NewSAP Cloud Application Programming Model
In the last 30 days
190 changes
Today
Give Your AI Agent Some Tools: Introducing the UI5 MCP ServerpublishedAnnounces @ui5/mcp-server@ui5/mcp-serverSAP's MCP server for UI5 development: ten tools that scaffold an app or a card, read the project in front of the agent, and run the linter and the manifest validator against it.sap official, ui5, SAP's open-source MCP server for UI5 development, and walks through its initial six tools. get_project_info, get_api_reference and run_ui5_linter (which applies UI5 linter@ui5/linterSAP's static analysis tool for UI5 projects: it scans JavaScript, TypeScript, XML, JSON and other files for deprecated APIs, global variables and possible CSP violations, and fixes part of them with --fix.sap official, ui5 fixes) read the project's own version, manifest and code rather than an LLM's training data, which is what agent access to your codeAgent access to your codeLetting a coding agent read the project or the system you actually have, reach its model, its objects and its checks, and act on it. In file-based environments that works out of the box; complex systems need dedicated access capabilities. Whatever the environment, the agent also needs project- and framework-specific context, so it understands the thing in front of it rather than guessing from what it remembers of its training data. The transport is incidental: an MCP server, a language server or a CLI answer the same question, and what differs between them is how much of the real thing the agent can see. Distinct from MCP servers, which is a protocol adapter on your own running service, and from agent guidance, which is knowledge handed over as files rather than read from the thing itself.SAP and community, unassessed explains. create_ui5_app scaffolds a new JavaScript or TypeScript project, standalone or inside an existing CAP application, from templates with pre-configured OData model setups, which is generatorsGeneratorsGetting from nothing to a project that runs, and from a project that runs to one that has the piece you just decided you need. Two different moments: the first is a one-time decision about layout, the second recurs for the life of the project.SAP and community, narrow by design.Agent access to your code
Joule Studioがリリースされたので早速CAPアプリを自然言語で操作するカスタムスキルを構築してみたpublishedA walkthrough of building a custom Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella skill on a CAP bookshop app:
cds add sample and cds add mta scaffold the project and its deployment descriptor, cds compile srv/ --to xsuaa generates the role template behind the @requires: 'admin' check on AdminService from the SAP Authorization and Trust Management serviceSAP Authorization and Trust Management serviceThe OAuth server behind a BTP application: issues the JWT the app checks, holds the scopes and role collections it checks against, and brokers trust to an identity provider. Bound, never installed.sap official, btp (XSUAA), and mbt build packages the app for deployment to the SAP BTP, Cloud Foundry RuntimeSAP BTP, Cloud Foundry RuntimeThe Cloud Foundry runtime of SAP BTP: memory for applications in a Cloud Foundry org, run from SAP's Java, Node.js and Python buildpacks or community buildpacks and managed with the standard Cloud Foundry tools.sap official, btp. The skill reaches the deployed ODataODataExposing data and operations through OData, including the service model, metadata and protocol versions clients require. Version differences affect which clients can consume a service and which query features they can use.SAP and community, narrow by design API through the SAP Destination serviceSAP Destination serviceNamed, credentialed addresses of other systems, resolved at runtime — so an application holds no URL and no secret of its own, and the same code reaches a different system in every landscape.sap official, btp, configured with the OAuth2 Client Credentials grant using the client ID, secret and token endpoint from the app's XSUAA service key, so Joule answers a natural-language question about a book by its ID.Agent toolingUI5 MCP Server Got Extended for UI Integration Cards GenerationpublishedVersion 0.2.1 of the UI5 MCP Server@ui5/mcp-serverSAP's MCP server for UI5 development: ten tools that scaffold an app or a card, read the project in front of the agent, and run the linter and the manifest validator against it.sap official, ui5 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.Agent access to your code
Agent access to your codecoverage by ecosystem, coverage by flavor revisedReassessed against the graph (check:capabilities): removed the tool count and the two absence claims about who has built something.Agent access to your code
Show 9 more
Agent evalscore coverage, coverage by ecosystem revisedReassessed against the graph (check:capabilities): albertmink-agentic-abap-evals, an independent set of ABAP tasks and a grader for coding agents, was entered after the block was written; the count is dropped and the second kind named. State unchanged.Agent evals
Agent guidancecoverage by ecosystem, coverage by flavor revisedReassessed against the graph (check:capabilities): docs/WRITING.md §3 rules out provider counts and absence claims in every capability field.Agent guidance
Agent toolingcore coverage, coverage by flavor, coverage by ecosystem revisedReassessed against the graph (check:capabilities): sap-joule-studio and sap-joule, both sap-official, now provide this capability behind the BTP door, so the note's claim about every entry no longer held. The state stays core-only: no provider of another origin counts for the door.Agent tooling
Document extractioncoverage by ecosystem revisedReassessed against the graph (check:capabilities): removed the provider-count and absence claims (docs/WRITING.md §3); the states are unchanged.Document extraction
LLM integrationcoverage by ecosystem, core coverage, coverage by flavor revisedReassessed against the graph (check:capabilities): the note claimed who provides the capability behind this flavor, which moves with the corpus. The flavor state is unchanged.LLM integration
Prompt managementcoverage by ecosystem, core coverage revisedReassessed against the graph (check:capabilities): the note was a claim about who provides, which the option list derives.Prompt management
Retrieval-augmented generationcoverage by ecosystem, core coverage revisedReassessed against the graph (check:capabilities): a CAP-door provider reaches Document Grounding through the LangChain vector store interface, a shape the two plugins do not cover.Retrieval-augmented generation
Tool governancedescription, core coverage, coverage by ecosystem, framing by ecosystem, coverage by flavor revisedReassessed against the graph (check:capabilities): a count of providers removed.Tool governance
Workflow integrationcore coverage revisedReassessed against the graph (check:capabilities): the CAP Java n8n plugin is SAP-official and uses the outbox, so outbox dispatch is no longer only a community addition. Source: the plugin's README. State unchanged.Workflow integration
Yesterday
Agent access to your codecoverage by ecosystem revisedRewritten at the maintainer's request (2026-10-25): what SAP ships named whole, and what the community adds written from what its ABAP MCP servers state about how they run, connect and sign in.Agent access to your code
Sat 24
btp-agentadded to the atlasLangGraph agent and UI5 chat screen over four BTP MCP servers
Using BTP Document Extraction Service into actual App developmentpublishedWalks through calling SAP Document AI's REST API directly: getting a client-credentials bearer token from the service key's UAA, then POSTing to /document/jobs with a file and an options body naming the document type and the header fields and line items to extract (paymentTerms, documentDate, taxId, description for an invoice), and polling the returned job id until the status resolves. Covers the trial-account booster and its own UI for uploading a document and testing extraction before moving to Postman and a small Python script that lists jobs over the same bearer token.Document extraction
Fri 23
Cloud Integration with Document AIpublishedWalks through connecting Cloud IntegrationCloud IntegrationBuilds and runs integration flows that process, route and map messages between cloud and on-premise systems, SAP and non-SAP, through prebuilt adapters; available only under an SAP Integration Suite plan.sap official, btp to SAP Document AISAP Document AIExtracts header fields and line items from invoices, payment advices, purchase orders and custom document types, as structured data over a REST API — the extraction is the service's, the schema can be yours.sap official, btp: an iFlow posts a prescription PDF to Document AI's job API, polls the job endpoint until it completes, and a groovy script reads back the result, keeping only the fields above a stated 60% confidence threshold. The scenario is a hospital extracting a new patient's past illnesses, allergies and blood group from uploaded prescriptions, matched against a custom extraction schema.Document extraction
Thu 22
@mi8y/cap-agents-sdm-backendadded to the atlasDeep Agents filesystem over an SAP Document Management repositoryAgent tooling
Reports Assistant with SAP Document Managementadded to the atlasCAP agent writing reports into a shared SDM document workspace
Tue 20
What an AI infra engineer sees when opening SAP's AI stack (1/3): the model gatewaypublishedA first look at SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp's Generative AI Hub from someone who builds gateways outside SAP for a living: the orchestration service harmonizes provider calls onto one API (a model name string switches providers, and SAP Note 3437766 carries the current model list, token rates and deprecation dates), runs a fixed, non-reorderable module pipeline — templating, masking through SAP Data Privacy Integration, grounding, content filtering, then the model call — and retries down an ordered fallback list whose entries can each carry their own model and rules. It places @sap-ai-sdk/orchestration@sap-ai-sdk/orchestrationThe Orchestration Service client of SAP's AI SDK, which applies templating, grounding, filtering and masking around a model call rather than in the application.sap official, cap among the official JavaScript, Java and Python SDKs, and notes SAP's own LiteLLM provider as a way to put a different gateway in front of it.LLM integration
Mon 19
🟣 Bring AI into Your ABAP Applications with ISLM: Build, Integrate, and Consume AI NativelypublishedDevtoberfest 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, 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 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, abap, 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.LLM integration
🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and CompliancepublishedDevtoberfest 2026 session AI-21. A cross product owner on the SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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 managementPrompt 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.SAP only); 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 evalsAgent 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.SAP and community, unassessed); and the orchestration service harmonising the providers behind one message format with a priority-sorted fallback list (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). 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.LLM integration
Achieve Agentic Enterprise Automation with SAP Integration Suite and Joule StudiopublishedA Devtoberfest 2026 integration-track session (INT-22), the second of that week's integration sessions, given by an SAP product expert for process automation and integration together with the product manager for Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella, who walks the audience through it. The opening states the subject: process management, automation and orchestration unified into one combined approach, which the presenters put forward as the foundation for building custom AI agents.Agent tooling
