Reference architectureReference architectureA published architecture with a diagram and named components. The topology outlasts the product names in it.See every one →SAP Architecture Center
Generative AI on SAP BTP
The reference shape for a generative AI application on BTP: a CAP@sap/cdsThe CAP Node.js runtime, which compiles the CDS model, serves the services declared in it, answers generic requests before any handler runs, and loads every cds-plugin.sap official, cap backend, SAP HANA CloudSAP HANA CloudThe managed database under most of this: CAP's default target, the store Datasphere and Analytics Cloud sit on, and a service with plans and components.sap official, btp 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.
Where it sits
Explains
LLM integrationCAPBTPLLM 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.Retrieval-augmented generationCAPBTPRetrieval-augmented generationGrounding a model's answer in data retrieved at question time: text split into chunks, each chunk embedded as a vector, and the chunks nearest to the question placed into the prompt. Semantic search is the same retrieval with a person reading the matches, and fine-tuning changes the model's weights, not its input.
Use cases
Answer a question from records in a CAP serviceAnswer a question from records in a CAP serviceCited as a scenario of the way "Through cap-llm-plugin's single retrieval method".
Since then
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28
Source
reachable
Who is behind it
SAP Architecture CenterSAP Architecture CenterWrote this
In the atlas: maintains 1, wrote 26author
In the atlas: maintains 1, wrote 26author
Before you read it
ApplicabilityCore changedLLM integration changed in @cap-js/ai 1.0.0, 2026-04-28.
This is a derived prompt to re-check the work, not a claim that the work is wrong. Exact stale statements are recorded separately after editorial review.
Architecture
parts read from 4 readme files,Parts, as the source names them
- Useran actorinteracts with the application through the user interface and submits promptsRA0005 1-basics/readme.md in SAP/architecture-center
In this architecture, the Cloud Application Programming (CAP) model serves as the central point for managing application logic and sending prompts, either through well-designed, integrated prompt templates within the application itself or via a user interface like SAPUI5 for end-user interaction.
RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-centerThe user submits a question or prompt, which is transformed into a dense vector (embedding) by an embedding model.
- @sap/cdscentral hub for application and domain logicSAP BTPRA0005 readme.md in SAP/architecture-center
In the provided Reference Architecture, CAP serves as the central hub for application and domain logic, interacting with SAP solutions (Cloud or On-Premise), 3rd party applications, and managing data sources such as SAP HANA Cloud.
RA0005 1-basics/readme.md in SAP/architecture-centerIn this architecture, the Cloud Application Programming (CAP) model serves as the central point for managing application logic and sending prompts, either through well-designed, integrated prompt templates within the application itself or via a user interface like SAPUI5 for end-user interaction.
RA0005 2-semantic-search/readme.md in SAP/architecture-centerCAP natively supports embeddings as part of its data schema, allowing for seamless integration of vector representations.
- SAP HANA Cloudstores data and embeddings for similarity search through its Vector EngineSAP BTPRA0005 readme.md in SAP/architecture-center
At its core, this reference architecture features a [CAP](#sap-cloud-application-programming-model)-based backend to manage application logic, SAP HANA Cloud for storing data, including embeddings to facilitate similarity search with the power of its [Vector Engine](#vector-engine), and the [Generative AI Hub](#generative-ai-hub) as the central access point to Foundation Models and Large Language Models (LLMs).
RA0005 2-semantic-search/readme.md in SAP/architecture-centerThese vectors are then stored and indexed within SAP HANA Cloud's [Vector Engine](../readme.md#vector-engine), enabling fast similarity searches through methods like cosine similarity.
- SAP AI CoreGenerative AI Hub: central access point to foundation models, with orchestration and groundingSAP BTPRA0005 readme.md in SAP/architecture-center
At its core, this reference architecture features a [CAP](#sap-cloud-application-programming-model)-based backend to manage application logic, SAP HANA Cloud for storing data, including embeddings to facilitate similarity search with the power of its [Vector Engine](#vector-engine), and the [Generative AI Hub](#generative-ai-hub) as the central access point to Foundation Models and Large Language Models (LLMs).
