two-hour hands-on TechEd 2026 session (Wednesday 28 October, Berlin), presented by Christoph Morgen, Jan Zwickel, Markus Fath and Thomas Hammer, written here from SAP's abstract; the recording is not yet published.
SAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core read as the management and orchestration layer of an AI architecture, beyond the model runtime: SAP's abstract lists extending Joule Agents, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. It names the connections and not the APIs behind them. A TechEd 2026 session (Tuesday 27 October, Berlin; also RA107V, virtual), presented by Franziska Dobrigkeit and Hadi Hares, written here from SAP's abstract; the recording is not yet published.
Joule and SAP Knowledge Graph: Context-aware AI across SAP solutionsJoule and SAP Knowledge Graph: Context-aware AI across SAP solutionsThe catalogue carries RA107's abstract under this title, and what it describes is SAP AI Core as the management and orchestration layer of an AI architecture: extending Joule Agents in SAP Joule, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. The SAP Knowledge Graph the title names does not appear in that text, so the edges rest on the abstract as published, and whether the session follows the title or the abstract is not known until it is recorded. A TechEd 2026 session (Wednesday 28 October, Berlin; also RA110V, virtual), presented by Jan Portisch and Pavithra G K, written here from SAP's abstract; the recording is not yet published.
Build business differentiation with SAP AI CoreBuild business differentiation with SAP AI CoreSAP AI Core as the orchestration layer for enterprise AI, worked through with SAP's engineers: extend Joule Agents with models from its library, ground them in SAP Business Data Cloud products, embed them in SAP S/4HANA flows, then govern, scale and monitor them from prototype to production. The abstract says what the layer does for an agent and not which services carry each step. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by David Knaack, Franziska Dobrigkeit, Hadi Hares and Jonas Israel, written here from SAP's abstract; the recording is not yet published.
SAP-RPT and TabPFN: Get started with tabular foundation modelsSAP-RPT and TabPFN: Get started with tabular foundation modelsTabular foundation models, SAP-RPT and TabPFN, in a hands-on with SAP and Prior Labs: the model families first, then predictions run through SAP AI Core with a workflow built on tabular orchestration and connected to the participant's own data for real-time predictions. A predictive models session with the models as the subject; the abstract does not name the SDK or API the workflow is built with. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Eliott Kalfon, Janick Zaehringer-Frasch, Johannes Hoehne, Katharina Schell, Nilay Mehta and Sherene Tan, written here from SAP's abstract; no recording is announced.
Behind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain ModelsBehind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain ModelsThe strategy behind SAP Business AI's intelligence layer: SAP Knowledge Graph for enterprise context, SAP Domain Models for SAP-specific expertise and tabular AI for predictions, unified on SAP AI Core with SAP Document AI. Knowledge Graph and Domain Models are not atlas entries, so the edges rest on the two products the abstract names as the infrastructure and on Predictive models for the tabular AI; nothing is stated about what any of them does in the layer. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST103V, virtual), presented by Jan Portisch and Richard Grandpierre, written here from SAP's abstract; the recording is not yet published.
SAP Joule for Consultants: Unified knowledge for requirements and designsSAP Joule for Consultants: Unified knowledge for requirements and designsFit-to-standard analysis as a consultant on a cloud transformation project: connecting an organisation's data to SAP Joule for Consultants through SAP AI Core, getting answers from SAP knowledge and that content, then building an expert, loading project files and running guided prompts. The edges are to SAP Joule, of which Joule for Consultants is a part, and to SAP AI Core, named as the connection path; how the data is grounded is left to the session. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Anantharaman Ravi, Natalie Han, Sachin Kaura and Yi Hsuan Lin, written here from SAP's abstract; the recording is not yet published.
Ship your own sandboxed AI operations agent to Kyma in two hoursShip your own sandboxed AI operations agent to Kyma in two hoursAn operations agent built and then broken on purpose: the abstract has participants deploy a reasoning agent to SAP BTP, Kyma runtime, connect it to SAP AI Core, give it observability over the runtime and cause a failure for it to diagnose, the operations automation concern with an agent doing the diagnosis. Patterns for cost control and monitoring are promised at the end; the agent framework and how the sandbox is drawn are not named. A TechEd 2026 session (Tuesday 27 October, Berlin, two hours), presented by Christian Lechner, Piotr Tesny, Thorsten Sandfuchs and Vipin VijayKumar, written here from SAP's abstract; the recording is not yet published.
Details
Graph
LLM integrationcapability, core and community
SAP AI Coreartifact
@sap-ai-sdk/orchestrationartifact
SAP Communitypublishing source
SAP Communitybtp-tag
Source
Type
blog
Published on
Host
community.sap.com
Discovered via
First seen
History
- Entered the atlasDiscovered via SAP Community · btp-tag.
For your agent
- Ref
content:what-an-ai-infra-engineer-sees-when-opening-sap-s-ai-stack-1-3-the-model-gateway- JSON
- /content/what-an-ai-infra-engineer-sees-when-opening-sap-s-ai-stack-1-3-the-model-gateway.json
- MCP
- Connecting an agent