AI Assisted CAP DevelopmentpublishedA Devtoberfest 2026 session (CAP-43) on building CAP applications with a coding agent, in two demos. The first asks the same question twice in a dev container, once with no MCP server configured and once with @cap-js/mcp-server@cap-js/mcp-serverSAP's MCP server for CAP development, run as cds-mcp: search_model searches the project's compiled CDS model, search_docs searches the CAP documentation indexed as embeddings on the developer's own machine.sap official, cap registered: without it the agent answers CAP's semantic search with an outdated vector type and CQL, with its documentation search it writes the built-in vector embedding function and a working similarity query. The second installs the cap-developer plugin from 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, from a Devtoberfest preview branch, and runs its guided-development skill stage by stage — domain model, sample data, services, constraints — each stage reviewed before the next.Agent access to your code
Show 16 more
AI-assisted SAP development with MCPpublishedA Devtoberfest 2026 session (UI-41) that traces AI-assisted SAP development from pasting code into a chat window to coding agents with built-in connectors, and sorts the MCP servers around SAP development into SAP's own, the community's and the hosted ones, where the agent cannot change what the server allows. Four demos follow: GitHub Copilot alone explaining an ABAP report from a Git repository, @ui5/mcp-server@ui5/mcp-serverSAP's MCP server for UI5 development: ten tools that scaffold an app or a card, read the project in front of the agent, and run the linter and the manifest validator against it.sap official, ui5 reading an OpenUI5 sample app and converting it to TypeScript, mcp-sap-docsmcp-sap-docsAn MCP server over seventeen cloned SAP documentation repositories — ABAP keyword docs, capire, OpenUI5, Cloud SDK, BTP — searched with BM25 and prebuilt embeddings fused by reciprocal rank fusion.independent, cap grounding Terraform files for a BTP subaccount the presenter had not written before, and arc-1arc-1An MCP server in front of the ADT REST API that runs locally and on Cloud Foundry with twelve tools that read, search, write, activate, lint and transport ABAP objects.independent, abap with Copilot in Eclipse tracing why a title longer than 40 characters is rejected and proposing the DDIC-allowed length instead. It ends on a skill that migrates an SAP Gateway project on an ECC system to RAP on S/4HANA step by step, and on a rule Marian ZeisMarian Zeismaintains 35 entries, created 25 pieces, contributed to 86 entries gives for servers written for internal use: keep them read-only, because what the agent is short of is context.Agent access to your code
Be the First to Understand Joule Work's Agentic ThinkingpublishedA Devtoberfest 2026 session on the agent harness behind agentic thinking in Joule WorkJoule WorkSAP’s workspace where people express a goal, work with the results in contextual Spaces and direct Joule Assistants and Joule Agents across SAP and third-party systems.sap official, umbrella: generic operating-system tools in a gVisor-isolated sandbox instead of hand-wired domain functions, a react loop, a warm pool of sandboxes torn down after each task, tenant-separated skill loading, and placeholder tokens the agent never sees swapped for real credentials at the egress path. A skill is a folder with a SKILL.md carrying metadata and instructions, and where it reaches a system, an SAP connectivity JSON that declares each connector by ORD ID with its guardrails — GET allowed by default, POST, PUT, PATCH and DELETE requiring human approval, everything else blocked. The demo uploads a cost-centre skill through the skills view, then has agentic thinking delegate over A2A through Agent Gateway to a custom agent built in Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella, whose MCP tools read cost centres from an S/4HANA Cloud system, and ends by turning the result into a PDF; the Joule Studio trace is what shows the tool call actually happened.Agent tooling
Beyond copilots: Agentic development with SAPUI5publishedDevtoberfest 2026 session UI-12, from the SAPUI5 team, on the year of work behind UI5/plugins-coding-agentsUI5/plugins-coding-agentsUI5's own plugins for coding agents, three of them: everyday development, modernising a legacy project, and converting one to TypeScript, each installed into Claude Code or GitHub Copilot.sap official, ui5: what a model produces for UI5 without help — outdated concepts, framework versions a decade old, generic JavaScript rules, code that does not run — and the two ways they chose to close that gap, an MCP server in September 2025 and skills packaged as plugins once agents began reading them. Three plugins are demonstrated live in Claude Code: the everyday one scaffolds an Oktoberfest tents application in about four minutes, the TypeScript conversion plugin rewrites an existing JavaScript project and reconfigures its build with the types and the transpile task, and the modernisation plugin takes a ten-year-old application through staged migrations, applying UI5 Linter's automatic fixes where they cannot break the app and the model where they can, then running the tests. @ui5/mcp-server@ui5/mcp-serverSAP's MCP server for UI5 development: ten tools that scaffold an app or a card, read the project in front of the agent, and run the linter and the manifest validator against it.sap official, ui5 is still the path for the parts that need a server, and the plugins are installed from the Claude Code and GitHub Copilot marketplaces rather than a UI5-hosted one.Agent guidance
Bring "developers.sap.com" Into Your Dev Environment: SAP Developer Context for AI Coding AgentspublishedDevtoberfest 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 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 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 MCPSAP Developers MCPThe hosted MCP server of developers.sap.com, over which an agent searches SAP's tutorials, reads missions and queries the site's knowledge graph of tutorials and concepts.sap official, umbrella 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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.Agent guidance
Building Agentic Workflows with n8n in Joule StudiopublishedA Devtoberfest 2026 session, JS-31, on SAP-managed n8n inside Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella, 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 CenterSAP Task CenterOne inbox across SAP applications: tasks from S/4HANA, SuccessFactors, Ariba and BTP workflows in one list, with a public API for a custom task provider.sap official, btp, and SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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.Agent tooling
Building Code-Based AI Agents on the BAIPpublishedA Devtoberfest 2026 session on writing the agent yourself rather than configuring one, which is the agent toolingAgent 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.SAP and community, unassessed 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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-webuicap-agent-ui5-webuiGives a CAP agent a UI5 web interface out of the box, so an agent built in the service has somewhere to be talked to without a separate frontend project.independent, cap 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.Agent tooling
From Intent to Arcade: Building Joule*Bert with Joule Studio and AI-Assisted Pro CodepublishedA Devtoberfest 2026 AI-track session that takes a Q*bert-style arcade game, written as an Easter egg for colleagues, through every phase Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella runs: intent analysis with its clarifying questions, a product requirements document, a specification with its task list, generated code, generated tests and deployment. The knowledge-graph lookup reports that the game maps to no enterprise process and the flow adjusts, and the presenter edits the requirements by hand when the first version declares sound out of scope. He then pushes the project to GitHub, clones it and initialises the jl command line@sap/joule-work-dev-cli-early-adoptersjl, the pro-code CLI of the new Joule Studio: a solution is a folder with a solution.yaml and typed assets, validated, built into a zip and deployed to Joule Studio's managed runtime, with Claude Code or OpenCode wired in over MCP. Early Adopter Care.sap official, btp so that Joule Studio's MCP servers are wired into the coding agent in VS Code, where mobile arrow keys were added afterwards; applications could not yet be deployed to the Joule Studio runtime, so this one runs on Kyma.Agent tooling
How to implement business AI capabilities in ABAP CloudpublishedA Devtoberfest 2026 session (ABA-32) on embedding AI in an ABAP Cloud application and on making SAP Joule aware of what that application can do. The first demo implements two features of a RAP travel app with the ABAP AI 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, abap: a determination on an uploaded receipt that sends the image together with the allowed categories and transaction types to a model reached through an intelligent scenario, then writes the extracted description, category, currency and amount back to the expense entity; and a recommendation function, triggered by a side effect on the trip title, that proposes a trip type with a score the Fiori UI sorts the proposals by and leaves the business user to accept — which is LLM 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 from ABAP code. The second demo builds a capability for SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp in the Joule Studio code editor in VS Code, with a scenario that extracts a trip title from the user's intent and calls an OData service in the ABAP backend through a BTP destination, deploys it and asks the Joule test UI for the trip's details; the session states that agents reach ABAP only over governed remote APIs — OData, SQL and MCP — and that automatic grounding of custom OData services in the knowledge graph is upcoming rather than available.LLM integration
Intelligent App Development at Scale: SAP Fiori Elements + ABAP Development Tools for VS CodepublishedA Devtoberfest 2026 session (UI-33) that builds a RAP service and the SAP Fiori elements app over it from one VS Code workspace, with a coding agent driving two of SAP's MCP servers. The ABAP Development Tools for VS CodeABAP Development Tools for VS CodeSAP's ABAP tools in VS Code: editing, debugging, ABAP Unit, ATC and transports for classes, CDS and RAP objects, over RFC to an on-premise or Private Cloud system and HTTP to a cloud one, with Joule's ADT MCP server and code completion behind an AI-unit licence.sap official, abap edges hold on the demo itself: its virtual file system keeps the ABAP package beside the Fiori project, the ADT MCP ServerADT MCP ServerSAP's own ADT MCP server, and not a package: a preference inside ABAP Development Tools for VS Code that starts a local HTTP MCP server on a port you choose.sap official, abap inside it creates, changes and activates the ABAP objects, and a version not yet released publishes the service binding from the agent instead of by hand. The @sap-ux/fiori-mcp-server@sap-ux/fiori-mcp-serverSAP's Fiori MCP server, run as fiori-mcp, letting a coding assistant create and edit Fiori applications directly rather than describing the steps.sap official, ui5 edge covers its generators and the three-step workflow it uses for changes — list the functionality available for the application, ask for its JSON schema, then execute it — and the agent guidanceAgent 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, where the agent reads the real project instead of being handed a file about it.SAP and community, core adopted it edge rests on the skills the Fiori team publishes beside it, on the session's account of what a skill adds that a server does not, and on the analytical chart demo where a skill orchestrates both servers in one task.Agent access to your code