RA0005 readme.md in SAP/architecture-centerThe [Generative AI Hub](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/generative-ai-hub-in-sap-ai-core) incorporates Generative AI into your AI activities in [SAP AI Core](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-core?region=all) and [SAP AI Launchpad](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-launchpad?region=all).
RA0005 readme.md in SAP/architecture-centerAn important feature of the Generative AI Hub is [Orchestration](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration), which combines content generation via an [Harmonized API](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/harmonized-api) with essential functions often required in business AI scenarios.
RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center[SAP’s Orchestration Workflow](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration-workflow) contains a [Grounding module](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/grounding) which provides specialized data retrieval through vector databases.
- SAP AI Launchpadmanages AI use cases across AI runtimesSAP BTPRA0005 readme.md in SAP/architecture-center
The [Generative AI Hub](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/generative-ai-hub-in-sap-ai-core) incorporates Generative AI into your AI activities in [SAP AI Core](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-core?region=all) and [SAP AI Launchpad](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-launchpad?region=all).
RA0005 readme.md in SAP/architecture-centerCustomers and partners can use SAP AI Launchpad to manage AI use cases (scenarios) across multiple instances of AI runtimes (such as SAP AI Core).
- cap-llm-pluginplugin within the application logic for Generative AI solutionsSAP BTPRA0005 readme.md in SAP/architecture-center
Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/).
RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-centerCustom CAP based application can benefit from the CAP LLM Plugin for efficient and faster development.
RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-centerThe CAP LLM Plugin also supports anonymization.
- @sap-ai-sdk/foundation-modelsSDK within the application logic for the Generative AI Hub and the Vector EngineSAP BTPRA0005 readme.md in SAP/architecture-center
Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/).
RA0005 2-semantic-search/readme.md in SAP/architecture-centerAdditionally, various SDKs and plugins, such as the [SAP Cloud SDK (for AI)](https://github.com/SAP/ai-sdk-js), [CAP LLM Plugin](https://github.com/SAP-samples/cap-llm-plugin-samples) and [LangChain](https://www.langchain.com/), enhance the embedding process and streamline integration with both, the Generative AI Hub and the Vector Engine.
- @sap-ai-sdk/orchestrationSDK client for the orchestration configurationSAP BTPRA0005 readme.md in SAP/architecture-center
However, details for each module can be configured, and optional modules can be omitted by including an orchestration configuration in JSON format with the request body or even easier leveraging the [SAP Cloud SDK for AI](https://sap.github.io/ai-sdk/).
RA0005 1-basics/readme.md in SAP/architecture-centerThe [Orchestration Service](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration) provides a harmonized API for content generation (e.g., LLM completions) and includes key functionalities such as prompt templating and content filtering, making it even easier and more efficient to work with these models.
- SAP BTP, Cloud Foundry RuntimeruntimeSAP BTPon On the Cloud Foundry runtimeRA0005 readme.md in SAP/architecture-center
This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications.
RA0005 readme.md in SAP/architecture-center[SAP BTP, Cloud Foundry Runtime](https://discovery-center.cloud.sap/serviceCatalog/cloud-foundry-runtime?region=all) lets you develop polyglot cloud-native applications and run them on the SAP BTP Cloud Foundry environment.
- SAP BTP, Kyma runtimeruntimeSAP BTPon On the Kyma runtimeRA0005 readme.md in SAP/architecture-center
This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications.
RA0005 readme.md in SAP/architecture-center[SAP BTP, Kyma runtime](https://discovery-center.cloud.sap/serviceCatalog/kyma-runtime/?region=all) is a fully managed Kubernetes runtime based on the open-source project "Kyma".
- @sap/approuterconsuming application that accesses the HTML5 static contentSAP BTPRA0005 readme.md in SAP/architecture-center
In runtime, the service enables the consuming application, typically the application router, to access HTML5 application static content in a secure and efficient manner.
- SAP HTML5 Application Repository service for SAP BTPcentral storage of HTML5 applicationsSAP BTPRA0005 readme.md in SAP/architecture-center
[SAP HTML5 Application Repository Service for SAP BTP](https://discovery-center.cloud.sap/serviceCatalog/html5-application-repository-service?region=all) enables central storage of HTML5 applications on SAP BTP.
