Person
Stefan Rudi
Capabilities
Contributes to
Agent evalsCAPBTPABAPAgent evalsKnowing whether an AI feature still behaves after a model, prompt or schema change. Regression testing for non-deterministic output, against fixtures that reflect real business data.Agent guidanceCAPUI5BTPABAPAgent guidancePackaged knowledge you hand a coding agent so it gets a framework right unprompted — skills, rule files, instruction packs. Distinct from agent tooling, which is about building agentic features into your application, and from [agent access to your code](capability:agent-code-access), where the agent reads the real project instead of being handed a file about it.Agent toolingCAPBTPAgent toolingBuilding an agent into your own application — the tools it may call, the state it keeps between turns, and the framework it runs in. Distinct from MCP servers, which expose an application to somebody else's agent, and from agent guidance, which is knowledge handed to a coding agent.AttachmentsCAPUI5ABAPBTPAttachmentsStoring a file somebody uploaded next to the record it belongs to, and getting it back out — where the bytes actually live, who may read them, and what the UI shows while they are being scanned.Audit loggingCAPBTPAudit loggingRecording who touched personal or sensitive data, in a form an auditor accepts, without hand-writing it in every handler. It is often confused with application logging, which records what the code did rather than who accessed what.Change trackingCAPABAPChange trackingKeeping a readable history of what changed on a record, who changed it and when — as business history rather than database journalling.Data privacyCAPABAPBTPData privacyDoing what the law requires with personal data — knowing which fields are personal, answering a subject's request about them, and deleting them when the reason for holding them expires.LLM integrationCAPUI5BTPABAPLLM 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.LoggingCAPBTPABAPUI5LoggingSeeing what a running service did, in a form something can read afterwards — levels, a formatter that suits a laptop and one that suits a log service.NotificationsCAPABAPNotificationsTelling a person something happened when they are not looking at the screen — a notification in the launchpad, an email, a message somewhere they already are.Retrieval-augmented generationCAPABAPBTPRetrieval-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.Serve your application over MCPCAPBTPABAPServe your application over MCPExposing selected application data and business operations to an AI agent through the Model Context Protocol. An application may also integrate remote services through [service integration](capability:service-integration), connecting its exposed contract with [agent access to your systems](capability:agent-systems-access). Development assistance belongs to [agent access to your code](capability:agent-code-access).TestingCAPBTPTestingProving the service still does what it did — against the model and the handlers, without a deployed system and without a database somebody has to keep clean.Workflow integrationCAPWorkflow integrationDriving an external workflow or automation engine from an application and reacting to what it emits — triggering runs transactionally and importing the engine’s shape as a typed model.
Entries
Group by13 of 13 entries
EntrySignals
Contributes to
@cap-js/agents@cap-js/agentsSAP's own CDS plugin for building agents inside a CAP service, wired to audit logging and telemetry through peer dependencies rather than leaving observability to the author.sap official, cap
Not as a gateway or proxy for SAP Application APIs: capire's guide states that CAP-level agents are intended only for exposing custom CAP application services and are not an SAP-endorsed architecture or pathway for agentic access to those APIs, and sends the reader to the SAP Architecture Center for the endorsed routes. Not as the screen a user of the application talks to, either — the chat preview in the generic index.html page is marked experimental and for local development.
CDS plugin for building agents inside a CAP service
@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
Value-help recommendations and SAP AI Core as a CAP service
@cap-js/attachments@cap-js/attachmentsAn official CAP Node.js plugin for attachment handling, with local database storage and AWS S3, Azure Blob or GCP Object Store integration.sap official, cap
CAP Node.js attachments with database, S3, Azure or GCP storage
@cap-js/audit-logging@cap-js/audit-loggingIntegration with the SAP Audit Log service, so operations on personal data are recorded in the form an auditor expects without the application writing the entries.sap official, cap
CAP integration with the SAP Audit Log service
@cap-js/cds-test@cap-js/cds-testTest support for CAP Node.js, installed as a dev dependency: it starts the project's server for the test, hands the test an HTTP client bound to it, and carries the assertions.sap official, cap
Test support for CAP Node.js: server start, HTTP client, assertions
@cap-js/change-tracking@cap-js/change-trackingOut-of-the-box change history for annotated entities.sap official, cap
Change history for annotated CAP entities
@cap-js/data-privacy@cap-js/data-privacyIntegration with SAP Data Privacy Integration, driven by the personal-data annotations already on the model — the annotation that marks a field is the one the service acts on.sap official, cap
CAP integration with SAP Data Privacy Integration
@cap-js/mcp@cap-js/mcpA CAP plugin that serves an @mcp-annotated service over MCP with three generated tools, describe, query and call_action, and writes its endpoint into the local agent's configuration in development.sap official, cap
SAP prohibits gateway/proxy use for SAP Application APIs; the Atlas applies that prohibition to CAP wrappers around those APIs. Data changes require application-defined unbound actions, and the adapter supplies no rate limiting, agent-action audit logging, approval workflows or policy enforcement. In beta, with nine releases in the six weeks after the first, so pin it.
