ServiceServiceA BTP service you subscribe to and bind, rather than install. It has plans and regions, not versions, and may deliver a product that lives outside the atlas.See every one →What this type is →by SAPby SAPPublished by SAP itself. A visible facet, never an input to a reading — a dormant official plugin reads exactly like a dormant independent one.See every one →
SAP AI Core
SAP'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.
A model call from an SAP application needs a model to call, credentials that are not a developer's, a way to change the model without changing the code, and somewhere to put what runs around the call. SAP AI Core is the service that holds all of that: it is provisioned in the BTP cockpit, the service key carries the URLs and credentials, and the Generative AI Hub exposes the models. Its orchestration service puts one harmonised API in front of them and adds four modules, templating, content filtering, data masking and grounding, so a filter or a masked field is configuration rather than code; the Prompt Registry keeps templates out of the codebase, and Document Grounding connects a document store and does ingestion, chunking, embedding and retrieval itself. The SDKs on the CAP door, @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, @sap-ai-sdk/foundation-models@sap-ai-sdk/foundation-modelsThe package of SAP's AI SDK that calls foundation models through SAP AI Core and the Generative AI Hub, and the one an application actually reaches for.sap official, cap, @sap-ai-sdk/ai-api@sap-ai-sdk/ai-apiThe AI Core API surface of SAP's AI SDK, covering deployments, configurations and the rest of the control plane, as opposed to calling a model.sap official, cap and @sap-ai-sdk/prompt-registry@sap-ai-sdk/prompt-registryA package for keeping prompts in SAP's prompt registry rather than in the codebase, so changing a prompt is not a deployment.sap official, cap, are its clients, and @cap-js/ai@cap-js/aiOut-of-the-box value-help recommendations powered by SAP RPT-1, SAP AI Core as a standard CAP service, and an experimental local embedding model behind SQLite's vector functions.sap official, cap exposes it as a CAP service. SAP AI LaunchpadSAP AI LaunchpadThe SaaS front end over SAP AI Core on BTP: a Model Library, Grounding Management for document pipelines, Workspaces that connect AI runtimes, and ML Operations for the lifecycle of a scenario.sap official, btp is the UI over the same instance.
Where it sits
Lives in
Provides
LLM integrationABAPCAPBTPLLM 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.Prompt managementBTPCAPPrompt managementKeeping the prompts an application sends to a model as templates with placeholders, stored and versioned apart from the code that calls them, so a change of wording is not a deployment. What people conflate under it: the template filled at runtime, the registry it lives in, and the orchestration step that fills it.Data maskingBTPCAPData maskingReplacing the personal or confidential values in a prompt with placeholders before it leaves for a model, and putting them back in the answer. Anonymisation, where the values are gone for good, and pseudonymisation, where they return, are the two forms; which fields count as sensitive is the application's question, not the module's.Content filteringBTPCAPContent filteringChecking what goes into a model and what comes out of it against content rules, and stopping or flagging a request that fails them. Distinct from [data masking](capability:data-masking), which hides values: a filter refuses content.Retrieval-augmented generationABAPCAPBTPRetrieval-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.
Designs
Agentic AI & AI AgentsAgentic AI & AI Agentsmanaged runtime where Joule Studio agents executeAgentic AI & AI AgentsAgentic AI & AI AgentsGenerative AI Hub: harmonized orchestration service layer with foundation model accessAgentic Engineering for SAP BTP ExtensionsAgentic Engineering for SAP BTP ExtensionsGoverned model accessGenerative AI on SAP BTPGenerative AI on SAP BTPGenerative AI Hub: central access point to foundation models, with orchestration and groundingIntegrating and Extending JouleIntegrating and Extending JouleLLMs through the generative AI hub, and document grounding for AI agents
Who is behind it
SAPSAPMaintains this
In the atlas: maintains 137, wrote 14@SAPmaintainer
In the atlas: maintains 137, wrote 14@SAPmaintainer
What it declares
Every artifact
- Type
- Service
- Origin
- By SAP
As a service
- Plans
- 3
- Regions
- 23
- Support component
- CA-ML-AIC
Connections
Group by58 of 58 connections
NodeRelationBasis
Functional
Content filteringContent filteringChecking model input and output against content rulesSAP only
provides
stated
provides Content filtering
The content filtering module of the orchestration service, on the input and on the output, for the hateful, violent, sexual and vulgar categories SAP names.
“AI Core provides content filtering for hateful, violent, sexual and vulgar content through input and output filtering”“This feature allows you to restrict the type of content passed to and received from a generative AI model.”
Checking model input and output against content rules
Data maskingData maskingReplacing personal values in a prompt with placeholdersSAP only
provides
stated
provides Data masking
The data masking module of the orchestration service: anonymisation or pseudonymisation before the prompt reaches the model, with unmasking of the response under pseudonymisation.
“This feature enables data masking through anonymization or pseudonymization before passing it into a generative AI model. If pseudonymization is used, masked data in the model's response will be unmasked.”“AI Core supports data masking as a feature.”
Replacing personal values in a prompt with placeholders
LLM integrationLLM integrationCalling a language model with tenant and credential handling solvedSAP and community, narrow by design
provides
stated
provides LLM integration
Gives an application its models: the Generative AI Hub exposes them, and the orchestration service's harmonised API lets the client switch model without changing code.