RA0005 readme.md in SAP/architecture-centerIn runtime, the service enables the consuming application, typically the application router, to access HTML5 application static content in a secure and efficient manner.
- SAP Destination servicebackend destination detailsSAP BTPRA0005 readme.md in SAP/architecture-center
[SAP Destination service](https://discovery-center.cloud.sap/serviceCatalog/destination?service_plan=lite®ion=all&commercialModel=cloud) lets you retrieve the backend destination details you need to configure applications in the Cloud Foundry environment.
- SAP Authorization and Trust Management serviceuser authorizations and trust to identity providersSAP BTPRA0005 readme.md in SAP/architecture-center
[SAP Authorization and Trust Management Service](https://discovery-center.cloud.sap/serviceCatalog/authorization-and-trust-management-service?region=all) lets you manage user authorizations and trust to identity providers.
- Cloud Identity Servicesidentity providerRA0005 readme.md in SAP/architecture-center
Identity providers are the user base for applications. We recommend that you use the SAP Identity Authentication Service (IAS), an SAP on-premise system, or a custom corporate identity provider.
- SAP Business Application Studiodevelopment environmentSAP BTPRA0005 readme.md in SAP/architecture-center
[SAP Business Application Studio](https://discovery-center.cloud.sap/serviceCatalog/business-application-studio?region=all) (the next generation of SAP Web IDE) is a powerful and modern development environment, tailored for efficient development of business applications for the Intelligent Enterprise.
- SAP Continuous Integration and DeliveryCI/CD pipelinesSAP BTPRA0005 readme.md in SAP/architecture-center
[SAP Continuous Integration and Delivery service](https://discovery-center.cloud.sap/serviceCatalog/continuous-integration--delivery?region=all) lets you configure and run predefined continuous integration and delivery (CI/CD) pipelines that automatically build, test, and deploy your code changes to speed up your development and delivery cycles.
Roles the source leaves open
- Plugins and SDKs within the application logica capability, LLM integrationRA0005 readme.md in SAP/architecture-center
Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/).
RA0005 1-basics/readme.md in SAP/architecture-centerFurthermore, various SDKs, frameworks, and plugins, such as [SAP Cloud SDK (for AI)](https://github.com/SAP/ai-sdk-js), [LangChain](https://www.langchain.com/), and [CAP LLM Plugin](https://github.com/SAP-samples/cap-llm-plugin-samples), can be leveraged within CAP to not only streamline interactions with the Generative AI Hub but also simplify implementation and enhance robustness by using features like [Output Parsing](https://js.langchain.com/docs/concepts/#output-parsers).
The source draws it as cap-llm-plugin, @sap-ai-sdk/foundation-models, @sap-ai-sdk/orchestration.
- @cap-js/ai
- @sap-ai-sdk/ai-api
- @sap-ai-sdk/core
- @sap-ai-sdk/foundation-models
- @sap-ai-sdk/orchestration
- @sap-ai-sdk/prompt-registry
- @ui5/webcomponents
- ABAP AI SDK
- cap-java/cds-ai
- SAP AI Core
- @geertjanklaps/cds-toon-ai-protocol-adapter
- @jerome-benoit/sap-ai-provider
- @saptarishi/cds-plugin-llm
- @shahid.la/cds-db-nlquery-mcp
- abap_btocs_ollama
- abap-agent-runtime
- abap-sdk-nwas
- abap-sdk-nwas-x
- cap-llm-plugin
- llm_client
- Microsoft AI SDK for SAP
- ui5-cap-ai-features
- zllm
- Custom-built RAG on SAP BTPa use case, Answer a question from records in a CAP serviceRA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center
To leverage these underlying RAG principles, users can choose to either make use of SAP's standardized, use case-specific RAG services, or implement custom-built approaches on SAP BTP.
RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-centerCustom CAP based application can benefit from the CAP LLM Plugin for efficient and faster development.
The source draws it as cap-llm-plugin.