Meet Joule Studio and Build your First AI AgentpublishedA Devtoberfest 2026 session from the product manager of Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella, walking one agent through the whole path the tool defines: an intent, the problem statement and goals a coding agent derives from it, the business context it takes from the SAP knowledge graph, and the solution type it proposes with a stated intent fit. The demo is a collections agent that drafts dunning emails: the product requirements document names the metrics and the human-in-the-loop review, the technical specification lists the artifacts to build — the MCP tools among them — and the build is followed by a business test run against business partner 10001, technical unit tests, and deployment to the managed runtime, where the agent and its MCP server appear as deployed assets. Two points shape how it is used rather than what it produces: every asset is a file, editable in the web editor or in the code view and pushable to git, and the same solution can be built from local pro-code tools; n8n workflows are stated as delivered out of the box inside the studio.Agent tooling
Real Pro-Code Development with Joule StudiopublishedA Devtoberfest 2026 AI-track session that runs one agent build across both of Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella's paths. Playing a procurement manager, one presenter states the intent in the browser, answers the clarifying questions, watches the fit-gap analysis name the S/4HANA APIs the use case needs, and pushes the intent and requirements document to GitHub; the other clones it and carries on in a terminal, logging in with the jl command line@sap/joule-work-dev-cli-early-adoptersjl, the pro-code CLI of the new Joule Studio: a solution is a folder with a solution.yaml and typed assets, validated, built into a zip and deployed to Joule Studio's managed runtime, with Claude Code or OpenCode wired in over MCP. Early Adopter Care.sap official, btp against her landscape URL and running its init command to fetch Joule Studio's skills for OpenCode. From there the coding agent writes the specification, the discovered API specifications, the MCP translation and the agent's Python file with its model configuration and evaluation scenarios, which is the edge to Agent toolingAgent 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.SAP and community, unassessed; the skills themselves, which SAP says not to edit but which a developer may add to, are the edge to Agent guidanceAgent 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, where the agent reads the real project instead of being handed a file about it.SAP and community, core adopted it.Agent tooling
SAP BDC and AI: A Perfect MatchpublishedA Devtoberfest 2026 data-track session (DAT-22) in which Business Data Cloud's CTO sets out how SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp feeds SAP's business AI platform: data products whose primary persistence is an object store and whose semantics are kept with them, the one domain model that links a supplier in Ariba to a supplier in S/4HANA, and the SAP knowledge graph, a triple store running in SAP HANA Cloud and queried with SPARQL, that SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp consults before answering. The live demo asks Joule for the available data products and the top ten open purchase orders, with the data product query agent compiling SQL over virtual tables and a space rendering a dashboard, which is the cataloguing side of this: a central registry, the Unified Customer Landscape, that every activated data product is registered in. The Q&A covers where the knowledge graph lives and what a customer may extend, base policies that turn into filter conditions on an agent's queries, and Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella as the place to build your own agents and data products.Agent tooling
Supply Chain Rescueadded to the atlasCAP and SAPUI5 demo of recovery from a supply disruption
Unlocking Tabular Foundation Models: From Experimentation to ProductionpublishedA 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, 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-skillsaicore-skillsFour agent skills for SAP AI Core, published as a plugin inside SAP's AI Skills Library: admin resources, the deployment lifecycle, the foundation models in the Generative AI Hub, and the Context Registry behind tabular prediction.sap official, btp plugin in a coding agent, and one of them only resolves once the agent is told which scenario configuration to use.LLM integration
secondsky/sap-skillstype properties, flavors revisedRead today in the two plugins that answer the CAP and the UI5 door, which the ABAP pass had not opened. The sap-cap-capire skill's frontmatter states that it covers Node.js and Java runtimes, so CAP's two flavors rest on the maintainer's sentence where the entry previously answered in both by the serves-another-door fallback, which is the same reading off an absence. The sapui5 skill's frontmatter names freestyle apps and Fiori elements apps in one clause, so freestyle is stated, and fiori-elements moves onto that sentence from the README line about which request activates sap-fiori-tools, which said what triggers a plugin rather than what it covers. Nothing read names UI5 Web Components, so that flavor stays unstated. Stating freestyle changes an answer: the entry answered no there while it stated one UI5 flavor and now answers yes, which a reader comparing that flavor's options will see. The ABAP pair is unchanged.Agent guidance
Werkbankprovides revisedWhat Werkbank adds for ABAP, CAP and UI5 is its catalog of development skills; the workspace itself is not specific to any of those stacks. Agent workspaces is narrowed back to BTP.Agent guidance
Sun 18
CAP in the age of AI #4 - more on agentspublishedAsking a human first, and telling the agent how to behave. Ordering a book through @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 happens without a question being asked; the human-in-the-loop annotation on the action turns the same request into an approve-or-reject step, which the episode follows down to the A2A status update that stores the task in an input-required state in the database — A2A itself being JSON-RPC 2.0 over HTTP with server-sent events for the stream. The rest is instructions on disk: an
agents.md in the service's own folder removes the question about how many copies to order, a skill under a skills folder is advertised by its description and read only when the agent decides the case applies, and either file makes the plugin build a deep agent instead of the plain one.Agent toolingCAP in the age of AI #5 - agents wrap-uppublishedThe 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@cap-js/telemetryAutomatic OpenTelemetry instrumentation for CAP Node.js services and their database calls, exported as traces and metrics to the console, SAP Cloud Logging, Dynatrace, Jaeger or an OTLP endpoint.sap official, cap 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 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 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.Agent toolingCAP in the age of AI #6 - vector embeddingspublishedVector embeddings put to work in the incident managementcapire/incidents-appThe Incident Management reference application — the one SAP's own tutorial paths build, step by step, and the model cds add incidents-sample drops into a project.sap official, cap 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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 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 the function is native, while SQLite needs packages added to the project.LLM integrationCAP in the age of AI #7 - vector embeddings wrap-uppublishedThe same embeddings model taken from SQLite to 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, then handed to an agent. Locally it is @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 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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@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, so an agent asked about low output from solar panels calls semantic search instead of writing the query itself.LLM integrationShow 3 more
How Redwood Software and SAP are shaping the next era of automation with Joule StudiopublishedRedwood's Field CTO describes a tech preview where an SAP Basis administrator tells SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp in natural language to pause background jobs and dependent Integration Suite iFlows for unplanned system maintenance; Joule acts as a control tower, triggering a pre-approved RunMyJobs workflow and asking for approval before the restart proceeds. The integration is built by publishing RunMyJobs operations to the SAP Business Accelerator Hub, securing access through SAP BTP with API keys and role-based permissions, and combining those actions into a skill inside Joule StudioJoule StudioSAP’s managed development environment for building custom agents, applications and workflows from business intent, in six phases from intent and specification to deployment on an SAP-managed runtime.sap official, umbrella's low-code design canvas.Agent tooling
SAP Developers MCPadded to the atlasHosted MCP server of developers.sap.com tutorials and missionsAgent guidance
SAP Developers MCPentry revisedNEIGHBOURS §5.1 named the hosted MCP as a companion to index as an artifact, and the graph had no entry for it. ecosystem: umbrella because its content covers SAP technologies across stacks (llms.txt names ABAP Cloud, CAP, Fiori, HANA Cloud and integration) and no single door holds it. No read_only: the anonymous mounts are read-only, but the signed-in tier writes progress (complete_step). No tool_count: the quickstart and the API page list different tools per mount. The site also serves a GraphQL API, not recorded as an interface here for want of a page read. /mcp/homepage is left out of the description: the quickstart lists it as anonymous and the API page as signed-in.Agent guidance
Sat 17
⚡Unlocking the Power of LLMs in CAP: Understanding llms.txt and llms-full.txtexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent guidance
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3explains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3explains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3explains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
Show 51 more
A modern workflow for SAP Cloud Integration with CAP and Azure DevOpsexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Workflow integration
Adapting SAP Joule for Purchase Order Creation from an Existing Purchase Requisitionexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Agent access to your systemsdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.cap. Maintainer-requested scope audit.Agent access to your systems
Agentic Engineering for SAP BTP Extensionsexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
AI-assisted full stack development using model context protocol serversexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
AI-native North Star architecture — Platform Layerexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent tooling
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Automate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation Appsexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Workflow integration
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI Stackexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Boost your CAP Development with AI: Introducing the MCP Server for CAPexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
Building a CAP service with cds‑mcp and Cline — HANDS‑ON SUPER BASIC GUIDE [ with screenshots ] 🍌explains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
Building an LLM Agent in CAP Java with Spring AIexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Building an LLM Agent using CAPexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Building Durable AI Agents - Announcing the cds-langgraph-persistence Pluginexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
cds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