“Access generative AI capabilities and prompt lifecycle management via the generative AI hub.”“the harmonized API allows you to use different foundation models without changing the client code”
Calling a language model with tenant and credential handling solved
Prompt managementPrompt managementPrompt templates stored and versioned apart from the codeSAP only
provides
stated
provides Prompt management
Templating as an orchestration module, filling placeholders at inference, and the Prompt Registry as the place a template is stored, versioned and referenced from.
“This feature lets you compose prompts with placeholders that are filled during inference.”“When using AI core this is achieved using the prompt registry.”
Prompt templates stored and versioned apart from the code
Retrieval-augmented generationRetrieval-augmented generationGrounding a model's answer in data retrieved at question timeSAP and community, unassessed
provides
stated
provides Retrieval-augmented generation
Document Grounding: a managed connector to a document store, with ingestion, chunking, embedding and retrieval done by the service and a Vector API for data that is chunked and embedded already.
“SAP Document Grounding is a managed service offering under the Generative AI Hub on SAP Business Technology Platform (BTP).”“Once a data source is connected through one of the managed connectors, the service automatically handles document ingestion, chunking, embedding creation, and retrieval.”
Grounding a model's answer in data retrieved at question time
Technical
analytics-cloud-rpt15-prediction-demoanalytics-cloud-rpt15-prediction-demoFastAPI backend for SAP-RPT-1.5 predictions from SAP Analytics Cloudsap official, btp
connected from
derived
connected from analytics-cloud-rpt15-prediction-demo
sends the rows to predict with the already-scored rows as context, and takes the predicted value and confidence interval back
“RPT-1.5 is deployed in **SAP AI Core**, the data lives in **SAP Datasphere**, and this **FastAPI** service — deployed to **Cloud Foundry** — wraps the prediction call.”“The job reads every row from the `V_PAYMENT_DELAY_PREDICTION` view. Rows with a `NULL` `Days_Late` are marked `[PREDICT]`; all other rows are sent as **context** so RPT-1.5 can make accurate in-context predictions.”
FastAPI backend for SAP-RPT-1.5 predictions from SAP Analytics Cloud
btp-agentbtp-agentLangGraph agent and UI5 chat screen over four BTP MCP serversindependent, cap
connected from
derived
connected from btp-agent
The message history and bound tools the model node sends on every turn, and the answer it streams back, called through the service binding the CAP application already owns.
“The LLM itself is AzureOpenAiChatClient from @sap-ai-sdk/langchain, which targets AI Core’s Generative AI Hub through the service binding the CAP app already owns.”“The model node calls the chat model with the current message history and the bound tools; the tool node executes any tool calls and appends their results to the state; an edge sends control back to the model until it returns a plain message.”
LangGraph agent and UI5 chat screen over four BTP MCP servers
cap-java/cds-aicap-java/cds-aiBridge from CAP Java to SAP AI Core, with Fiori field recommendationssap official, cap
connected from
derived
connected from cap-java/cds-ai
An SAP AI Core service binding exists.
Calling SAP AI Core from a CAP Java application: resource groups, deployments, configurations and predictions. Without a binding the plugins answer from mock implementations.
“Bridges CAP Java to SAP AI Core - resource group management, deployment lifecycle, configuration CRUD, and prediction API”“Without an AI Core binding the plugins fall back to mock implementations for local development.”
Bridge from CAP Java to SAP AI Core, with Fiori field recommendations
Sample CAP Application with SAP Cloud SDK for AISample CAP Application with SAP Cloud SDK for AICAP samples calling SAP AI Core through the SAP Cloud SDK for AIsap official, cap
connected from
derived
connected from Sample CAP Application with SAP Cloud SDK for AI
The prompt each action sends to a language model and the response it returns to the caller.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“It provides examples of how to interact with language models to obtain responses based on user prompts within a CAP service context.”
CAP samples calling SAP AI Core through the SAP Cloud SDK for AI
SAP BTP AI Best Practice Demo - Content Filtering - CAPSAP BTP AI Best Practice Demo - Content Filtering - CAPCAP samples comparing SAP AI Core responses with content filteringsap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Content Filtering - CAP
The prompt each action sends to the model and the response it logs, filtered on the way in or on the way out.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“The application will serve the `/chatWithSupport` (filter input) and `/generateParaphrase` (filter output) APIs, which uses content filtering, then sends a prompt to the AI model and logs the response.”
CAP samples comparing SAP AI Core responses with content filtering
SAP BTP AI Best Practice Demo - Data Masking - CAPSAP BTP AI Best Practice Demo - Data Masking - CAPCAP samples generating email through SAP AI Core with anonymizationsap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Data Masking - CAP
The prompt the action sends to a language model and the email it gets back.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“It provides examples of how to interact with language models to obtain responses based on user prompts within a CAP service context.”
CAP samples generating email through SAP AI Core with anonymization
SAP BTP AI Best Practice Demo - Prompt Registry - CAPSAP BTP AI Best Practice Demo - Prompt Registry - CAPCAP samples using SAP AI Core's Prompt Registry for templatessap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Prompt Registry - CAP
The template the sample writes to and deletes from the Prompt Registry, and the prompt it sends to the model.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“The application will serve the `/askCapitalOfCountry` API, which uses prompt templating, then sends a prompt to the AI model and logs the response.”