Ways the source names
- On the Cloud Foundry runtimeRA0005 readme.md in SAP/architecture-center
This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications.
RA0005 readme.md in SAP/architecture-center[SAP BTP, Cloud Foundry Runtime](https://discovery-center.cloud.sap/serviceCatalog/cloud-foundry-runtime?region=all) lets you develop polyglot cloud-native applications and run them on the SAP BTP Cloud Foundry environment.
- On the Kyma runtimeRA0005 readme.md in SAP/architecture-center
This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications.
RA0005 readme.md in SAP/architecture-center[SAP BTP, Kyma runtime](https://discovery-center.cloud.sap/serviceCatalog/kyma-runtime/?region=all) is a fully managed Kubernetes runtime based on the open-source project "Kyma".
Properties
About this work
For llm-integration
Applies in
For retrieval-augmented-generation
Applies in
Group by75 of 75 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
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 #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
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
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
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
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.
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
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
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
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
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.
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.
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.
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.
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 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
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
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
Establish a central entry point with SAP Build Work ZoneEstablish a central entry point with SAP Build Work ZoneSAP's reference architecture for a business site in SAP Build Work Zone, standard edition or SAP Build Work Zone, advanced edition as one entry point to business applications, processes, information and communication, on the web or in the Joule Work mobile app. Three of its eight flow steps are how content gets in, the ground launchpad and site content covers: custom apps through the channel to the subaccount's SAP HTML5 Application Repository service for SAP BTP, other content through content providers that expose it over APIs from cloud or on-premise systems and content packages uploaded as files, and SAP Cloud Transport Management or manual export and import to move it between environments. Users and role assignments come from Cloud Identity Services, and the components inside the subscription, among them Notifications, SAP Mobile Services and UI Theme Designer, cannot be decoupled from the product, so a custom mobile app needs its own SAP Mobile Services subscription.published 2026-05-22
AI-native North Star architecture — Platform LayerAI-native North Star architecture — Platform LayerThe platform layer of SAP's North Star architecture, the chapter that says where agents run and what a developer builds them with. It names an AI Golden Path built on the SAP Cloud Application Programming Model, the ABAP Cloud development model with RAP and the SAP Fiori design system, and a managed agent runtime on SAP BTP that is designed to provide software development kits for building agents in any framework, an agent sandbox, container-hosted execution, a skills registry and continuous evaluations, which is the ground agent tooling covers. Agents are extended without changing their code through four patterns, the first of them tool extensibility through the Model Context Protocol, the concern MCP servers is named for; the process-layer chapter adds that a pro-code path with a standardised agent SDK and a prompt-driven path through the Joule Studio solution produce the same code artifact on the same runtime. It describes a design SAP intends rather than products that exist, and the SDK and the registry it names have no entry here yet.published 2026-05-13
AI-native North Star architecture — Platform Layer
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects A reference.
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
Explore your Hyperscaler data with SAP Business Data CloudExplore your Hyperscaler data with SAP Business Data CloudSAP's map of the ways data held on hyperscaler and partner platforms is joined with SAP data in SAP Business Data Cloud, with a sub-page each for AWS, Azure, Google Cloud, Databricks and Snowflake. It sets four modes side by side: BDC Connect shares data products in both directions over the Delta Sharing protocol from the object store layer, while in the SAP Datasphere layer federation reads remote tables in place, Replication Flows copy SAP data out to stores such as Amazon S3 or Google BigQuery, and Data Flows import files and transform them into Datasphere tables, the last three being the ground loading a warehouse covers. The Snowflake and BigQuery connectors are dated to 2026 releases, and a closing page lists what slows federation, from source and tenant in different regions to queries that do not filter and aggregate at the source.published 2026-05-08