Exposes CAP services as MCP servers for AI agents
@cap-js/n8n@cap-js/n8nTriggers n8n workflows from a CAP application through @n8n.process.start annotations or a programmatic n8n service, resolving credentials from local config, a Cloud Foundry binding or a BTP destination.sap official, cap
Triggers n8n workflows from a CAP application
@cap-js/notifications@cap-js/notificationsPublishes business notifications to SAP Build WorkZone from the application, so a user is told something happened without the UI polling for it.sap official, cap
Business notifications from CAP to SAP Build WorkZone
capire/docscapire/docsThe sources of capire itself, in the repository it is built from: the documentation every core_coverage claim in this graph is checked against, so a claim can be dated against a commit.sap official, cap
Sources of capire, the CAP documentation
capire/skillscapire/skillsSAP's own skill set for coding agents working on CAP — cap-developer, cap-add-remote-service, cap-upgrade and cap-trivia, each a SKILL.md with references beside it.sap official, cap
Agent skills for CAP development, each a SKILL.md with references
xtravelsxtravelsA travel-booking application built on the master data that xflights publishes, composing another package's schema into its own rather than owning master data itself.sap official, cap
CAP travel-booking app built on xflights master data
Writing and topics
Piece, what it offersStill applies
CAP in the age of AI #5 - agents wrap-upCAP in the age of AI #5 - agents wrap-upThe agents topic closed out on what sits around the agent rather than inside it, now that the documentation has moved into capire. The chat preview's session is persisted in the database rather than kept in memory, traces go out through @cap-js/telemetry to a self-hosted MLflow under the OpenTelemetry conventions for generative AI, and the panel is explicit that @agent reuses the MCP adapter's code programmatically without serving an MCP endpoint. It ends in the xtravels sample, where a travel agent delegates to a hotel-service sub-agent and reaches a separately started flight service over MCP through the service binding CAP resolves anyway. Earlier in the hour the same agent answers from a model running on the presenter's laptop, reached as an OpenAI-compatible endpoint.published 2026-10-02
CAP in the age of AI #3 - from MCP to A2ACAP in the age of AI #3 - from MCP to A2AThe episode that finishes @cap-js/mcp with authorisation and then crosses to agents. @requires and @restrict are the same annotations CAP already has, and the plugin reads them to filter the tool list and the describe output per user and per request, so a model is not told about entities the caller cannot reach — where the OData metadata of the same service lists every exposed entity regardless. The second half annotates a service with @agent from @cap-js/agents, which serves it over A2A with an agent card and a chat preview, runs first against a mocked response and then against SAP AI Core bound with cds bind and a hybrid profile, and reuses the MCP adapter's tools rather than defining new ones.published 2026-08-21
CAP in the age of AI #2 - more on the MCP adapterCAP in the age of AI #2 - more on the MCP adapterWhat the query tool costs in tokens, and the third tool @cap-js/mcp registers. Counted against a model running locally under llama.cpp, the same query is 26 tokens as CQL and 173 as CQN, and the tool definition sent with every system prompt drops from around 5,500 tokens to around 600 — the reason CQL became the default format. The call tool then exposes a service's unbound actions and functions, as one generic tool or, behind a flag, one tool per action with its own description and input schema; a question from the chat about extension points gets the answer that the adapter does the tools, which the panel calls a small subset of the protocol.published 2026-08-14
CAP in the age of AI #1 - the MCP adapterCAP in the age of AI #1 - the MCP adapterThe episode that opens the series and the first pass over @cap-js/mcp, with four of the people building it on the call. Two of the adapter's tools are worked through: describe, the one an MCP client reaches for first to get the overview of what it may do, and query, which the panel establishes as read-only. It also writes the server entry into a local agent's own configuration file, which episode three comes back to as auto-wiring.published 2026-08-07
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
Details
For your agent
- Ref
actor:stefanrudi- JSON
- /actors/stefanrudi.json
- MCP
- Connecting an agent