CAP samples using SAP AI Core's Prompt Registry for templates
SAP BTP AI Best Practice Demo - Prompt Templating - CAPSAP BTP AI Best Practice Demo - Prompt Templating - CAPCAP samples filling a prompt template sent to SAP AI Coresap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Prompt Templating - CAP
The filled template the action sends to the model, and the response it logs.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“The application will serve the `/askCapitalOfCountry` API, which uses prompt templating, then sends a prompt to the AI model and logs the response.”
CAP samples filling a prompt template sent to SAP AI Core
SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAPSAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAPCAP samples embedding CSV rows into the SAP HANA Cloud vector storesap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAP
Each uploaded row, sent to an embeddings model, and the vector that comes back.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“This project demonstrates best practices for accessing Embeddings models using the SAP GenAI Hub”
CAP samples embedding CSV rows into the SAP HANA Cloud vector store
SAP BTP AI Best Practice Demo - Vector Query (RAG) - CAPSAP BTP AI Best Practice Demo - Vector Query (RAG) - CAPCAP samples running RAG similarity queries over SAP HANA Cloud vectorssap official, cap
connected from
derived
connected from SAP BTP AI Best Practice Demo - Vector Query (RAG) - CAP
The rows sent for embedding on upload, and the retrieved documents passed to the model as context at inference.
“The application requires proper configuration to connect to the SAP AI Core service. This is handled through CDS bindings in both local and remote deployments.”“use them as context for the LLM during inference”
CAP samples running RAG similarity queries over SAP HANA Cloud vectors
SAP Document AISAP Document AIExtracts header fields and line items from business documentssap official, btp
connected from
derived
connected from SAP Document AI
calls SAP AI Core and the Generative AI Hub for the extraction steps that use an LLM
“For extraction steps that benefit from generative AI, the pipeline calls into **SAP AI Core** and the **Generative AI Hub**, using LLMs together with the **Prompt Registry** and pretrained models.”
Extracts header fields and line items from business documents
SAP-samples/smartrecruiters-ai-recruiting-custom-agentSAP-samples/smartrecruiters-ai-recruiting-custom-agentRecruiting agent on SmartRecruiters data flagging stalled candidatessap official, btp
connected from
derived
connected from SAP-samples/smartrecruiters-ai-recruiting-custom-agent
the LLM synthesis step, when SAP AI Core is reachable
the question and the analysis results the agent sends to the model, and the wording it gets back.
“**Responds** — Uses the LLM to generate a natural language summary”“The LLM is the "voice" of the agent — it interprets what you're asking and explains results in plain language.”
Recruiting agent on SmartRecruiters data flagging stalled candidates
@mi8y/cap-agents-aicore-vectorstore@mi8y/cap-agents-aicore-vectorstoreLangChain vector store on SAP AI Core Document Groundingindependent, cap
needed by
derived
needed by @mi8y/cap-agents-aicore-vectorstore
The Document Grounding collection it reads and writes: the package needs an existing collection and credentials for the service, through a binding or a configured destination.
“An existing SAP AI Core Document Grounding collection”“SAP AI Core credentials through a service binding or a configured SAP Cloud SDK destination”
LangChain vector store on SAP AI Core Document Grounding
ai-core-samplesai-core-samplesTutorial notebooks and templates for a first SAP AI Core projectsap official, btp
needed by
derived
needed by ai-core-samples
the instance the workflow templates are registered and executed on; the README accepts the free tier for the notebooks
“Please provision a SAP AI Core instance before you start using the templates. You should also be able to use the SAP AI Core free-tier too to work with the sample notebooks”
Tutorial notebooks and templates for a first SAP AI Core project
ai-enabled-integrations-codejamai-enabled-integrations-codejamCodeJam on LLM-backed integration flows and MCP via API Managementsap official, btp
needed by
derived
needed by ai-enabled-integrations-codejam
the LLM the integration flow calls and the prompt template of exercise 01; the tenant has to have it configured before the exercises start
“To complete the exercises in this repository, you will need access to an SAP Integration Suite tenant with SAP AI Core configured.”
CodeJam on LLM-backed integration flows and MCP via API Management
aicore-genai-samplesaicore-genai-samplesSample apps for SAP AI Core's Generative AI Hub capabilitiessap official, btp
needed by
derived
needed by aicore-genai-samples
the instance each sample application runs against; the README asks for it to be provisioned before any of them is started
“Please provision a SAP AI Core instance before you start using the application”
Sample apps for SAP AI Core's Generative AI Hub capabilities
aicore-multioutput-regression-restaurant-inspectionsaicore-multioutput-regression-restaurant-inspectionsML service on SAP AI Core scoring restaurant-inspection violationssap official, btp
needed by
derived
needed by aicore-multioutput-regression-restaurant-inspections
where the training runs and the inference service is deployed, from the workflow templates and Docker images in the repository
“A machine learning service that leverages the capabilities of SAP Business Technology Platform (SAP AI Core and SAP AI Launchpad)”“Digitizing Criticality Assessments using SAP AI Core and SAP AI Launchpad”
ML service on SAP AI Core scoring restaurant-inspection violations
aicore-skillsaicore-skillsFour agent skills for SAP AI Core in SAP's AI Skills Librarysap official, btp
needed by
derived
needed by aicore-skills
Every script calls the AI Core APIs with credentials taken from the environment, so none of the four skills does anything without a provisioned instance.
