onedevatlasBeta
Browse the atlas
AllCAPUI5ABAPBTP
NewSAP Business Technology Platform, also named SAP Business AI Platform

New in BTP/BAIP

7 days30 days90 daysAll time
In the last 30 days
24added to the atlas66new pieces of content150revisions
Change
Kind
Origin
Domain: 2
Clear all
240 changes
DayCapability
Domain AI & AgentsDomain Developer Experience

Today
15 changes
BASEnvSyncadded to the atlasCarries home-directory dotfiles from one BAS dev space to anotherIDE extension,
HANA SQL NOTEBOOKS in SAP BUILD / Business Application Studio(BAS) / Visual Studio CodepublishedWalks through SAP HANA SQL Notebooks, a .notebook file opened inside a dev space of SAP Business Application Studio (also reached from SAP Build and Visual Studio Code), that mixes CODE and MARKDOWN blocks and needs the project's mta and hana facets added first with cds add. A CODE block's connection-management mode uses a '#' syntax to list, select and show the active SAP HANA connection, drawn from the HANA Database Explorer's saved connections or the project's own Cloud Foundry connection, so any valid SQL statement can then run against the project's HDI container.Blog,
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 Studio 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 service (XSUAA), and mbt build packages the app for deployment to the SAP BTP, Cloud Foundry Runtime. The skill reaches the deployed OData API through the SAP Destination service, 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.Blog,
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.Capability,
Show 11 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.Capability,
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.Capability,
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.Capability,
Agent workspacescore coverage revisedReassessed against the graph (check:capabilities): Joule Work is a sap-official provider serving BTP, so the core is present; the note's absence claim is dropped.Capability,
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.Capability,
Editor supportcore coverage, coverage by ecosystem revisedReassessed against the graph (check:capabilities): the providers behind the UI5 door are SAP's (UI5 Language Assistant, and SAP Build Code and SAP Web IDE Full-Stack, which serve ui5). The community SAPUI5 Extension is an entry in the graph but has no provides edge to this capability.Capability,
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.Capability,
Predictive modelscore coverage revisedReassessed against the graph (check:capabilities): the note explained the state by the batch it was written from and counted repositories; it now names the kinds of SAP service that have since arrived. The state stays core-only: both are sap-official services on the btp door.Capability,
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.Capability,
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.Capability,
Tool governancedescription, core coverage, coverage by ecosystem, framing by ecosystem, coverage by flavor revisedReassessed against the graph (check:capabilities): a count of providers removed.Capability,
Yesterday
1 change
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.Capability,
Sat 24
3 changes
btp-agentadded to the atlasLangGraph agent and UI5 chat screen over four BTP MCP serversSample,
SAP-samples/hana-cli-claude-pluginadded to the atlasClaude Code plugin registering hana-cli's MCP serverMCP server,
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.Blog,
Fri 23
4 changes
Cloud Integration with Document AIpublishedWalks through connecting Cloud Integration to SAP Document AI: 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.Blog,
BTP MCP Serverserves ecosystems revisedThe tag came in with the entry on 2026-09-10 and nothing sourced it: the README names BTP Core Services and the proxy it runs on, never CAP. It read as a routing leftover from when the MCP servers capability lived on the CAP door; the entry stays on BTP, its home.MCP server,
hana-mcp-serverserves ecosystems revisedThe tag came in with the entry on 2026-09-10 and nothing sourced it: the README names HANA and no CAP stack. Removed with the other unsourced tags from that sweep; the entry stays on BTP, its home.MCP server,
odata-mcp-proxyserves ecosystems revisedThe tag came in with the entry on 2026-09-10 and nothing sourced it: the README describes a config-driven proxy on BTP Cloud Foundry and names no CAP stack. Removed with its sibling configs; the entry stays on BTP, its home.MCP server,
Tue 20
1 change
What an AI infra engineer sees when opening SAP's AI stack (1/3): the model gatewaypublishedA first look at SAP AI Core's Generative AI Hub from someone who builds gateways outside SAP for a living: the orchestration service harmonizes provider calls onto one API (a model name string switches providers, and SAP Note 3437766 carries the current model list, token rates and deprecation dates), runs a fixed, non-reorderable module pipeline — templating, masking through SAP Data Privacy Integration, grounding, content filtering, then the model call — and retries down an ordered fallback list whose entries can each carry their own model and rules. It places @sap-ai-sdk/orchestration among the official JavaScript, Java and Python SDKs, and notes SAP's own LiteLLM provider as a way to put a different gateway in front of it.Blog,