Connecting AI agents to the ABAP RESTful application programming modelexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Creating a meal generator application with SAP Build, Cloud Application Programming and openAIexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Document Groundingexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Retrieval-augmented generation
Elevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM Pluginexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
Empowering Your Data Analytics with GPT-3 and SAP CAP Integrationexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Enhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI Pluginexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
Evaluating SAP’s new MCP servers: UI5, CAP, and Fiori tools in practiceexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
Event Driven SAP CAP on Kyma with Agentic AI and UI Auto Refreshexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent tooling
From SEGW and Legacy UI5 to RAP with ARC-1explains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
Generate agentic workflows using SAP-managed n8n in Joule Studioexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Generative AI on SAP BTPexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Github Copilot VSCode - My Own SAP Development Rulesexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent guidance
HANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI Embeddingexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Retrieval-augmented generation
Hands on SAP Document AI: Next-generation intelligent document processingexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Document extraction
How I Use AI for Development and Why Context Mattersexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
How SAP Document AI brings agentic intelligence to business documentsexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Document extraction
How to Reduce Prompt Token Costs Using Toon = Save Moneyexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
How to use Cloud SDK for AI in an existing CAP NodeJS Project in CommonJSexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Integrate CAP application as outbound channel for SAP Document AIexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Document extraction
Integrating a Custom AI Model into SAP CAP Using AI Launchpadexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Integrating and Extending Jouleexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
Integrating SAP Document Information Extraction (Document AI) with SAP CAP – Step by Stepexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Document extraction
Lets Talk to the Database - CAP & SQLite Powered by Google Gemini-2.5-Proexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).LLM integration
Natural Language Queries for SAP CAP via MCP: The LLM Translates, CDS Executesexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
OData to outcomes—Build AI-enabled SAP Fiori apps using SAP Fiori elementsexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
RAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Retrieval-augmented generation
SAP Build Process Automation – Use Principal Propagation in Actions sample: CAP Node.js Serviceexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Workflow integration
SAP Document AIexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Document extraction
SAP Fiori Tools Update – First Release of the SAP Fiori MCP Server for Agentic AIexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent access to your code
SAP Joule implementation in an S/4HANA private cloud 3 system landscapeexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Agent tooling
SAP’s compositional design system: Craft enterprise UIs with AI on the flyexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Generative UI
Teaching AI Agents Best Practices: A Skills Workspace for CAP Developmentexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Agent guidance
Triggering SAP Build Process Automation Processes from SAP Cloud Application Programming (CAP) Appsexplains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Workflow integration
UI5 AI Features library is now an npm Packageexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).LLM integration
Using HANA Cloud’s "VECTOR_EMBEDDING" Function in CAPexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Retrieval-augmented generation
Workflow integrationdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.cap. Maintainer-requested scope audit.Workflow integration
Thu 15
Agentic Engineering for SAP BTP ExtensionspublishedAn agent harness coordinates code generation across isolated Git worktrees, using a skills registry, SAP CAP MCP Server@cap-js/mcp-serverSAP's MCP server for CAP development, run as cds-mcp: search_model searches the project's compiled CDS model, search_docs searches the CAP documentation indexed as embeddings on the developer's own machine.sap official, cap, Fiori MCP Server@sap-ux/fiori-mcp-serverSAP's Fiori MCP server, run as fiori-mcp, letting a coding assistant create and edit Fiori applications directly rather than describing the steps.sap official, ui5 and UI5 Web Components MCP Server@ui5/webcomponents-mcp-serverFour tools that answer an agent's questions about UI5 Web Components from the framework's own documentation — component API, integration guides, and the docs themselves.sap official, ui5 for development context. The diagram shows LiteLLM as a model proxy in front of SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, while automated checks and review gate the generated changes. The worked scenario is CAP-based extensions on BTP, with specifications written before generation and reusable skills governed across teams.Agent access to your code
cap-openaiadded to the atlasCAP service actions calling OpenAI chat completions two ways
Joule Studioadded to the atlasSAP's managed environment for building custom agents and workflowsAgent tooling
Werkbankadded to the atlasLocal desktop workspace for AI conversations with SAP connectorsAgent guidance
Show 26 more
@cap-js/agentsdescription, provides, requires revisedHow the agent reaches a model was nowhere on the entry, while the Java module of the same plugin already carried the edge. capire's configuration table states that aicore is the default for the production and hybrid profiles and connects to SAP AI Core, with auto and mock as the development kinds, so the requirement is conditional and the condition names the alternatives.Agent tooling
@cap-js/aiprovides[llm-integration] revisedRe-read for the capability's impact assessment. The page still carries the claim, now in a longer sentence that also names the automatic service-binding resolution and the tenant-aware resource groups and deployments the coverage paragraph leans on, so the quote is the full sentence and the date is today's.LLM integration
@jerome-benoit/sap-ai-providerprovides[llm-integration], description revisedThe page opened with its index line alone, which left two facts a reader of this capability needs unsaid: that there are two routes into SAP AI Core and that only the model is replaced, not the SDK around it.LLM integration
@mi8y/cap-agents-memoryprovides revisedcapability:agent-tooling declared four comparison properties on 2026-10-15. Three are answered from the README's own opening and CAP notes, re-read the same day and unchanged, scoped to the node flavor: the package holds state between turns, it is written against LangGraph's Store API, and that state is rows in the CAP database under the request's tenant. The approval property is left out: the README says nothing about it.Agent tooling
@mi8y/cds-langgraph-persistenceprovides revisedThe entry stated the capability with nothing behind it while the README says exactly what the package holds. Read on 2026-10-15: checkpoints are short-term, thread-scoped state used to resume workflows, retain conversation history and support time travel, backed by CDS, requiring @sap/cds >= 10. capability:agent-tooling declared its comparison properties the same day, so the edge now answers three of them, scoped to the node flavor. The README's sentence about what to prefer for a new application has been reworded since 2026-09-21 — it now reads 'This package remains available for its existing CDS checkpointer implementation' — and the claim the page already carries is unchanged, so only the quote on the edge is new.Agent tooling
@sap-ai-sdk/foundation-modelsprovides[llm-integration] revisedcapability:llm-integration declared model_access and response_streaming on 2026-10-15. The package's own chat-completion page, read the same day, states that its chat client streams over server-sent events, which is the fact that decides whether a chat surface can show an answer as it is written; the edge rested on the repository README alone before.LLM integration
@sap-ai-sdk/orchestrationprovides[llm-integration] revisedcapability:llm-integration declared model_access and response_streaming on 2026-10-15. The orchestration chat-completion page, read the same day, states that the model is the name property of the promptTemplating configuration and that the harmonised API behind it lets a different model be used without the client code changing, and that the client streams over server-sent events. Both facts decide something for a reader and neither was on the edge.LLM integration
@sap/joule-studio-clidescription, provides, links revisedCurrent npm README for 2.0.4, published 2026-10-07, says "Installing
@sap/joule-studio-cli gives you two commands:" and lists joule and jl. SAP Help now installs this package for the new Studio workflow. The historical alpha package stays separately indexed; no unverified rename or lineage relationship is inferred.Agent tooling@saptarishi/cds-plugin-llmprovides revisedcapability:llm-integration declared the same two properties on 2026-10-15. This is the one option behind the CAP door whose README names providers on both sides of the SAP AI Core boundary, and the streaming value rests on the
stream method in the interface the README's own opening sentence lists. Both values are scoped to the node flavor, which is the only one this plugin states.LLM integrationAgent access to your codeframing by ecosystem revisedBeside Agent access to your systems, the ABAP door read as two names for one thing. This one is about the code, development objects reached through ADT; that one is about business data and operations. The atlas maintainer's decision.Agent access to your code
Agent evalscore coverage, coverage by flavor, facets, gap revisedThe note rested on "everyone" and "nobody", which nothing here sources. The replacement says what the material read on the three doors covers and what it leaves to the project, which is checkable.Agent evals
Agent guidancecoverage by ecosystem, framing by ecosystem, facets, coverage by flavor, framing by flavor revisedskillOverflowDanKromp/skillOverflowA collection of 41 agent skills, 37 for CAP, Fiori, BTP, UI5, ABAP, Integration Suite and HANA work and four for creating, reviewing and retiring skills, each with its own eval.independent, cap entered on 2026-09-18, after this flavor was assessed, serves the UI5 door and states no flavor, so by the flavor rule it answers in all of them. Its own skill list names SAPUI5 data binding, custom controls, i18n and testing and nothing about the component library, so it is reported as a fallback rather than read as a community presence here. Saying so is what keeps core-only honest beside the options the page lists.Agent guidance
Agent toolingcore coverage, coverage by flavor, framing by flavor, facets, normative relevance revisedcapire's own guide opens with a caution naming section 2.2.2 of the SAP API Policy and stating that CAP-level agents are not an SAP-endorsed architecture or pathway for exposing, proxying or providing agentic access to SAP Application APIs. That is the core's statement about where this capability may be pointed, so it belongs beside the framing rather than only in the boundary sentence. Recorded as context to inspect, not as a coverage assessment.Agent tooling