“SAP AI Core instance with credentials configured”“Requires Python 3.11+, uv, sap-ai-sdk-core, and BTP CLI (btp) for registering”
Four agent skills for SAP AI Core in SAP's AI Skills Library
analytics-cloud-rpt15-prediction-demoanalytics-cloud-rpt15-prediction-demoFastAPI backend for SAP-RPT-1.5 predictions from SAP Analytics Cloudsap official, btp
needed by
derived
needed by analytics-cloud-rpt15-prediction-demo
the RPT-1.5 Large deployment the service calls for every prediction
“- **SAP AI Core** with an RPT-1.5 Large deployment”
FastAPI backend for SAP-RPT-1.5 predictions from SAP Analytics Cloud
btp-agentbtp-agentLangGraph agent and UI5 chat screen over four BTP MCP serversindependent, cap
needed by
derived
needed by btp-agent
the Generative AI Hub the chat model is called against, bound as the `aicore` resource on the extended plan
“The LLM itself is AzureOpenAiChatClient from @sap-ai-sdk/langchain, which targets AI Core’s Generative AI Hub through the service binding the CAP app already owns.”“The MTA ships nine modules (approuter, CAP srv, UI5 chat, HANA deployer, and four MCP-server apps) and binds xsuaa, HANA HDI, destination, connectivity, html5-repo (host+runtime) and AI Core (extended plan).”
LangGraph agent and UI5 chat screen over four BTP MCP servers
btp-gen-ai-hub-sdk-samplesbtp-gen-ai-hub-sdk-samplesSetup guide and Python notebooks for SAP AI Core's Generative AI Hubsap official, btp
needed by
derived
needed by btp-gen-ai-hub-sdk-samples
the service the Generative AI Hub belongs to, on the service plan the prerequisites name
“- AI Core with Service Plan "Extended"”
Setup guide and Python notebooks for SAP AI Core's Generative AI Hub
Reports Assistant with SAP Document ManagementReports Assistant with SAP Document ManagementCAP agent writing reports into a shared SDM document workspaceindependent, cap
needed by
derived
needed by Reports Assistant with SAP Document Management
The model the agent calls, reached through the destination named in `cds.requires.llm.destinationName`.
“Requires a SAP BTP Cloud Foundry environment with AI Core, Document Management,
Destination, XSUAA, and HTML5 Application Repository runtime services.”“set `cds.requires.llm.destinationName` and model.”
CAP agent writing reports into a shared SDM document workspace
sap-btp-ai-best-practicessap-btp-ai-best-practicesSample implementations for AI-powered applications on SAP BTPsap official, btp
needed by
derived
needed by sap-btp-ai-best-practices
the AI service every example calls; the README lists access to it beside a BTP account as the repository's two requirements.
“Access to SAP AI Core service”“It serves as a practical guide for developers looking to implement enterprise-grade AI solutions using SAP's AI services and integration with generative AI models.”
Sample implementations for AI-powered applications on SAP BTP
sap-rpt-samplessap-rpt-samplesBruno collections and code for SAP-RPT predictions on tabular datasap official, btp
needed by
derived
needed by sap-rpt-samples
the service the prediction request is sent to: an instance on the extended plan with the model deployed, whose service key the collection is configured with.
“Please note that you need a service instance of SAP AI Core (service plan "extended") and a deployment of the model”“Navigate to your BTP service instance page and Click on the `SAP AI Core` instance to view the service key details.”
Bruno collections and code for SAP-RPT predictions on tabular data
SAP-samples/btp-ai-core-usage-monitorSAP-samples/btp-ai-core-usage-monitorPython agent alerting on SAP AI Core capacity unit consumptionsap official, btp
needed by
derived
needed by SAP-samples/btp-ai-core-usage-monitor
the service whose capacity unit consumption is what the agent counts
“3. **SAP AI Core** (Extended plan) active in the **subaccount whose usage you want to monitor** — this is the `SUBACCOUNT_ID` you configure”
Python agent alerting on SAP AI Core capacity unit consumption
SAP-samples/btp-sourcing-decision-boardSAP-samples/btp-sourcing-decision-boardProcurement decision support cross-validating two AI agent strategiessap official, btp
needed by
derived
needed by SAP-samples/btp-sourcing-decision-board
the deployment the agents call, configured by client id, secret, auth URL, API URL and deployment id
“- SAP BTP account with AI Core enabled”“- **AI/ML**: SAP AI Core + SAP Generative AI Hub”
Procurement decision support cross-validating two AI agent strategies
SAP-samples/codejam-code-based-agentsSAP-samples/codejam-code-based-agentsCodeJam on code-based AI agents in Python or TypeScript on SAP BTPsap official, btp
needed by
derived
needed by SAP-samples/codejam-code-based-agents
The service the agents are built on: Generative AI Hub runs on it, and exercise 00 of every stack is understanding that.
“Exercise 00 - Understanding Generative AI Hub in SAP AI Core”“In this CodeJam, you will learn how to build state-of-the-art AI agents using Generative AI Hub, Python and JavaScript.”
CodeJam on code-based AI agents in Python or TypeScript on SAP BTP
SAP-samples/generative-ai-codejamSAP-samples/generative-ai-codejamCodeJam deploying an LLM on Generative AI Hub and building RAGsap official, btp
needed by
derived
needed by SAP-samples/generative-ai-codejam
The service Generative AI Hub runs on and the LLM is deployed to; the first exercise connects it.
“In this CodeJam you will learn how to use Generative AI Hub on SAP AI Core to implement a retrieval augmented generation (RAG) use case to improve the responses of large language models (LLMs) and reduce hallucinations.”