Integrating and Extending JouleIntegrating and Extending JouleSAP's reference architecture for SAP Joule across SAP cloud applications: a request is checked against a Scenario Catalog of the applications' skills and a Knowledge Catalog answered by retrieval-augmented generation, combined with the user's roles and history, sent to an LLM available through the generative AI hub, and, where a Joule function is needed, turned into a call to the backend. Its identity page is the authentication path: each user sits in the Identity Directory of Cloud Identity Services with a Global User ID, Identity Provisioning synchronises role assignments into SAP Build Work Zone, whose navigation service decides which functions a user may call, and the Destination service exchanges the user's token to call a function in the user's name. Its extension page covers Joule Studio in SAP Build, where Joule skills automate rule-based tasks over APIs and AI agents plan and reason with models and document grounding from SAP AI Core, the ground agent tooling covers; a later Joule Studio page describes a managed Joule Studio Runtime on the SAP Business AI Platform, which has no entry here.published 2026-03-16
Designing Event-Driven ApplicationsDesigning Event-Driven ApplicationsSAP's guidance for building applications on event-driven architecture with BTP services. It sets out a two-part strategy: SAP Cloud Application Event Hub for events between SAP cloud applications and BTP, and the SAP Integration Suite family for dedicated event brokers in hybrid landscapes. Its sub-pages then cover EDA patterns, design considerations and AWS and Azure IoT integration. The framing is integration between systems; the in-process outbox and queueing inside one CAP service are not its subject.published 2025-10-10
Transitioning Architectures from SAP NetWeaverTransitioning Architectures from SAP NetWeaverA community contribution from Glencore, an SAP customer, on what replaces NetWeaver-based products as their standard maintenance ends in 2027: the scenarios where NetWeaver-era solutions fall short — integration with cloud-based landscapes, extensibility — and the successor options per use case, pointing at SAP's product availability matrix and note 1648480 for the official successors. Customer-authored, so the framing is a migration decision rather than a product description.published 2025-08-02
DevOps with SAP BTPDevOps with SAP BTPHow SAP frames a delivery pipeline for applications on BTP Cloud Foundry: continuous integration through the SAP Continuous Integration and Delivery service and its pipeline templates for CAP and Fiori, transport and change management across environments, and a section on reasonable alternatives for teams with existing CI infrastructure. Culture first, tools second, and explicit that the setup differs on other BTP environments.published 2025-06-06
Integrate and Extend with SAP Build Process AutomationIntegrate and Extend with SAP Build Process AutomationSAP's reference architecture for SAP Build Process Automation integrating and extending SAP and non-SAP solutions in cloud and hybrid landscapes, the ground process automation covers. Processes start from events, APIs, schedules or forms, the forms built in SAP Build Process Automation, as UI5 applications or in SAP Build Apps; they reach other systems through the SAP Connectivity service with actions over APIs from sources that include CAP and RAP OData destinations and SAP Business Accelerator Hub specifications, and users reach them through SAP Build Work Zone and SAP Mobile Start, with SAP Task Center as the place tasks are managed. Decisions, Process Visibility, Processes and Automations come inside the one subscription and cannot be decoupled from it; CAP appears only as a source of API actions, and the examples are business scenarios such as mass job requisitions in SAP SuccessFactors.published 2025-05-14
Secure Service Consumption Across HyperscalersSecure Service Consumption Across HyperscalersSAP's design for a workload on SAP BTP that calls Amazon Web Services or Google Cloud services with short-lived credentials instead of stored keys, which is the outbound side of authentication: the BTP application proving who it is to another cloud. On AWS it draws two paths, an ID token from Identity Authentication in Cloud Identity Services exchanged through AWS STS for an IAM role, or an X.509 certificate kept in SAP Destination service and presented to IAM Roles Anywhere; on Google Cloud only the token path, through Workload Identity Federation and an impersonated service account. It is drawn for those two hyperscalers only, and Microsoft Azure has no page in it.published 2025-05-14