cap-agent-ui5-webuidescription revisedThe README has grown well past what the page carried, and the entry stated the capability with no source at all. Read on 2026-10-15: it serves a freestyle SAPUI5 TypeScript chat client same-origin from the CDS server against the services carrying @agent, renders a picker for more than one agent where switching starts a new conversation, speaks nothing but A2A as @cap-js/agents serves it, pins that package to exactly 0.9.1 and says to expect breakage on upgrade, and ships a scripted LLM because the bundled mock can never call an action and leaves an @agent.hitl gate unreachable. The dependency on @cap-js/agents is what the plugin is written against, so it is a required edge rather than a sentence.Agent tooling
cap-java/cds-aiprovides[llm-integration], description revisedThe 0.0.2-alpha coordinates are a fact about Maven Central and not a statement by the maintainer. capire's plugin list, read on 2026-10-15, says in SAP's own words that the Java version of the AI plugin is currently in alpha, which is the declaration a reader choosing between the two runtimes needs; it is quoted rather than paraphrased and the coordinates stay beside it.LLM integration
cap-llm-pluginprovides[llm-integration] revisedThe edge that names this entry's own home capability carried nothing: no sentence, no source, and no room for the comparison property the capability declared on 2026-10-15. The README at 1.5.1, re-read the same day, names the chat-completion method and the orchestration service's harmonised APIs, and both run through SAP AI Core, which is what the property states. response_streaming is left absent: the README's feature list says nothing about streaming, and absent is not no.LLM integration
capire/skillsflavors, provides revisedThe edge carried one source and no quote. Re-read both eval files on 2026-10-15: the fixture path, the expected-output field, the named assertions and the stack marker are now quoted, and the capability's two comparison properties are answered from the same sentences.Agent guidance
cds-agentsdescription, provides revisedcapability:agent-tooling declared four comparison properties on 2026-10-15. Both brings values rest on their own sentence — CAPToolkit is the raw-tool layer and the production default, CAPAgent a ready-made ReAct agent for demos and small apps — and the protocol is the one its own executor names as a client, not a protocol it serves. The state and approval properties are left out: the README says nothing about either.Agent tooling
com.sap.cds:cds-adapter-agentdescription, provides revisedcapability:agent-tooling declared four comparison properties on 2026-10-15. All four values are scoped to the java flavor, the only one this module states, and the last two are stated negatives rather than absences: capire states that conversation history sits in volatile memory and that @agent.hitl is not yet supported by CAP Java. The harness property is left out: neither page names an agent framework underneath the Java adapter.Agent tooling
DanKromp/skillOverflowprovides revisedThe entry's own prose said the collection covers UI5 and Fiori work and the edge cited only the total count. The UI5 pass needed to know what that coverage is, because this entry states no flavor and so answers in all of a door's flavors; the two rows name the skills the fallback rests on, which is what the capability's freestyle and web-components readings now cite.Agent guidance
Joule Studioecosystem, artifact type, links revisedThe browser builder and managed runtime do not establish a separately subscribed and bound BTP service. Keep CAP and BTP as served views: the product overview names CAP development, and the current SAP Help tutorial requires "An SAP S/4HANA system configured with an SAP BTP destination." The architecture chapter is titled "Building AI Agents with SAP Joule Studio on SAP BTP" while distinguishing the SAP-managed runtime from Bring Your Own Agent in a customer subaccount. The CLI link is backed by the current npm README, which now ships both joule and jl; its atlas record is revised in the same batch. The positive basis for web-tool is SAP’s description of a visual browser-based builder with no local setup. It identifies the hosted development interface, including provisioned access; it does not classify the runtime as an unbound or customer-hosted service.Agent tooling
LLM integrationcore coverage, coverage by flavor, framing by flavor, facets revisedTwo questions the options here answer differently and the page could not show. Which models an option reaches is the first fact a reader needs, because all but one of the CAP options are clients of SAP AI Core; whether the response can be streamed decides whether a chat surface is possible at all. Both are scoped to cap: the ABAP, UI5 and BTP options were not read for them in this pass.LLM integration
SAP Power for Kiroprovides, description revisedThe entry said it is packaged as a Kiro power and not how it gets there or which Kiro it needs; the README read on 2026-10-15 states both.Agent guidance
secondsky/sap-skillslinks, flavors, requires, provides, description revisedThe same correction as description.what_it_solves, on the edge that carries this artifact's answer to the capability, so the two do not state the repository's evidence model differently. The rewording also removes the two em dashes the prose scan reported in this field.Agent guidance
ui5-cap-ai-featuresprovides[llm-integration], requires[sap-ai-sdk-orchestration] revisedThe edge read as an unconditional prerequisite while this entry's own when_not_to_use already said the package is an optional peer. The README states it in one sentence, quoted now: a frontend-only install does not need it and a backend project installs it explicitly, which is the distinction a reader deciding what to add to package.json needs. The edge to the HTML5 Application Repository is untouched; nothing was read for it in this pass.LLM integration
Werkbankecosystem revisedThe project homepage describes "A small, curated shelf of MCP servers and SAP development skills." Its own catalog spans ABAP (ARC-1 and ABAP Cloud), CAP (CAP Upgrade), and UI5 skills; the workspace is not specific to one stack. This intake follows the maintainer’s explicit request after the September source sweep passed it over for lacking a workspace capability; that concern now exists as Agent workspaces. The served views describe which users the project-owned install catalog addresses. Werkbank provides the workspace; each selected connector or skill supplies the stack-specific behavior. No SAP implementation capability is attributed to Werkbank itself.Agent guidance
Wed 14
Adapting SAP Joule for Purchase Order Creation from an Existing Purchase RequisitionpublishedA custom Joule Agent and Joule Skill, built in Joule Studio, classic editionJoule Studio, classic editionThe low-code capability in SAP Build for custom Joule skills and Joule agents: skills call OData APIs through BTP destinations, agents get a model, instructions, tools and MCP servers, and both deploy to Joule.sap official, btp to extend SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp past its built-in Purchase Order display and change features: a buyer's single sentence naming a Purchase Requisition number becomes a created Purchase Order, with the skill wrapping the Purchase Requisition and Purchase Order OData V4 APIs as Action Packages reached through two destinations. The author anchors the agent's success condition to a PurchaseOrderNumber in the skill's output rather than an HTTP status code, and reports that the Purchase Requisition item structure does not map one-to-one onto the Purchase Order creation payload.Agent tooling
Agent access to your codenormative relevance revisedThe policy's agentic provision reaches every server that calls ADT for an agent; it was stated on arc-1 alone and as unsourced prose in several boundaries.Agent access to your code
LLM integrationcoverage by flavor revisedThe PromptInput page no longer carries the sentence this rested on. Read again on 2026-10-14 it states "The @ui5/webcomponents-ai package is under development and considered experimental - components' APIs are subject to change. Furthermore, the package supports Horizon themes only", with no version marker in it. The since-2.0 claim had no second source, so it goes rather than stand unsourced; the experimental state and the Horizon-only limit stay, in the words the page now uses, which are the words coverage_by_ecosystem.ui5 already quoted. The flavor's own assessment of who provides it was not redone, so assessed_at stands.LLM integration
Mon 12
Explaining SAP Joule for HR Business Users & Functional Consultants.publishedWritten for HR business users and functional consultants, this walks through how SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp is provisioned on SAP BTP and wired into SuccessFactors: the Joule instance sits in a BTP subaccount, SAP Build Work Zone is created alongside it, and Identity provisioningIdentity provisioningGetting users, groups and role assignments into every system that needs them, and out again when a person leaves, through provisioning jobs or SCIM APIs. Authentication answers who is calling one request; provisioning decides whether the user exists in that system at all.SAP only syncs users from SuccessFactors into Build Work Zone while Cloud Identity Services authenticates the launch through an IAS tenant. It lists five prerequisites for the connection — a BTP global account, a Joule entitlement, Cloud Identity Service and SuccessFactors admin access, and the right personas — and notes that running BTP's booster adds the Joule permission to the SuccessFactors user's profile.Agent tooling
@shahid.la/cds-db-nlquery-mcpprovides[mcp-servers], provides, requires revisedResolves the requested review findings while preserving the structured comparison values, runtime scopes and implementation restrictions.LLM integration
Agent access to your systemscore coverage, coverage by ecosystem, description revisedMaintainer requested complementary boundaries so a CAP bridge can connect system access and application MCP exposure, while implementation restrictions remain explicit. Domains, providers and task classifications are unchanged.Agent access to your systems
Sun 11
Agent-led test management: Hands-on lab with Joule in SAP Cloud ALMpublishedThe Test Management Assistant, a Joule capability in SAP Cloud ALM, worked through on project scenarios: scoping requirements, detecting coverage gaps and generating test cases with AI. The edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, which the assistant runs on; SAP Cloud ALM has no entry here, and the atlas's testing concern, proving a service's model and handlers, is not this session's test management. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Christina Pickhardt, Daniel Lorenz, Niclas Weidner and Tobias Keller, written here from SAP's abstract; the recording is not yet published.Agent tooling
AI-accelerated RISE with SAP migration with the system transition workbenchpublishedSAP Joule for Consultants and the RISE with SAP system transition workbench in a move to SAP S/4HANA Cloud Private Edition: readiness assessments, migration workflows and the SAP tools involved. The edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, of which Joule for Consultants is a part; the system transition workbench has no entry here, and Platform migrationPlatform migrationMoving an application, integration or database from one platform to another: assessing what exists, converting what tooling supports, and adapting what cannot carry over. Language-level compatibility is a separate concern from moving the platform around an application.SAP and community, unassessed covers applications leaving older BTP platforms, not an ERP system's move. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Daniel Funkert, Kristin Aleksandrova, Mirja Kempin and Moritz Gysler, written here from SAP's abstract; the recording is not yet published.Agent tooling