CodeJam deploying an LLM on Generative AI Hub and building RAG
SAP-samples/joule-a2a-agent-toolkitSAP-samples/joule-a2a-agent-toolkitSkills for building an A2A agent for Joule and deploying it to CFsap official, btp
needed by
derived
needed by SAP-samples/joule-a2a-agent-toolkit
calling SAP GenAI Hub models through [SAP AI Core](artifact:btp-ai-core)
“**BTP subaccount** with Cloud Foundry runtime, AI Core service, and Destination service”
Skills for building an A2A agent for Joule and deploying it to CF
@cap-js/agents@cap-js/agentsCDS plugin for building agents inside a CAP servicesap official, cap
optionally used by
derived
optionally used by @cap-js/agents
The aicore kind is configured under cds.requires.llm, which capire states is the default for the production and hybrid profiles; development defaults to auto, which reads credentials from a local Claude Code or OpenCode installation, and mock returns dummy responses.
The model the agent calls on each turn of its loop, reached through an SAP AI Core service instance.
“The default for `production` and `hybrid`, connects to SAP AI Core”“The LLM used by an agent is configured via `cds.requires.llm`.”
CDS plugin for building agents inside a CAP service
@cap-js/ai@cap-js/aiValue-help recommendations and SAP AI Core as a CAP servicesap official, cap
optionally used by
derived
optionally used by @cap-js/ai
The recommendations run in a production deployment; without the binding, local development uses a mock implementation for UI smoke tests.
The service binding the recommendations need in a production deployment; without one, local development uses a mock implementation for UI smoke tests.
“A production deployment requires an [SAP AI Core](https://help.sap.com/docs/sap-ai-core) service binding. Without one, local development uses a mock implementation for UI smoke tests.”
Value-help recommendations and SAP AI Core as a CAP service
@saptarishi/cds-plugin-llm@saptarishi/cds-plugin-llmCAP service kind putting eleven model providers behind one APIindependent, cap
optionally used by
derived
optionally used by @saptarishi/cds-plugin-llm
The llm-genai-hub kind is configured; the other ten kinds reach their own provider with their own key.
The kind that routes calls to models in the Generative AI Hub, reached with an AI Core binding, a resource group and a deployment id.
“LLM-agnostic AI platform for SAP CAP. **11 providers** behind one unified interface — Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Ollama, Groq, Fireworks, DeepSeek, Mistral, any OpenAI-compatible endpoint, and SAP Generative AI Hub”“"impl": "@saptarishi/cds-plugin-llm/lib/providers/genai-hub.js"”
CAP service kind putting eleven model providers behind one API
cap-java/cds-aicap-java/cds-aiBridge from CAP Java to SAP AI Core, with Fiori field recommendationssap official, cap
optionally used by
derived
optionally used by cap-java/cds-ai
Production use; without a binding the plugins fall back to mock implementations for local development.
“Without an AI Core binding the plugins fall back to mock implementations for local development.”
Bridge from CAP Java to SAP AI Core, with Fiori field recommendations
cap-llm-plugincap-llm-pluginGenerative AI in CAP with fields anonymised through SAP HANAindependent, cap
optionally used by
derived
optionally used by cap-llm-plugin
An embedding, a chat completion or the single retrieval method is called; each of them goes through SAP AI Core.
The embedding and chat models the plugin calls, and the service the retrieval method reaches them through.
“Seamlessly generate vector embeddings via SAP AI Core.”“Simplified single RAG (retrieval-augmented generation) retrieval method powered by SAP AI Core and SAP HANA Cloud Vector Engine.”
Generative AI in CAP with fields anonymised through SAP HANA
com.sap.cds:cds-adapter-agentcom.sap.cds:cds-adapter-agentA2A adapter turning a CAP Java service into an LLM-backed agentsap official, cap
optionally used by
derived
optionally used by com.sap.cds:cds-adapter-agent
The aicore chat model kind is used, which is CAP Java's default LLM configuration for the production and hybrid profiles.
“If no configuration matches, CAP Java falls back to aicore when an SAP AI Core service binding is present, and to mocked otherwise.”“The default for production and hybrid, connects to SAP AI Core”
A2A adapter turning a CAP Java service into an LLM-backed agent
custom-llm-clientcustom-llm-clientLocal chat client for SAP questions with a CAP LangGraph backendindependent, cap
optionally used by
derived
optionally used by custom-llm-client
LLM_PROVIDER is set to sap-ai-core; the README lists Azure OpenAI, the OpenAI API and Ollama as the other providers
The model the chat calls, reached at a deployment's inference URL with a client id and secret, when SAP AI Core is the configured provider.
“Supports Azure OpenAI, OpenAI API, Ollama (local), and SAP AI Core (BTP). Not production-hardened.”
Local chat client for SAP questions with a CAP LangGraph backend
LLM-Benchmark-ABAP-Code-GenerationLLM-Benchmark-ABAP-Code-GenerationBenchmark of LLM ABAP code generation against a real SAP systemindependent, abap
optionally used by
derived
optionally used by LLM-Benchmark-ABAP-Code-Generation
the model being benchmarked is SAP's sap--abap-1
the orchestration endpoint, client credentials and resource group the run reads from the environment to reach SAP's own ABAP model; every other provider is called directly
“# SAP AI Core (for ABAP-1 via orchestration)”
Benchmark of LLM ABAP code generation against a real SAP system
SAP-samples/smartrecruiters-ai-recruiting-custom-agentSAP-samples/smartrecruiters-ai-recruiting-custom-agentRecruiting agent on SmartRecruiters data flagging stalled candidatessap official, btp
optionally used by
derived
optionally used by SAP-samples/smartrecruiters-ai-recruiting-custom-agent
the agent's conversational answers; without SAP AI Core it falls back to keyword-based intent detection and template responses
the model that reads the question and words the answer; the README offers a fallback mode and mock data for running without it.