SAP IAM integration with SAP Cloud Identity ServicesSAP IAM integration with SAP Cloud Identity ServicesIdentity and access management for SAP SaaS in a landscape where SAP is one vendor among several: SAP Cloud Identity Services as the designated interface, single sign-on over SAML 2 and OIDC, identity lifecycle through SCIM 2 replication of users and groups, and authorization designed per domain — an S/4HANA role and a BTP role collection are different objects that both have to reach the user. Drawn from customer projects, and the source of what authentication here says about Cloud Identity Services.published 2025-05-13
Edge Integration Cell on HyperscalersEdge Integration Cell on HyperscalersSAP's architecture for Edge Integration Cell, the runtime of SAP Integration Suite that executes integration flows in a Kubernetes cluster the customer runs, while design, monitoring and governance stay on SAP BTP and the runtime reaches BTP over outbound-only channels. The main page gives the reasons SAP names for it: data residency, security policies that forbid inbound access, and latency to a distant BTP region. Three sub-pages draw the same setup on AWS, Azure and Google Cloud, each with a private network across three availability zones, a managed Kubernetes cluster, managed PostgreSQL and Redis, sizing left to an SAP Note, and each says it outlines a small production deployment to be treated as a starting point.published 2025-04-18
Medallion Reference Architecture for Big Data Processing in SAP HANA CloudMedallion Reference Architecture for Big Data Processing in SAP HANA CloudSAP's medallion layout for SAP HANA Cloud: structured, semi-structured and unstructured data lands raw in HANA Cloud, data lake files as the bronze layer, is cleansed into a common structure in silver, held in data lake files or the HANA database, and is curated and read-optimised in gold, from where it can also be exposed as a Delta Share. The staged path from raw to consumable is the ground loading a warehouse covers, with Spark jobs and SAP Datasphere data flows named as ways to move data between layers and SAP Analytics Cloud among the consumers of gold. It leaves the ingestion method open, to be chosen by source, freshness and performance, and names no pipeline or schedule beyond that.published 2025-04-03
SAP HANA Cloud as an Esri GeodatabaseSAP HANA Cloud as an Esri GeodatabaseSAP's design for running an Esri ArcGIS Enterprise geodatabase inside SAP HANA Cloud, so that geometries and SAP business data sit in one database and are joined in a HANA calculation view, which is the spatial part of graph, spatial and document data. It traces three personas: an analyst in ArcGIS Pro building query layers over that view, a developer whose CAP application models spatial types such as ST_Point in CDS, and an analyst using a Fiori app on top of such an application. The deployment advice stops at placement: ArcGIS Server and HANA Cloud go in the same region and availability zone, because Esri's certified architectures allow under 5 milliseconds of network latency between them.published 2025-03-25
Architecting Multi-Region HA/DR resiliency patternsArchitecting Multi-Region HA/DR resiliency patternsPatterns for running BTP applications across regions when the default multi-availability-zone resilience is not enough: DNS-based load balancing across regional endpoints with Azure Traffic Manager, Route 53 or Cloud DNS, replication of data and configuration between regions, and the fundamentals of single-region versus multi-region resiliency in its sub-pages. BTP services are multi-AZ by default; a multi-region setup is something the customer architects, and this is SAP's description of how.published 2025-02-19
Establish a central inbox with SAP Task CenterEstablish a central inbox with SAP Task CenterSAP's reference architecture for SAP Task Center as one inbox for the tasks of several SAP applications, opened in the Task Center web app or as To-Dos in SAP Start and SAP Mobile Start, which is the inbox half of task and approval UIs. It rests on Cloud Identity Services: every task provider must work with Identity Authentication, its users must carry the Global User ID and so must the recipients of each task, and sign-on between the provider and Identity Authentication is what lets a user navigate from Task Center into the provider. Task Center reaches providers through destinations in a customer subaccount, with Cloud Connector for on-premise SAP S/4HANA.published 2025-02-11
Multitenant SaaS Application using CAPMultitenant SaaS Application using CAPSAP's reference architecture for a multitenant SaaS application on BTP built with CAP: one deployment serving many tenants with logically separated data, the subscription and onboarding flow, and the BTP services the design leans on. Written for partners and line-of-business teams building on BTP, and it is SAP's own side of the shape multitenancy takes on BTP.published 2025-01-31
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