Mon 19
19 changes
🟣 AI Eating Brains! How I Fed Mine to Joule Work DesktoppublishedDevtoberfest 2026 session AI-22. Mathias Kemeter connects his Obsidian note vault to Joule Work Desktop with VaultGate, a local HTTP MCP server he wrote in his spare time because the desktop's sandbox accepts HTTP MCP servers and not stdio ones, and because he wanted the vault reached through Obsidian's own command line rather than by direct file access. The demo builds a Space of management tasks from notes and mailbox together, has the assistant pick up a conventions file in the vault without being told where the reporting rules are, finds a conflict the notes never name by semantic search over local embeddings, and appends a task to a sprint note behind a write confirmation, which is where the edges to Joule Work and Agent workspaces hold. The second half is about the guardrails he had AI choose for the project it then had to live inside: tests and coverage, type safety, static checks, dependency and secret scanning, blocking on commit, on push and in CI.Talk,
🟣 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 Core, a GPT-5 mini model, an orchestration flow template that configures data masking, input and output filtering and translation into the user's logged-in language, then prompts with a grounding query over five companies' return-policy documents — and consumes it from an ABAP report through the ABAP AI SDK, which calls the orchestration API and returns the summary as JSON. Two newer pieces follow: SAP RPT, the relational pre-trained transformer for tabular prediction, called with context rows and query rows and answering with a confidence value and no training step; and system-triggered agents, where an application job in the ABAP system starts a billing-creation agent that reaches S/4HANA OData APIs as tools through the agent gateway with principal propagation. The closing availability matrix states the generative AI capabilities for on-premise and private cloud from the 2021 release, with SAP notes to implement on lower ones.Talk,
🟣 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 Core team gives the reasons an AI application ends up on more than one model — a model down at the hyperscaler, a data centre that is not allowed to run it, a version being deprecated — and runs a joke app that answers from Gemini 2.5 Flash in EU10 and from Claude 4.5 Haiku in Asia-Pacific. The walk through AI Core's parts is where the edges hold: prompts kept as templates in the prompt registry, imported through the launchpad and the APIs or synced as YAML from a git repository (Prompt management); the evaluation service scoring one prompt across up to four models per run on built-in or model-as-judge metrics, and the prompt optimizer generating variants against one metric (Agent evals); and the orchestration service harmonising the providers behind one message format with a priority-sorted fallback list (LLM integration). The session also states where a metric has to be designed rather than picked: an exact-JSON match scores an email generator at zero, so the joke app's custom metric judges topic and family-appropriateness instead.Talk,
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 Studio, 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.Talk,
Show 15 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 reading an OpenUI5 sample app and converting it to TypeScript, mcp-sap-docs grounding Terraform files for a BTP subaccount the presenter had not written before, and arc-1 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 Zeis gives for servers written for internal use: keep them read-only, because what the agent is short of is context.Talk,
Be the First to Understand Joule Work's Agentic ThinkingpublishedA Devtoberfest 2026 session on the agent harness behind agentic thinking in Joule Work: 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 Studio, 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.Talk,
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 Cloud and SAP BTP, open-sourced in full, and the half of the session that places it here is how its content reaches an agent: every tutorial is also served as markdown, a coding agent is detected and given that version instead of the HTML, a well-known agent card advertises what the site offers, and SAP Developers MCP answers questions about tutorials, news and a reader's own completion history in Claude Code and Joule Desktop, over OAuth or a personal access token. Behind the answers sit two things working together: a knowledge graph in the HANA database over 1400 tutorials and 11,000 concepts, and SAP AI Core for the Joule interactions and the embeddings, with the agent harness written for the site rather than taken off a shelf. Where neither MCP nor A2A is available, the same content is published as skills.Talk,