“Works out of the box with mock data. Add your SAP AI Core and SmartRecruiters credentials for the full experience.”“If SAP AI Core is temporarily unavailable, the agent doesn't break.”
Recruiting agent on SmartRecruiters data flagging stalled candidates
Joule Studio, classic editionJoule Studio, classic editionLow-code SAP Build capability for custom Joule skills and agentssap official, btp
used by
derived
used by Joule Studio, classic edition
document grounding as an agent tool: the resource groups holding the documents live in SAP AI Core
“Document grounding: create resource groups in AI Core with your business documents, then add those resource groups as tools to your agent in Joule Studio.”
Low-code SAP Build capability for custom Joule skills and agents
Sample CAP Application with SAP Cloud SDK for AISample CAP Application with SAP Cloud SDK for AICAP samples calling SAP AI Core through the SAP Cloud SDK for AIsap official, cap
used by
derived
used by Sample CAP Application with SAP Cloud SDK for AI
The service instance the samples call for both actions, bound locally with `cds bind` or named in the fullstack sample's mta.yml.
“Access to SAP AI Core service”
CAP samples calling SAP AI Core through the SAP Cloud SDK for AI
SAP AI LaunchpadSAP AI LaunchpadSaaS front end over SAP AI Coresap official, btp
used by
derived
used by SAP AI Launchpad
the AI runtime it manages; a workspace is a connection to an AI runtime instance, and SAP's setup pairs the two
“You use the app to create and manage connections between SAP AI Launchpad and your AI runtimes (for example ,SAP AI Core).”
SaaS front end over SAP AI Core
SAP BTP AI Best Practice Demo - Content Filtering - CAPSAP BTP AI Best Practice Demo - Content Filtering - CAPCAP samples comparing SAP AI Core responses with content filteringsap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Content Filtering - CAP
The service instance the samples bind to at runtime for the filtered and unfiltered chat and paraphrase calls.
“Access to SAP AI Core service”
CAP samples comparing SAP AI Core responses with content filtering
SAP BTP AI Best Practice Demo - Data Masking - CAPSAP BTP AI Best Practice Demo - Data Masking - CAPCAP samples generating email through SAP AI Core with anonymizationsap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Data Masking - CAP
The service instance the samples bind to at runtime to generate the email, with or without the input masked first.
“Access to SAP AI Core service”
CAP samples generating email through SAP AI Core with anonymization
SAP BTP AI Best Practice Demo - Prompt Registry - CAPSAP BTP AI Best Practice Demo - Prompt Registry - CAPCAP samples using SAP AI Core's Prompt Registry for templatessap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Prompt Registry - CAP
The service instance the samples bind to at runtime, which also holds the Prompt Registry template that the CDS actions create, resolve and delete.
“Access to SAP AI Core service”
CAP samples using SAP AI Core's Prompt Registry for templates
SAP BTP AI Best Practice Demo - Prompt Templating - CAPSAP BTP AI Best Practice Demo - Prompt Templating - CAPCAP samples filling a prompt template sent to SAP AI Coresap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Prompt Templating - CAP
The service instance the samples bind to at runtime to resolve the prompt template and return a completion, bound locally with `cds bind`.
“Access to SAP AI Core service”
CAP samples filling a prompt template sent to SAP AI Core
SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAPSAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAPCAP samples embedding CSV rows into the SAP HANA Cloud vector storesap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAP
The service instance the samples bind to at runtime to create the embeddings for each uploaded row.
“Access to SAP AI Core service”
CAP samples embedding CSV rows into the SAP HANA Cloud vector store
SAP BTP AI Best Practice Demo - Vector Query (RAG) - CAPSAP BTP AI Best Practice Demo - Vector Query (RAG) - CAPCAP samples running RAG similarity queries over SAP HANA Cloud vectorssap official, cap
used by
derived
used by SAP BTP AI Best Practice Demo - Vector Query (RAG) - CAP
The service instance the samples bind to at runtime: the embeddings for an upload, and the model the retrieved documents are passed to.
“Access to SAP AI Core service”
CAP samples running RAG similarity queries over SAP HANA Cloud vectors
SAP-samples/teched2025-AI160SAP-samples/teched2025-AI160Hands-on building an AI agent with the SAP Cloud SDK for AIsap official, btp
used by
derived
used by SAP-samples/teched2025-AI160
the orchestration deployment both tracks call for the model; on a reader's own instance it has to be created and its credentials supplied first.
“**[SAP AI Core Orchestration Service](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration-8d022355037643cebf775cd3bf662cc5?locale=en-US)**: Handles LLM invocation, content filtering, and data masking”“You need to create a deployment for orchestration by referring the [documentation](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-orchestration?locale=en-US).”
Hands-on building an AI agent with the SAP Cloud SDK for AI
teched2025-AD162teched2025-AD162TechEd 2025 workshop on a Fiori app with ABAP Cloud and Joulesap official, abap
used by
derived
used by teched2025-AD162
what the ABAP system must be connected to for the AI features the exercises use.