API Managed IntegrationAPI Managed IntegrationSAP's reference architecture for API-managed integration, which puts the API Management capability of SAP Integration Suite in front of business applications as API proxies that intercept each call to apply security policies, transformations and governance and to collect usage metrics. SAP defines it as a pattern that complements the other integration patterns, and draws three routes behind the proxy: a managed API forwarded to its provider for simple transformations and protocol adaptations, the Graph capability exposing data from several sources as one connected API, and Cloud Integration for mediation beyond API Management's scope, with the edge integration cell runtime for managing APIs in a customer-managed Kubernetes environment. SAP states that it delivers no predefined scenarios for this pattern, so the proxies and policies are the customer's or partner's to build.published 2024-08-01
Application to Application IntegrationApplication to Application IntegrationSAP's reference architecture for application-to-application integration, where messages carrying transactional data such as sales orders pass between business applications in near real time and each one triggers the next process step. When the sender's and receiver's APIs do not match, Cloud Integration in SAP Integration Suite sits between them to determine receivers, filter, map structures and convert protocols, which is the ground of integration flows; SAP Connectivity service, Cloud Connector and SAP Destination service reach on-premise receivers, and the edge integration cell runtime keeps processing inside a customer-managed landscape where compliance requires it. Direct exchange without middleware is allowed when the two APIs already align, asynchronous communication is the default the page states, and it is drawn at the level of the pattern, following SAP's Integration Solution Advisory Methodology, without designing any one flow.published 2024-08-01
Business to Business IntegrationBusiness to Business IntegrationSAP's reference architecture for business-to-business integration, the exchange of business documents with customers, suppliers and other trading partners over agreed standards such as EDIFACT, ANSI X.12 and IDoc and protocols such as AS2. Its design-time steps are Cloud Integration in SAP Integration Suite, the predefined content of SAP Business Accelerator Hub, and Integration Advisor, which defines message implementation and mapping guidelines and generates runtime artifacts from them; Trading Partner Management then turns partner profiles into agreements pushed to the Partner Directory, and generic integration flows on Cloud Integration read those agreements at runtime to exchange messages with each partner. The alternatives it names are API-based exchange where an industry has standardised its APIs, and SAP Business Network with the managed gateway for spend management in place of connecting partners one by one.published 2024-08-01
Connect Business Processes with SAP Master Data IntegrationConnect Business Processes with SAP Master Data IntegrationSAP's reference architecture for keeping master data such as materials, business partners and cost centres consistent across applications with SAP Master Data Integration, a central hub that stores every change in an event log and distributes it to the solutions that consume it. Cloud Integration in SAP Integration Suite carries what the hub does not reach, SAP solutions it does not yet support and third-party or on-premise systems, through an SAP Master Data Integration adapter, which is where the design meets integration flows; newer SAP S/4HANA releases connect to the hub without it. Consolidation, data quality and central governance are outside the architecture and left to SAP Master Data Governance, and SAP Master Data Integration itself has no entry in the atlas yet.published 2024-08-01
Details
Graph
LLM integrationcapability, core and community
Retrieval-augmented generationcapability, core and community
SAP Architecture Centerpublishing source
Source
Type
reference-architecture
Published on
Host
architecture.learning.sap.com
Signals as of
Discovered via
First seen
History
- explains → applies_to on capability:llm-integration (cap, btp); capability:retrieval-augmented-generation (cap, btp)Door scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).
- parts → 17 parts, 3 edges, 1 areaFilled from SAP's own readmes at the maintainer's request; the AI-native door reads these designs. Every part names what the graph holds; what it lacks is listed as candidates in the curation note.
- roles, paths → the plugins and SDKs within the application logic typed by LLM integration with the three the source names, the hub fixed, custom-built RAG typed by the CAP use case with the plugin the source names; two ways, one per runtime the readme accommodatesThe readme names the place for plugins and SDKs by example and leaves it open, and the RAG page names SAP's standardized services or a custom-built approach as the choice (docs/concepts/design-roles-and-interfaces.md §3). The three scenario pages are overlapping flows over the same parts, so they are not ways; the two runtimes are.
- capability → capability:retrieval-augmented-generationThe capability moved to a neutral id when it opened to HANA, BTP and ABAP; the concern and this entry's edge to it are unchanged.
- Entered the atlasDiscovered via SAP Architecture Center.
For your agent
- Ref
content:ac-generative-ai-on-sap-btp- JSON
- /content/ac-generative-ai-on-sap-btp.json
- MCP
- Connecting an agent