AI-assisted full stack development using model context protocol serverspublishedMCP servers in Visual Studio Code used to configure, query and change a full-stack application built with CAP, CDS and ODataODataExposing data and operations through OData, including the service model, metadata and protocol versions clients require. Version differences affect which clients can consume a service and which query features they can use.SAP and community, narrow by design: the agent access to your codeAgent access to your codeLetting a coding agent read the project or the system you actually have, reach its model, its objects and its checks, and act on it. In file-based environments that works out of the box; complex systems need dedicated access capabilities. Whatever the environment, the agent also needs project- and framework-specific context, so it understands the thing in front of it rather than guessing from what it remembers of its training data. The transport is incidental: an MCP server, a language server or a CLI answer the same question, and what differs between them is how much of the real thing the agent can see. Distinct from MCP servers, which is a protocol adapter on your own running service, and from agent guidance, which is knowledge handed over as files rather than read from the thing itself.SAP and community, unassessed concern, a coding assistant reading and changing the project it works in. The abstract names no server, so neither @cap-js/mcp-server@cap-js/mcp-serverSAP's MCP server for CAP development, run as cds-mcp: search_model searches the project's compiled CDS model, search_docs searches the CAP documentation indexed as embeddings on the developer's own machine.sap official, cap nor any other is attached, and it does not say which changes are made. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Sergio Guerrero, written here from SAP's abstract; the recording is not yet published.Agent access to your code
AI-enhanced analytics with SAP Business AI PlatformpublishedSAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp data products joined to an ontology, a semantic layer the abstract says is supported by the Model Context Protocol, and read from Joule Work (SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp) and SAP Analytics CloudSAP Analytics CloudSAP's SaaS front end for analytics: business intelligence, planning and predictive in one product, and the place a Datasphere analytic model is meant to end up being read.sap official, btp: that is the architecture SAP's abstract states for its AI-enabled analytics. The abstract names the parts and not how the semantic layer is modelled or what an analytics developer builds against. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Hacen Benkhedah, Joaquin Recio HuertasJoaquin Recio Huertasgave 1 talk, contributed to 3 entries, Matilda Hyka and Oliver Huth, written here from SAP's abstract; the recording is not yet published.Agent tooling
Show 31 more
Behind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain ModelspublishedThe 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp with SAP Document AISAP Document AIExtracts header fields and line items from invoices, payment advices, purchase orders and custom document types, as structured data over a REST API — the extraction is the service's, the schema can be yours.sap official, btp. 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 modelsPredictive modelsTraining, deploying and calling a model that predicts a value from tabular business data: a classification, a regression, a forecast. Distinct from LLM integration, where a language model generates text, even where both run on the same service.SAP only 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.LLM integration
Build business differentiation with SAP AI CorepublishedSAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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 CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp 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 KnaackDavid Knaackgave 1 talk, contributed to 13 entries, Franziska Dobrigkeit, Hadi Hares and Jonas Israel, written here from SAP's abstract; the recording is not yet published.LLM integration
Build your first agent with Joule Studio in a pro-code waypublishedThe command line interface of Joule Studio, which the atlas holds as @sap/joule-work-dev-cli-early-adopters@sap/joule-work-dev-cli-early-adoptersjl, the pro-code CLI of the new Joule Studio: a solution is a folder with a solution.yaml and typed assets, validated, built into a zip and deployed to Joule Studio's managed runtime, with Claude Code or OpenCode wired in over MCP. Early Adopter Care.sap official, btp, carries an agent from a structured intent through generated product requirements documentation and wired APIs to a deployment on Joule Studio's SAP-managed runtime, in one guided flow. SAP's abstract names the stages of that pipeline and promises working code at the end; what the generated requirements and APIs look like is not described. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Charan Ravikumar, Evgenii Skrebtcov, Maria Kondratyeva and Simon Endres, written here from SAP's abstract; the recording is not yet published.Agent tooling
Building custom Joule Agents with SAP Knowledge GraphpublishedCustom Joule Agents built in a hands-on with SAP Knowledge Graph and Joule Studio: discovering APIs from a user's intent, grounding an agent's answers in business context, and integrating data products for SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp. The agents are SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp's; the Knowledge Graph is not an atlas entry, and the abstract does not say which Joule Studio edition the exercises use. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Jan Portisch, Lucas Kiesow, Pavithra G K and Rafael Martin, written here from SAP's abstract; no recording is announced.Agent tooling
Building enterprise agent extensions with the Joule Studio solutionpublishedExtending SAP's standard agents with third-party integrations and business actions in Joule Studio: agents that run a process across systems, call an external service, put an approval step in the middle and bring the result back into the business context, which is what SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp's agents do and what Joule Studio, classic editionJoule Studio, classic editionThe low-code capability in SAP Build for custom Joule skills and Joule agents: skills call OData APIs through BTP destinations, agents get a model, instructions, tools and MCP servers, and both deploy to Joule.sap official, btp is in the atlas. The abstract names Joule Studio without saying which edition the exercise uses, and lists outcomes rather than the steps built. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Charan Ravikumar, Jacob Hornberger, Maria Kondratyeva and Michael Zadikowitsch, written here from SAP's abstract; the recording is not yet published.Agent tooling
Connecting AI agents to the ABAP RESTful application programming modelpublishedJoule Studio, classic editionJoule Studio, classic editionThe low-code capability in SAP Build for custom Joule skills and Joule agents: skills call OData APIs through BTP destinations, agents get a model, instructions, tools and MCP servers, and both deploy to Joule.sap official, btp connects Joule Agents to applications built with the ABAP RESTful application programming model through actions and skills, calling the OData services those applications expose their business objects through: the tools an agent may call, which is the agent toolingAgent 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.SAP and community, unassessed concern seen from the ABAP side. The abstract promises alternative integration patterns and does not name them. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Leon Karlau, written here from SAP's abstract; the recording is not yet published.Agent tooling
Discover fast-track implementation of SAP Cloud ERP with AIpublishedSAP's implementation practice for SAP S/4HANA Cloud Public EditionSAP S/4HANA Cloud Public EditionSAP's cloud ERP, run by SAP as software as a service. For the things here it is the business system a side-by-side application on BTP reads from and writes to over its published OData APIs. and the AI-driven tooling SAP says is changing stages of a project, with faster and more predictable deployments, less manual effort and lower risk as the stated outcomes. The abstract names the product, an external here, and no tool; the edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp because SAP's AI tooling for implementation in the sibling sessions TM109, TM263 and TM265 is Joule for Consultants, and whether this session shows it is not stated. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Anurag Barua and Khaled MUSILHY, written here from SAP's abstract; the recording is not yet published.Agent tooling
Discover how SAP Joule for Consultants transforms cloud implementationspublishedA customer's use of SAP Joule for Consultants in a cloud transformation: grounding project data, running fit-to-standard workshops faster and keeping teams aligned, followed by the technical architecture behind those capabilities and an early road map preview on feasibility for developers and enterprise architects. The edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, of which Joule for Consultants is the offering for consultants and has no entry of its own here; the abstract leaves the customer as a placeholder and the architecture to the session. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Philipp Kandziora and Yi Hsuan Lin, written here from SAP's abstract; the recording is not yet published.Agent tooling
Enriching AI models with SAP AI Core in SAP Business Data CloudpublishedThe integration between SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp and SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, 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.LLM integration
Experience core foundational capabilities of SAP Cloud ERPpublishedGuided exercises in SAP S/4HANA Cloud Public EditionSAP S/4HANA Cloud Public EditionSAP's cloud ERP, run by SAP as software as a service. For the things here it is the business system a side-by-side application on BTP reads from and writes to over its published OData APIs., which SAP calls the execution backbone of the Autonomous Enterprise: validating AI capabilities against master data for industry and domain needs, generating AI-driven KPIs and reporting summaries. The product is an external here and the abstract names no AI feature by name; the edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, SAP's AI layer across its applications and the one entry the AI capabilities of SAP Cloud ERP attach to, which the abstract itself does not name. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Akshat Kharial, Ankush Thareja and Nises Soni, written here from SAP's abstract; the recording is not yet published.Agent tooling
From intent to extension: Joule and the future of solution extensibilitypublishedHow Joule turns natural-language intent into extensions across SAP Autonomous Suite: intent-based agent extensions, enriching the agents SAP delivers, packaging options for partners and what SAP calls a harmonised extensibility experience. The edges are to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, which does the translating, and to ExtensibilityExtensibilityLetting a customer change delivered behaviour without modifying it — key-user fields and logic, developer extensions, and the released extension points that make either safe across an upgrade.SAP and community, unassessed, the concern; the abstract names the directions and no feature that ships today. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Amitha Kamath, Oren Shatil and Richard Kuba, written here from SAP's abstract; the recording is not yet published.Agent tooling