Building Agentic Workflows with n8n in Joule StudiopublishedA Devtoberfest 2026 session, JS-31, on SAP-managed n8n inside Joule Studio, shown as a labs preview on a blocked-invoice scenario: a solution made of assets, an intent refined by the web agent into requirements and then a specification, and the generated workflow opened in the n8n editor that Joule Studio connects to its own n8n tenant, with the generated files committed through GitHub. The nodes carry the other edges — the human-in-the-loop node is built on SAP Task Center, and SAP AI Core is where model providers are configured centrally instead of per developer. It ends in Joule chat, where the approval task the workflow created is listed, opened and completed.Talk,
Building Code-Based AI Agents on the BAIPpublishedA Devtoberfest 2026 session on writing the agent yourself rather than configuring one, which is the agent tooling edge: an agent is a model with tools, skills, memory and context around it, and the session reads the code of one built in CAP as a LangGraph state graph, with an agent node that calls the model, a tools node holding the MCP clients, and the edge between them looping until no tool is needed. It then shows the shorter route, a CDS service annotated for the agent protocol with its instructions and skills in an agent.md file. SAP AI Core carries both, with the CAP service in front of it as middleware so the credentials never reach the browser, and that is what cap-agent-ui5-webui is demonstrated against: added as a dependency, it gives the annotated service a UI5 chat interface that can be deployed rather than only previewed. A Python multi-agent application on Cloud Foundry, where an orchestrator delegates to per-stack specialists so no single model sees every tool, closes the session.Talk,
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 Studio 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 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.Talk,
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 SDK: a determination on an uploaded receipt that sends the image together with the allowed categories and transaction types to a model reached through an intelligent scenario, then writes the extracted description, category, currency and amount back to the expense entity; and a recommendation function, triggered by a side effect on the trip title, that proposes a trip type with a score the Fiori UI sorts the proposals by and leaves the business user to accept — which is LLM integration from ABAP code. The second demo builds a capability for SAP Joule in the Joule Studio code editor in VS Code, with a scenario that extracts a trip title from the user's intent and calls an OData service in the ABAP backend through a BTP destination, deploys it and asks the Joule test UI for the trip's details; the session states that agents reach ABAP only over governed remote APIs — OData, SQL and MCP — and that automatic grounding of custom OData services in the knowledge graph is upcoming rather than available.Talk,
How We Make Tabular Predictions in 2026 with TabPFNpublishedA Devtoberfest 2026 session, AI-32, on why a table needs a model of its own: a language model reasons its way to a plausible number, while a tabular foundation model takes the table as context in one forward pass and learns from its features statistically. That is predictive models from both ends — a scikit-learn-shaped fit and predict in a notebook over a heart-disease data set, predicted class probabilities and SHAP values for which features drove the outcome, then the same model reached as an MCP tool by a coding agent that is asked which current customers are most likely to churn. The presenter is from the lab that publishes TabPFN; the Q&A puts it beside SAP's own tabular foundation model, which she says she has not used.Talk,
Meet Joule Studio and Build your First AI AgentpublishedA Devtoberfest 2026 session from the product manager of Joule Studio, 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.Talk,
Real Pro-Code Development with Joule StudiopublishedA Devtoberfest 2026 AI-track session that runs one agent build across both of Joule Studio'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 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 tooling; the skills themselves, which SAP says not to edit but which a developer may add to, are the edge to Agent guidance.Talk,
Supercharge Joule Desktop: Connect Any SAP API in Minutes with MCP GatewaypublishedDevtoberfest 2026 session INT-13, in which an SAP solution advisor connects a live S/4HANA system to the desktop experience of Joule Work through the MCP gateway in SAP Integration Suite. One OpenAPI specification covering business partners, sales orders, material stock, billing and purchase requisitions is uploaded as an MCP server artifact, deployed to integration cell with XSUAA inbound authentication, and registered as an MCP connector; the destination behind it is then switched from basic authentication to principal propagation, and the Cloud Connector monitor shows the same question arriving as the presenter's own user. That demonstration is the serve your application over MCP edge, and the second half is Joule Work itself: a Markdown skill that fixes the steps and format of a customer briefing, and a Space the skill rebuilds with each run.Talk,