“the access to a suitable ABAP system* that is connected to the [SAP AI Core](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-core)”
TechEd 2025 workshop on a Fiori app with ABAP Cloud and Joule
teched2025-AI161teched2025-AI161TechEd 2025 session on benchmarking and optimising promptssap official, btp
used by
derived
used by teched2025-AI161
the service whose generative AI hub capability carries the prompt editor, the registry and the benchmarking tools the exercises use.
“Get hands-on experience with the prompt editor, registry, and benchmarking tools available from the generative AI hub capability in SAP AI Core.”
TechEd 2025 session on benchmarking and optimising prompts
teched2025-AI163teched2025-AI163TechEd 2025 lab building a Joule Agent for Global Track and Tracesap official, btp
used by
derived
used by teched2025-AI163
the document grounding the create-shipment skill reads the rate card through; a resource group and a grounding pipeline have to be running.
“This exercise shows how to build a simple custom Joule Agent in Joule Studio that uses multiple Joule Skills along with Document Grounding via AI Core to manage shipments in the SAP Business Networks Global Track and Trace (GTT) system.”“A resource group and document grounding pipeline are set up and running.”
TechEd 2025 lab building a Joule Agent for Global Track and Trace
teched2025-DA266teched2025-DA266TechEd 2025 material on two SAP Databricks scenarios in BDCsap official, btp
used by
derived
used by teched2025-DA266
the orchestration services the payment-delay scenario calls for the human-readable explanation; a service instance and its key have to exist.
“Access to a configured SAP AI Core Service intance with corresponding service key”“Integrating SAP AI Core Service for LLM modelling”
TechEd 2025 material on two SAP Databricks scenarios in BDC
teched2025-XP267teched2025-XP267TechEd 2025 session on Automation Pilot fixes from Cloud ALM alertssap official, btp
used by
derived
used by teched2025-XP267
the deployment the extended flow calls to assess technical data and return recommendations; the prerequisite names the model.
“**SAP AI Core** credentials with a **GPT-4o** deployment”“Extending SAP Automation Pilot by an integration to SAP AI Core service for **assessment of technical data and recommendations by AI**”
TechEd 2025 session on Automation Pilot fixes from Cloud ALM alerts
Download
Learn more
Readings
- 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 2026-10-16DJ Adams, Johannes Vogt, YouTube — SAP Developers playlists
- 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 2026-10-15SAP Developers, YouTube — SAP Developers playlists
- 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 2026-10-09DJ Adams, Johannes Vogt, Daniel Schlachter, YouTube — SAP Developers playlists
26 more
- 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 2026-10-09Wouter Lemaire, YouTube — SAP Developers playlists
- 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 2026-10-08SAP Developers, YouTube — SAP Developers playlists
- 🟣 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 2026-10-01SAP Developers, YouTube — SAP Developers playlists
- 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 2026-09-30amishkush, SAP Community
- 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 2026-09-25SAP Developers, YouTube — SAP Developers playlists
- 🟣 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 2026-09-24SAP Developers, YouTube — SAP Developers playlists
- 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 2026-08-21DJ Adams, Johannes Vogt, Stefan Rudi, YouTube — SAP Developers playlists
- 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 2025-12-15arunmaarirajha_kv, SAP Community
- 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.SAP, SAP BTP AI Best Practices
- 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.SAP, SAP BTP AI Best Practices
- 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.SAP, SAP BTP AI Best Practices
- 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.SAP, SAP BTP AI Best Practices
- 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.Daniel Hutzel, Daniel Schlachter, SAP TechEd — session catalogue
- 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.SAP TechEd — session catalogue
- 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.SAP TechEd — session catalogue
- 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.SAP TechEd — session catalogue
- 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.SAP TechEd — session catalogue
- 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.Markus Fath, SAP TechEd — session catalogue
- 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.Markus Fath, Thomas Hammer, SAP TechEd — session catalogue
- SAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core deep dive: Models, agents, and business context at scaleSAP AI Core read as the management and orchestration layer of an AI architecture, beyond the model runtime: SAP's abstract lists extending Joule Agents, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. It names the connections and not the APIs behind them. A TechEd 2026 session (Tuesday 27 October, Berlin; also RA107V, virtual), presented by Franziska Dobrigkeit and Hadi Hares, written here from SAP's abstract; the recording is not yet published.SAP TechEd — session catalogue
- 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.SAP TechEd — session catalogue
- 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.David Knaack, SAP TechEd — session catalogue
- SAP-RPT and TabPFN: Get started with tabular foundation modelsSAP-RPT and TabPFN: Get started with tabular foundation modelsTabular foundation models, SAP-RPT and TabPFN, in a hands-on with SAP and Prior Labs: the model families first, then predictions run through SAP AI Core with a workflow built on tabular orchestration and connected to the participant's own data for real-time predictions. A predictive models session with the models as the subject; the abstract does not name the SDK or API the workflow is built with. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Eliott Kalfon, Janick Zaehringer-Frasch, Johannes Hoehne, Katharina Schell, Nilay Mehta and Sherene Tan, written here from SAP's abstract; no recording is announced.SAP TechEd — session catalogue
- 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 TechEd — session catalogue
- SAP Joule for Consultants: Unified knowledge for requirements and designsSAP Joule for Consultants: Unified knowledge for requirements and designsFit-to-standard analysis as a consultant on a cloud transformation project: connecting an organisation's data to SAP Joule for Consultants through SAP AI Core, getting answers from SAP knowledge and that content, then building an expert, loading project files and running guided prompts. The edges are to SAP Joule, of which Joule for Consultants is a part, and to SAP AI Core, named as the connection path; how the data is grounded is left to the session. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Anantharaman Ravi, Natalie Han, Sachin Kaura and Yi Hsuan Lin, written here from SAP's abstract; the recording is not yet published.SAP TechEd — session catalogue
- 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.Christian Lechner, Thorsten Sandfuchs, SAP TechEd — session catalogue
What’s New
from SAP Help Portal, readhelp.sap.com/whats-new, SAP AI CoreSAP’s wordsOn SAP Help Portal
147 entries from to , counted per month.