Generate agentic workflows using SAP-managed n8n in Joule StudiopublishedSAP-managed n8n inside Joule Studio generates a workflow from a business intent a developer states, and the workflow is then tested and deployed, consuming line-of-business application APIs, events and agents in SAP Business AI Platform: process automationProcess automationModelling and running a business process: the process flow, the forms people fill in, decision tables, bots for repetitive steps, and dashboards over the instances that run. Starting a process from an application and reacting to it is workflow integration, and the screen a person approves a task on is task and approval UIs.SAP only with the workflow generated from intent, and agent toolingAgent 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.SAP and community, unassessed where the workflow calls agents. The generated workflow sends notifications to the Joule Work mobile app of SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, to Microsoft Teams or to Slack. SAP's abstract names the pieces and not how the generation or the n8n hosting works. A two-hour hands-on TechEd 2026 session (Tuesday 27 October, Berlin), presented by Rama Sulakshani Murari, Rumen Dimitrov, Seshadri Sreenivas Ramanarayanan and Venugopal Chembrakalathil, written here from SAP's abstract; the recording is not yet published.Agent tooling
Get to know our AI-enhanced mobile apps across the Autonomous EnterprisepublishedA demo of the Joule Work mobile app, part of SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, and selected SAP mobile apps, showing the mobile AI features meant for using SAP Autonomous Suite on the go, followed by the mobile AI patterns and how to build your own Mobile appsMobile appsBuilding a native iOS or Android app over business data: onboarding, offline sync against an OData service, device features, and the client that runs on the phone. Distinct from a web app opened in a phone's browser; operating a web app with a finger is touch operation.SAP and community, unassessed with SAP Business AI Platform. The abstract names the apps and the patterns and states no feature or tool, so what building your own involves is not said. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Sandeep Tetali and Thilo Berndt, written here from SAP's abstract; the recording is not yet published.Agent tooling
Hands on SAP Document AI: Next-generation intelligent document processingpublishedSAP Document AISAP Document AIExtracts header fields and line items from invoices, payment advices, purchase orders and custom document types, as structured data over a REST API — the extraction is the service's, the schema can be yours.sap official, btp configured and run by hand: schema design, splitting and classifying documents, enriching the extracted data and custom prompting are the exercises SAP's abstract names. Document extractionDocument extractionGetting structured data out of a document somebody sent you — an invoice, a purchase order, a scanned form — instead of having a person key it in. The mirror image of document output, and a different problem from reading a service: the input is a file, the shape is unknown until something reads it, and the answer arrives with a confidence rather than a guarantee.SAP only from the configuring side, with the schema the participant's own; which document types or models the exercises use is not stated. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Christoph Lenschow, Tobias Weller and Tomasz Janasz, written here from SAP's abstract; no recording is announced.Document extraction
How SAP Document AI brings agentic intelligence to business documentspublishedSAP Document AISAP Document AIExtracts header fields and line items from invoices, payment advices, purchase orders and custom document types, as structured data over a REST API — the extraction is the service's, the schema can be yours.sap official, btp as SAP's abstract now describes it: composable, agent-ready skills for schemaless extraction, classification and summarisation of business documents, so Joule Agents can read and act on unstructured content, plus new document foundation models and agentic validation in its workflow engine. That widens document extractionDocument extractionGetting structured data out of a document somebody sent you — an invoice, a purchase order, a scanned form — instead of having a person key it in. The mirror image of document output, and a different problem from reading a service: the input is a file, the shape is unknown until something reads it, and the answer arrives with a confidence rather than a guarantee.SAP only past the fixed-schema fields the atlas entry records; the abstract names the features and not their release state. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Dheeraj Diwan, Soeren Leibach and Tomasz Janasz, written here from SAP's abstract; the recording is not yet published.Document extraction
Inside Joule Studio runtime: Agent deployment and integrationspublishedJoule Studio runtime from the inside: the tools and services SAP manages to deploy, integrate, run, extend and operate agents at scale, and the integrations through the agent gateway and SAP S/4HANA Cloud Private Edition. The edge is to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, whose agents the runtime runs; the atlas reaches that runtime through @sap/joule-work-dev-cli-early-adopters@sap/joule-work-dev-cli-early-adoptersjl, the pro-code CLI of the new Joule Studio: a solution is a folder with a solution.yaml and typed assets, validated, built into a zip and deployed to Joule Studio's managed runtime, with Claude Code or OpenCode wired in over MCP. Early Adopter Care.sap official, btp, which deploys a solution to it, and the abstract names neither the CLI nor a service by name. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Andre Lamego and Jens Huesken, written here from SAP's abstract; the recording is not yet published.Agent tooling
Joule and related AI offerings from SAP: One platform, many systemspublishedSAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp run across dozens of SAP systems: the SAP for Me portal, orchestration across systems, configuration and credential management, monitoring and tenant isolation are the topics SAP's abstract lists. It stays on the operating side and says nothing about building on Joule. A TechEd 2026 session (Wednesday 28 October, Berlin; also JW301V, virtual), presented by Lukas Lochner, Marvin Klaus and Mathias Rup, written here from SAP's abstract; the recording is not yet published.Agent tooling
Joule and SAP Knowledge Graph: Context-aware AI across SAP solutionspublishedThe catalogue carries RA107's abstract under this title, and what it describes is SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp as the management and orchestration layer of an AI architecture: extending Joule Agents in SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp, 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.LLM integration
Joule without walls: From personal skills to enterprise interoperabilitypublishedSAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp connects outward over two protocols, A2A and MCP, which SAP's abstract names as the foundation of its open ecosystem, with Joule Assistants as composable agents and extensibility built in. The session draws the line between a personal extension of Joule and one that needs enterprise governance; the abstract does not say where that line falls. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Mathis Boerner and Thomas Mueller, written here from SAP's abstract; the recording is not yet published.Agent tooling
OData to outcomes—Build AI-enabled SAP Fiori apps using SAP Fiori elementspublishedA Fiori elements app built through SAP's MCP servers: the OData V4 service comes from the MCP server for RAP, which the atlas holds as the ADT MCP ServerADT MCP ServerSAP's own ADT MCP server, and not a package: a preference inside ABAP Development Tools for VS Code that starts a local HTTP MCP server on a port you choose.sap official, abap, or from @cap-js/mcp-server@cap-js/mcp-serverSAP's MCP server for CAP development, run as cds-mcp: search_model searches the project's compiled CDS model, search_docs searches the CAP documentation indexed as embeddings on the developer's own machine.sap official, cap for CAP, and the UI from @sap-ux/fiori-mcp-server@sap-ux/fiori-mcp-serverSAP's Fiori MCP server, run as fiori-mcp, letting a coding assistant create and edit Fiori applications directly rather than describing the steps.sap official, ui5, with annotations and actions added before the app is tied to SAP's AI features. Agent access to your codeAgent access to your codeLetting a coding agent read the project or the system you actually have, reach its model, its objects and its checks, and act on it. In file-based environments that works out of the box; complex systems need dedicated access capabilities. Whatever the environment, the agent also needs project- and framework-specific context, so it understands the thing in front of it rather than guessing from what it remembers of its training data. The transport is incidental: an MCP server, a language server or a CLI answer the same question, and what differs between them is how much of the real thing the agent can see. Distinct from MCP servers, which is a protocol adapter on your own running service, and from agent guidance, which is knowledge handed over as files rather than read from the thing itself.SAP and community, unassessed on both the service and the UI side; SAP's abstract names the servers and the steps and says nothing about which AI features or which agent host. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Benedikt Schoelch, Sebastian Steinhauer, Sebastian Werner and Stefan EngelhardtStefan Engelhardtgave 1 talk, contributed to 5 entries, written here from SAP's abstract; the recording is not yet published.Agent access to your code
SAP AI Core deep dive: Models, agents, and business context at scalepublishedSAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp 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 CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp, 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.LLM integration
SAP Joule for Consultants: Unified knowledge for requirements and designspublishedFit-to-standard analysis as a consultant on a cloud transformation project: connecting an organisation's data to SAP Joule for Consultants through SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, getting answers from SAP knowledge and that content, then building an expert, loading project files and running guided prompts. The edges are to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, 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.Agent tooling
SAP-RPT and TabPFN: Get started with tabular foundation modelspublishedTabular 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 CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp with a workflow built on tabular orchestration and connected to the participant's own data for real-time predictions. A predictive modelsPredictive modelsTraining, deploying and calling a model that predicts a value from tabular business data: a classification, a regression, a forecast. Distinct from LLM integration, where a language model generates text, even where both run on the same service.SAP only 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.LLM integration
SAP’s compositional design system: Craft enterprise UIs with AI on the flypublishedSAP's compositional design system is the engine behind the generated interface in Joule Work, the front of SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp: SAP's abstract says AI assembles the UI at runtime from primitives and composites under a body of design knowledge, inside a brand-safe design system, and that the session covers the architecture that keeps the result consistent. A third shape of Generative UIGenerative UIPutting an interface inside an agent conversation: a tool result or an agent's reply shown as controls a person can work in, where text would have been. Two things go by the name. A prebuilt web UI that an MCP tool points to and the host renders in a sandboxed iframe, which the MCP Apps extension specifies, is selected by the model and not generated by it; a user interface rendered from a stream of JSON objects the agent sends, which the A2UI specification describes, is. Generating an application's source at design time is generators.Unmapped beside the two the capability describes, since here the model composes the interface at runtime. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Philip Miseldine and Sophia Levens, written here from SAP's abstract; the recording is not yet published.Generative UI