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 Core, where the tabular orchestration service plays the part the orchestration service plays for language models: a data destination, a table artifact with its CSN schema and a scenario configuration registered once at design time, after which a predict call passes only the query rows, the scenario configuration and a context-selection strategy. The last demo runs those same calls in natural language through the aicore-skills plugin in a coding agent, and one of them only resolves once the agent is told which scenario configuration to use.Talk,
Agent workspacesecosystems revisedThe ABAP, CAP and UI5 views existed only to hold Werkbank, whose stack-specific part is its catalog of development skills and connectors, not the workspace. That contribution moved to Agent guidance; nothing behind those doors offers a workspace of its own.Capability,
Editor supportecosystems revisedUI5 Language Assistant, SAP's VS Code extension for UI5 XML views and manifest.json, and the SAPUI5 Extension by iljapostnovs were staged in intake-20261019-bestofui5 with this concern as their best fit, and the capability was not open on the UI5 door. The UI5 reading comes from the UI5 Language Assistant README.Capability,
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.Skill,
Sun 18
6 changes
CAP in the age of AI #6 - vector embeddingspublishedVector embeddings put to work in the incident management sample, answering whether this problem has been seen before. An embedding element of type Vector is calculated and stored from the vector_embedding function, so the database refreshes it whenever the text behind it changes, and cosine_similarity compares it with a freshly embedded string; because a title says little, a scheduled action first summarises each incident's conversation through a model on SAP AI Core and the embedding is taken from that summary. The similar-incidents list is a view joining incidents to themselves, with order and limit set in a before handler on the expanded query, and the vector element excluded from the service, since OData knows nothing about vectors — on SAP HANA Cloud the function is native, while SQLite needs packages added to the project.Video,
CAP in the age of AI #7 - vector embeddings wrap-uppublishedThe same embeddings model taken from SQLite to SAP HANA Cloud, then handed to an agent. Locally it is @cap-js/ai that adds the vector functions SQLite lacks and downloads an all-MiniLM L6v2 ONNX model on first start; on HANA natural language processing has to be switched on, the model name is a mandatory argument, the vectors it returns are 768 dimensions, and dimensions must match on both sides of a comparison. HANA itself can be given SAP AI Core as a remote source for other embedding models, which a CDS.ql expression has to inject because the postfix notation only takes what the CDS model holds, and the hour ends with a search function over cosine similarity exposed over @cap-js/mcp, so an agent asked about low output from solar panels calls semantic search instead of writing the query itself.Video,
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 Joule 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 Studio's low-code design canvas.Blog,
Modernization Agents for SAP on AWSadded to the atlasAWS agents for ABAP, PI/PO and BW modernisation workApp,
Show 2 more
SAP Developers MCPadded to the atlasHosted MCP server of developers.sap.com tutorials and missionsMCP server,
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.MCP server,
Sat 17
50 changes
Access to Generative AI Modelsexplains 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).Doc,
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).Blog,
Agent access to your systemsdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.cap. Maintainer-requested scope audit.Capability,
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).Reference architecture,
Show 46 more
AI-enabled administration: Automating log analysis with generative AI hubexplains 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).Talk,
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).Reference architecture,
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).Blog,
Architecture diagramsdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.btp. Maintainer-requested scope audit.Capability,
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).Blog,
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).Blog,
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).Blog,
Calling Claude from ABAP: How I Wired SAP AI Core into a Real Business Scenarioexplains 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).Blog,
cf-create-app: Create End-to-End apps and deploy to Cloud Foundry in minutesexplains 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).Blog,
CI/CD pipelinesdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.btp. Maintainer-requested scope audit.Capability,
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).Talk,
Creating a Hybrid CAP (Node.js) Profile with PostgreSQL on BTP from Business Application Studioexplains 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).Blog,
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).Blog,
Custom Joule Agent for SAP Ariba SLP - Building an AI Agent for Supplier Registration Approvalexplains 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).Blog,