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Dataset API
Generative AI hub
Incremental improvements
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Service Plans
Service Plans
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Custom AI Executions
Administration
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
SAP BTP Cockpit
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generic Secrets
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Resource limits per tenant
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Generative AI hub
Deployments
Generative AI hub
Resource groups limit per tenant
Authentication
generative AI hub SDK
Generative AI hub
Template Generator
SAP AI Core Toolkit
Artifact signatures for artifact outputs from executions
LLM Package
Dataset API
Metadata in Response to List Executables
Contribute to Our Documentation
Bulk PATCH Endpoint to STOP or DELETE Multiple Executions or Deployments
Sync Endpoint for ArgoCD
WebHDFS Artifacts
Periodic Scheduling
Deployment Duration can be Limited
The YAML Files for Starter Tutorials Available Directly from GitHub
Enhancements to the GET Deployments API Call Response
Azure Blob Storage Supported
Deployment Duration Variable
Metrics Extension
Git Repository Name No Longer Mandatory
API Deprecation and Decommissioning
Serving Component Upgraded to KServe Version 0.7 for Security Compliance
Supported Object Stores
Enhanced Serving Template Parameters
Tracking Service Improvement
Documentation for the AI api client SDK has moved to PyPi.org.
Documentation for the sap-ai-sdk-core has moved to PyPi.org.
Additional Query Parameter for Metrics
Horizontal Scaling for Resource Group Operator Enabled
Resource Group Id Length Extended
Generic Secret Support at Main Tenant Level
AI API meta Endpoint
Others providing
LLM integrationLLM 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 and community, narrow by design
- llm_clientllm_clientAn ABAP client that gives chat-completion LLM APIs one interface for chat messages, structured output and tool calls across ten providers, from OpenAI and Anthropic to OLLAMA and AWS Bedrock.independent, abapABAP client with one interface to chat-completion LLM APIs
- abap-agent-runtimeabap-agent-runtimeAn ABAP-native MCP endpoint inside the SAP system: an agent reads the screen of an opted-in abap2UI5 app as structured data, fills its fields and fires its events as the logged-on SAP user.community org, abapABAP-native MCP endpoint that drives opted-in abap2UI5 apps
- abap_btocs_ollamaabap_btocs_ollamaAn ABAP plugin, built on the B-Tocs ABAP SDK, that calls models served by Ollama through an SM59 RFC destination, implementing four of its API endpoints: generate, tags, show and embeddings.independent, abapB-Tocs ABAP SDK plugin connecting to Ollama models
- abap-sdk-nwas-xabap-sdk-nwas-xAn ABAP client library for IBM's watsonx.ai and watsonx.ai Runtime APIs, installed into an SAP NetWeaver AS ABAP system through abapGit, generating and refreshing the IAM token from an API key.independent, abapABAP client library for IBM watsonx.ai APIs
- Microsoft AI SDK for SAPMicrosoft AI SDK for SAPMicrosoft's ABAP library for calling Azure OpenAI and OpenAI from an SAP application server, wrapping completions, embeddings, fine-tuning and the other operations in ABAP data types, installed with abapGit.partner, abapABAP library for calling Azure OpenAI and OpenAI
- zllmzllmAn ABAP framework for chaining and orchestrating calls to large language models in pure ABAP, with templated prompts, routing by complexity, response caching and token estimation.independent, abapABAP framework for chaining and orchestrating LLM calls
- ABAP AI SDKABAP AI SDKSAP's reuse library for calling a large language model from ABAP code, powered by Intelligent Scenario Lifecycle Management and reaching the models in the Generative AI Hub; delivered with SAP BTP ABAP environment, SAP S/4HANA Cloud Public and Private Edition and SAP S/4HANA.sap official, abapSAP reuse library for calling large language models from ABAP
- abap-sdk-nwasabap-sdk-nwasAn ABAP client library for IBM Watson's Discovery, Language Translator, Natural Language Understanding, Speech to Text, Text to Speech and Assistant services, installed through abapGit.independent, abapAn ABAP client library for IBM Watson's Discovery, Language Translator, Natural Language Understanding, Speech to Text, Text to Speech and Assistant services, installed through abapGit.
Retrieval-augmented generationRetrieval-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.SAP and community, unassessed
- zvdbzvdbA vector database implemented entirely in ABAP, which stores quantised vectors and retrieves the document chunks relevant to a prompt by brute-force dot product.independent, abapVector database implemented in ABAP for document chunk retrieval
Details
Sources
Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.
Compatibility and provenance
discovered viaAdded by hand
first seen in the atlas
ecosystem and domainbtp, ai-and-agents
History in the atlas
- First seen.
For your agent
- Ref
artifact:btp-ai-core- JSON
- /artifacts/btp-ai-core.json
- MCP
- Connecting an agent