Ship your own sandboxed AI operations agent to Kyma in two hourspublishedAn operations agent built and then broken on purpose: the abstract has participants deploy a reasoning agent to SAP BTP, Kyma runtimeSAP BTP, Kyma runtimeA fully managed Kubernetes runtime on SAP BTP, based on the open-source project Kyma, where extensions to SAP solutions run as containerised microservices and serverless Functions.sap official, btp, connect it to SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp, give it observability over the runtime and cause a failure for it to diagnose, the operations automationOperations automationActing on a running landscape without someone at the console: an alert routed to where a person or a system will pick it up, and a command that troubleshoots or remediates when it arrives. Logging, telemetry and health checks observe; this acts on what they report. Running an application's own recurring work is job scheduling.SAP only 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 LechnerChristian Lechnergave 2 talks, contributed to 12 entries, Piotr Tesny, Thorsten SandfuchsThorsten Sandfuchsgave 3 talks, contributed to 3 entries and Vipin VijayKumar, written here from SAP's abstract; the recording is not yet published.LLM integration
The road map for SAP Joule for Consultants—your go-to SAP consulting toolpublishedSAP's road map for SAP Joule for Consultants, which the abstract describes as becoming the tool for SAP software projects: landscape awareness and secure system connectivity, so that Joule understands an organisation's SAP environments and gives project teams more contextual guidance. The atlas holds no entry for Joule for Consultants, so the piece enters on SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, the product it is an edition of; the abstract states outcomes and no feature or date. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Natalie Han and Sachin Kaura, written here from SAP's abstract; the recording is not yet published.Agent tooling
Transform business data into AI-supported insightspublishedBusiness metrics turned into insights, narratives and recommendations by SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp's agents, with People Intelligence, the SAP Snowflake solution extension for SAP Business Data Cloud and SAP Analytics CloudSAP Analytics CloudSAP's SaaS front end for analytics: business intelligence, planning and predictive in one product, and the place a Datasphere analytic model is meant to end up being read.sap official, btp connected in SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp. The abstract names what is connected and what comes out, and does not say what the exercise builds or where the Snowflake extension sits in it; People Intelligence and the extension are not atlas entries. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Babacar Toure, Maximilian Paul Gander, Neetha Pucknat and San Tran, written here from SAP's abstract; the recording is not yet published.Agent tooling
What a Second Document AI Workshop Taught Me About GovernancepublishedFrom questions raised at a second SAP Document AISAP Document AIExtracts header fields and line items from invoices, payment advices, purchase orders and custom document types, as structured data over a REST API — the extraction is the service's, the schema can be yours.sap official, btp workshop: the retention period for extracted data is a setting in the service's administration rather than a fixed property, with the source file deleted after processing and the decommissioning period for the extracted data configured to the customer's own policy. It also draws a boundary readers kept merging: Document AI extracts across languages but does not translate, so turning a document into a reviewer's own language is a separate step, pointing on BTP at SAP Translation HubSAP Translation HubSAP's translation service for software texts and documents, drawing on repositories of verified and company translations and on machine translation by SAP's neural MT or large language models.sap official, btp.Document extraction
What’s next for agentic analytics and planning in SAP Business Data CloudpublishedWhat is next for agentic analytics and planning in SAP Business Data CloudSAP Business Data CloudSAP's umbrella over the data estate: installed intelligent content and data products, a governed catalog they are published through, and a path out to SAP Databricks.sap official, btp: SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp's agents automating insight delivery, analysis, narrative generation and modelling tasks. A road map session; the abstract names the four kinds of task and no agent or date. A TechEd 2026 session (Tuesday 27 October, Berlin; also DA806V, virtual), presented by Kristian Ruemmelin, written here from SAP's abstract; the recording is not yet published.Agent tooling
What’s next for the core platform capabilities of SAP Business AI PlatformpublishedA preview of the operations layer beneath SAP Business AI Platform: selected road map highlights across Joule Studio runtime, Cloud Identity ServicesCloud Identity ServicesIdentity Authentication and Identity Provisioning as one tenant: the login, the user store or the federation to a corporate identity provider, and the provisioning of users into whatever sits behind it.sap official, btp and SAP Cloud LoggingSAP Cloud LoggingAn instance-based observability service built on OpenSearch that stores and analyses logs, metrics and traces from Cloud Foundry, Kyma, Kubernetes and other runtime environments.sap official, btp, on how enterprise AI is governed and run. The edges are to the two named services and to SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp, whose agents the Joule Studio runtime runs; the abstract names the three areas and no highlight. A TechEd 2026 session (Tuesday 27 October, Berlin; also XP825V, virtual), presented by Andre Lamego and Jens Huesken, written here from SAP's abstract; the recording is not yet published.Agent tooling
Zero token architecture for Joule AgentspublishedA pattern for SAP JouleSAP JouleSAP's unified AI engagement layer across SAP applications: Joule Work is where a user expresses intent, Joule Assistants coordinate agents across business functions, and Joule Agents carry out the tasks, provisioned on BTP as a formation against SAP Cloud Identity Services.sap official, btp's agents in which an agent maps the solution path once, solves the problem, generates reusable code or configuration and validates it, and later requests reuse that output, so discovery is done by the model and execution is repeatable. The abstract states the pattern as an idea and names no Joule component and no case it was tried on. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by EDGAR ADRIAN MARTINEZ ARCE, written here from SAP's abstract; the recording is not yet published.Agent tooling
Fri 9
cap-mtx-scaffoldadded to the atlasAgent skill for CAP multitenancy scaffoldingAgent guidance
sap-cx-developer-companionadded to the atlasAgent skill for SAP Customer Experience APIs, CDS and errorsAgent guidance
Agent access to your systemsentry revisedSplit out of MCP servers at the maintainer's decision. That capability named a protocol and carried two concerns: exposing what you built to agents, which stays there under a name that says so, and giving agents a way into an SAP system you run, which is this one. Thirty providers moved with their own sentences; the Commerce and SuccessFactors slots moved with them. Named beside agent access to your code, its development-time sibling.Agent access to your systems
Agent guidanceecosystems revisedSAP Commerce opened as a product door (docs/concepts/product-doors.md, ADR-0033) and sap-commerce-skillsap-commerce-skillAn agent skill for SAP Commerce Cloud 2211-jdk21.1 and later: 21 reference guides, 58 code templates and three shell scripts, installed through the skills CLI.independent, commerce entered behind it with no tile to sit under. Packaged knowledge for the Commerce type system, service layer, ImpEx and OCC API is the same concern the node already holds on four doors, so the key was added rather than the capability forked.Agent guidance
Show 6 more
AI-native North Star architecture — Platform Layerparts revisedFilled from SAP's own pages at the maintainer's request (docs/concepts/product-doors.md was the occasion; 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.Agent tooling
cap-mcp-bridgeprovides revisedThe concern it answers is reaching into an SAP system from outside, split out of MCP servers on this day; the sentence on the edge is unchanged.Agent access to your systems
cap-mtx-scaffoldentry revisedA new repository in the SAP AI Skills Library registry snapshot of 2026-10-09, registering one skill at skills/cap-mtx-scaffold. Written from the repository's own README; hard rule 7: skills are indexed, never authored here. No flavor is stated: the repository badge reads SAP CAP Node.js and the toolkits it names are Node ones, but no sentence states a flavor, so the entry says nothing rather than inferring node.Agent guidance
Generative AI on SAP BTPparts, roles, paths revisedThe 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.LLM integration
Integrating and Extending Jouleparts revisedFilled 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.Agent tooling
sap-cx-developer-companionentry revisedA new repository in the SAP AI Skills Library registry snapshot of 2026-10-09, registering one skill at skills/sap-cx-developer-companion. Written from the repository's own README and SKILL.md; hard rule 7: skills are indexed, never authored here. Placed behind the SAP Commerce door because the CX API explorer and the error resolver are written against Commerce Cloud OCC and Sales and Service Cloud, with CAP and BTP as served doors for the CDS half.Agent guidance
Thu 8
cap-bp-ragadded to the atlasEvent-driven RAG app with CAP, Cloud Integration and SAP HANA Cloud
cap-embedding-functionadded to the atlasCAP service computing embeddings with HANA Cloud vector_embedding
Sun 27
@cap-js/processadded to the atlasStarts and manages SAP Build Process Automation processes from CAPWorkflow integration
Agent toolingcore coverage, facets revisedA role in a design is filled from evidence that an option speaks what the fixed part exposes, and that join runs over one protocol vocabulary (docs/concepts/design-roles-and-interfaces.md, P2). Declared here so options can state it; absent stays "does not say".Agent tooling
Retrieval-augmented generationcore coverage revisedcapire audit 2026-09-27, link-only pages read a fourth time: vector embeddings are one of the three things SAP frames as CAP's native AI support, in the one sentence the section's index says of its own.Retrieval-augmented generation
SAP Document AIinterfaces revisedAn interface may be named and stays a field (docs/concepts/design-roles-and-interfaces.md §3.2, P7): the hub's catalogue states the two APIs' titles, versions and states, and SAP's Help pages name the channels and the workspace, so a design's arrow can say which surface it lands on and a reader has the page to open. The inbound channels read mail: SAP's Help page names mail as the only channel type, so the SharePoint folders the reference architecture mentions are its claim and not the maker's. No status is entered: the hub's state is a crawled claim reported beside the interface.Document extraction
Show 1 more
SAP Document AIparts, areas, edges, roles, edges[client to docai] revisedThe ingestion page links the upload operation of document_information_extraction_api_v2 as the API-based integration, and the service now names that surface (docs/concepts/design-roles-and-interfaces.md §3.2, P7), so the arrow says which API it lands on and wears its protocol.Document extraction