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).Doc,
Don't Wait for SAP: Unlocking MCP Servers in BAS Right Nowexplains 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).Blog,
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).Blog,
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).Blog,
Explore SAP Fiori elements for ABAP developersexplains 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).Talk,
GenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportexplains 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).Blog,
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).Talk,
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).Reference architecture,
Get Started with an SAP Cloud Application Programming Model Project in SAP Continuous Integration and Deliveryexplains 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).Tutorial,
Govern AI-supported actions across enterprise systemsexplains 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).Talk,
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).Talk,
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).Blog,
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).Talk,
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).Blog,
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).Reference architecture,
Integration Tests in a Cloud Foundry Java App using SAP Cloud Application Programming Modelexplains 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).Blog,
Intelligent, governed, and agentic integrations with SAP Integration Suiteexplains 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).Talk,
Low-code appsdescription revisedKeep the default capability wording neutral; preserve the previous wording in framing_by_ecosystem.btp. Maintainer-requested scope audit.Capability,
Making CAP Application Development Easier and Faster with the Help of Storyboard in SAP Business Application Studioexplains 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).Blog,
Migrating Your CAP Applications from SAP Web IDE to SAP Business Application Studioexplains 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).Blog,
Model context protocol (MCP) unlocked: Enable governed access to AI agentsexplains 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).Talk,
SAP AI Services - DOX - Gen AI with SAP CAP Plugin - Part 3explains 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).Blog,
SAP BTP Showcase – SAP Continuous Integration and Delivery (SAP CI&D) for SAP HANA Cloudexplains 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).Blog,
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).Reference architecture,
SAP Integration Suite as the foundation for enterprise 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).Talk,
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).Blog,
SAP's API Policy on AI Agents: What It Prohibits, Allows, and Leaves Openexplains 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).Blog,
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).Talk,
Surviving and Thriving with the SAP Cloud Application Programming Model: Local development hurdlesexplains 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).Blog,
Testingecosystems revisedThe same concern on the SAP Digital Manufacturing door, opened 2026-10-17: SAP published test automation modules for the product's standard apps.Capability,
Testing your CAP HANA Artifacts with jest – including multitenancy, hdbprocedure and hdbviewexplains 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).Blog,
The fastest and easiest way to run full-stack applications in SAP Business Application Studioexplains 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).Blog,
Fri 16
1 change
What’s new in Mobile development kit client 26.9publishedThis Mobile development kit client 26.9 release note explains that @sap/mdk-mcp-server is now reachable from SAP Business Application Studio's AI chat, giving an assistant real knowledge of the MDK metadata schema rather than generic code generation. With it an assistant can scaffold an MDK project, generate pages, actions, rules, i18n, services and styles into it, iterate on it conversationally, and answer schema and client-API questions inline through mdk-docs.Blog,
Thu 15
35 changes
@saptools/brunoadded to the atlasRunner for Bruno collections against XSUAA-protected CF appsCLI,
@saptools/cf-debuggeradded to the atlasNode.js inspector tunnel over cf ssh to Cloud Foundry appsCLI,
@saptools/cf-exploreradded to the atlasFile search in apps deployed to SAP BTP Cloud Foundry over cf sshCLI,
@saptools/cf-function-traceadded to the atlasStep-by-step state recorder for one JavaScript function in Node.jsCLI,
Show 31 more
@saptools/cf-hanaadded to the atlasSQL runner against the SAP HANA Cloud database bound to a CF appCLI,
@saptools/cf-inspectoradded to the atlasShell debugger for remote Node.js over the Chrome DevTools ProtocolCLI,
@saptools/cf-live-traceadded to the atlasHTTP trace hook streaming a running CF Node.js app's trafficCLI,
@saptools/cf-syncadded to the atlasCloud Foundry topology cache for the other @saptools packagesCLI,
@saptools/sqltoolsadded to the atlasSQLTools connection from a Cloud Foundry app's HANA bindingCLI,
Agentic Engineering for SAP BTP ExtensionspublishedAn agent harness coordinates code generation across isolated Git worktrees, using a skills registry, SAP CAP MCP Server, Fiori MCP Server and UI5 Web Components MCP Server for development context. The diagram shows LiteLLM as a model proxy in front of SAP AI Core, 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.Reference architecture,
Joule Studioadded to the atlasSAP's managed environment for building custom agents and workflowsWeb tool,
Joule Workadded to the atlasSAP's workspace for conversations, Spaces and directing agentsWeb tool,
@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.CLI,
abap-skillsprovides revisedcapability:agent-guidance widened installs_into to the ABAP door. The README read on 2026-10-15 names the five clients the skills command line supports and adds "and other compatible agents", so the five named ones are the value; the README also documents separate routes for Claude Code, OpenCode and GitHub Copilot in VS Code, which name no client the sentence does not. system_reach is left out: the repository states nothing about needing a system or bringing one, and absent is not a no.Skill,
Agent 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.Capability,
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.Capability,
Agent guidancecoverage by ecosystem, framing by ecosystem, facets, coverage by flavor, framing by flavor revisedskillOverflow 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.Capability,
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.Capability,
Agent workspacesecosystems revisedAttach Werkbank to the same user-facing concern. Its own catalog lists ARC-1 and ABAP Cloud, CAP Upgrade, and UI5 development skills, while its README describes persistent conversations and Spaces. The additional views record only that scoped attachment; BTP coverage and its assessment date are preserved.Capability,
aicore-skillsprovides revisedcapability:agent-guidance declared the installs_into property on the BTP door, and the README's Installation section names the harnesses in one sentence. The entry's own description already carried the same four; the value puts it where the door's options can be compared on it. Two sentences from the lifecycle skill were read on the same day and added as sources for the edge, since they state how an operation is run and what a mutating script requires.Skill,
btp-solution-diagram-generatorprovides revisedThe edge said the rules are packaged and not what the package holds, which is the thing that separates this option from the other three skill sets behind the door that carry the same guideline. The README's own list was read on 2026-10-15 and its three lines are now the edge's sources.Skill,
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.Skill,
drawio-skill-sapprovides, description revisedThe entry carried the one-line install command and not the path the README's own first option uses, which is what a reader on Copilot needs.Skill,
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.Web tool,
Joule Workecosystem, artifact type, ecosystem revisedThe three-record acceptance on 2026-10-15 established the workspace as a separate part of SAP Joule. Retain that family split: SAP Joule records the BTP formation and identity integration, while Work records the user-facing experience across systems. RA0029 says "The experience is available across web, desktop and mobile"; there is no separate BTP subscription or binding documented for Work. Its BTP served view describes interaction with customer-managed agents connected to Joule, not a BTP runtime or core-coverage claim.Web tool,
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.Capability,
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.Skill,
sap-architectureprovides, description revisedThe entry said other agents can run it and not what that costs. The README's own caveat, read on 2026-10-15, is that the auto-load is Claude's alone, which is the difference between this option and a Claude-only one.Skill,
sap-cloud-integration-pipeline-assistantprovides revisedcapability:agent-guidance declared the installs_into property on the BTP door. The README names GitHub Copilot agent mode in its install step and gives a .claude/skills/ path beside it under the heading "For Claude", which names a product family rather than one of the property's values, so only Copilot is entered and the Claude line is kept as a source on the edge.Skill,
SAP-samples/html5-applications-migration-skills-for-sap-btpprovides, description revisedThe entry said the plugin needs no network access, which the README states, and said nothing about the four command lines the same README requires before anything is built or deployed. A reader who stopped at the first half would take the migration for the whole job. The cleanup skill's own sentence, which undeploys from Cloud Foundry, is added as a source on the edge beside it, because the two statements sit in one README and both are true of different steps.Skill,
SAP-samples/joule-a2a-agent-toolkitprovides, description revisedThe entry said the skills generate commands, which the README states of btp-cli, cf-cli and joule-cli, and said nothing about /sap-a2a-agent-toolkit:deploy-agent, which the Quick Start uses to deploy the scaffolded agent. The distinction decides whether anything here reaches an account, so it is now on the entry, and the README's own cf login and joule login step is named in the warning where the account conditions already were.Skill,
SAP/automation-pilot-agent-skillsprovides, description revisedThe README read on 2026-10-15 lists curl and jq in the same prerequisites table as Claude Code, for the API calls and the JSON parsing, and the entry named neither. The two API sentences read the same day are added as sources on the edge, since what the skills do through the Content Management and Executions APIs was described in the entry without a quote behind it.Skill,
SAP/leanix-ai-pluginsprovides, requires revisedThe edge rested on one phrase, "designed to work with the LeanIX MCP Server", which says the skills are written for it but not that a reader has to do anything. The sentence read on 2026-10-15 states the connection and the sign-in flow, which is what makes the requirement concrete.Skill,
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.Skill,
Testingcoverage by ecosystem revisedIntake of @saptools/bruno, which runs request collections against services deployed to Cloud Foundry: the concern exists behind the BTP door.Capability,
Wed 14
4 changes
Adapting SAP Joule for Purchase Order Creation from an Existing Purchase RequisitionpublishedA custom Joule Agent and Joule Skill, built in Joule Studio, classic edition to extend SAP Joule 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.Blog,
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.Capability,
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.Capability,
midasol/sap-mcp-serverdescription revisedThe whole paragraph was the policy, which Agent access to your systems carries as a condition sourced to the policy.MCP server,
Mon 12
2 changes
Explaining SAP Joule for HR Business Users & Functional Consultants.publishedWritten for HR business users and functional consultants, this walks through how SAP Joule 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 provisioning 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.Blog,
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.Capability,
Sun 11
40 changes
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 Joule, 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.Talk,
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 Joule, of which Joule for Consultants is a part; the system transition workbench has no entry here, and Platform migration 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.Talk,
AI-enabled administration: Automating log analysis with generative AI hubpublishedA log analysis tool for incident work, built in SAP Business Application Studio with the generative AI hub feature, which SAP AI Core ships as its LLM integration by its own documentation: it automates root-cause analysis over system errors and masks sensitive data. SAP's abstract states the tool's jobs and not how the hub is called, what the masking covers or which model answers. A TechEd 2026 session (Wednesday 28 October, Berlin), with no speaker listed in the catalogue at the time of writing, written here from SAP's abstract; the recording is not yet published.Talk,
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 Core with SAP Document AI. Knowledge Graph and Domain Models are not atlas entries, so the edges rest on the two products the abstract names as the infrastructure and on Predictive models for the tabular AI; nothing is stated about what any of them does in the layer. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST103V, virtual), presented by Jan Portisch and Richard Grandpierre, written here from SAP's abstract; the recording is not yet published.Talk,
Show 36 more
Build business differentiation with SAP AI CorepublishedSAP AI Core as the orchestration layer for enterprise AI, worked through with SAP's engineers: extend Joule Agents with models from its library, ground them in SAP Business Data Cloud products, embed them in SAP S/4HANA flows, then govern, scale and monitor them from prototype to production. The abstract says what the layer does for an agent and not which services carry each step. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by David Knaack, Franziska Dobrigkeit, Hadi Hares and Jonas Israel, written here from SAP's abstract; the recording is not yet published.Talk,
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, 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.Talk,
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 Cloud. The agents are SAP Joule'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.Talk,
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 Joule's agents do and what Joule Studio, classic edition 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.Talk,
calmcpadded to the atlasMCP server with read tools over the SAP Cloud ALM APIsMCP server,
Connecting AI agents to the ABAP RESTful application programming modelpublishedJoule Studio, classic edition 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 tooling 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.Talk,
Connecting SAP Integration Suite with SAP Document AI and SAP Business AIpublishedWalks through a Cloud Integration flow in SAP Integration Suite that pulls PDF purchase orders from a Gmail mailbox, extracts header and line-item fields through SAP Document AI's job-submission and polling API, and validates the result with SAP AI Core's generative AI hub using GPT-5-mini as a quality check rather than the source of the extracted values. Groovy steps combine the Document AI confidence score and the model's score into one figure that routes low-scoring purchase orders to manual review, with no S/4HANA posting performed.Blog,
Discover fast-track implementation of SAP Cloud ERP with AIpublishedSAP's implementation practice for SAP S/4HANA Cloud Public Edition 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 Joule 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.Talk,
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 Joule, 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.Talk,
Experience core foundational capabilities of SAP Cloud ERPpublishedGuided exercises in SAP S/4HANA Cloud Public Edition, 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 Joule, 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.Talk,
Explore SAP Fiori elements for ABAP developerspublishedSAP Fiori elements for an ABAP developer who now builds the UI as well as the RAP business object behind it, the transactional model of ABAP Cloud, in SAP Business Application Studio; the abstract calls the UI side new territory for that developer, and a Fiori elements app is rendered from the service's Fiori annotations rather than hand-written UI code. The abstract names the tool and the stack and does not say which floorplan or annotations are shown. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Björn Schulz, written here from SAP's abstract; the recording is not yet published.Talk,
From confident to correct: AI search results you can actually trustpublishedHow SAP LeanIX designs its AI search agents so that a result does not need checking in the UI: agents that adapt to each customer's own workspace model, with ambiguous queries and silent errors at scale as the two problems the talk takes on. The atlas holds no entry for SAP LeanIX itself; the SAP LeanIX MCP Server is the nearest entry, and the abstract names neither it nor any mechanism behind the agents, so the edge rests on the product name alone. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Aviral Vaid and Sai Krishna Subramanian, written here from SAP's abstract; the recording is not yet published.Talk,
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 Joule, which does the translating, and to Extensibility, 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.Talk,
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 automation with the workflow generated from intent, and agent tooling where the workflow calls agents. The generated workflow sends notifications to the Joule Work mobile app of SAP Joule, 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.Talk,
Get to know our AI-enhanced mobile apps across the Autonomous EnterprisepublishedA demo of the Joule Work mobile app, part of SAP Joule, 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 apps 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.Talk,
Govern AI-supported actions across enterprise systemspublishedGoverning what an AI agent may do once it takes business actions across enterprise systems, which is the Tool governance concern, with SAP Integration Suite as the place it is enforced. The abstract lists the mechanisms, scoped APIs, event-driven workflows, runtime policy enforcement, exception handling and observability across SAP and third-party systems, and names no Integration Suite feature behind any of them. A TechEd 2026 session (Tuesday 27 October, Berlin; also IN200V, virtual), presented by Finny Babu and Piyush Gakhar, written here from SAP's abstract; the recording is not yet published.Talk,
Hands on SAP Document AI: Next-generation intelligent document processingpublishedSAP Document AI 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 extraction 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.Talk,
How SAP Document AI brings agentic intelligence to business documentspublishedSAP Document AI 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 extraction 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.Talk,
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 Joule, whose agents the runtime runs; the atlas reaches that runtime through @sap/joule-work-dev-cli-early-adopters, 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.Talk,
Intelligent, governed, and agentic integrations with SAP Integration SuitepublishedSAP Integration Suite positioned as the control plane that connects and governs agentic workflows across SAP and third-party systems, set against the abstract's claim that exposing back ends directly to AI brings security, compliance and cost risks. That governing role is the Tool governance concern; the abstract promises recent innovations and names none. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Finny Babu and Piyush Gakhar, written here from SAP's abstract; the recording is not yet published.Talk,
Joule and related AI offerings from SAP: One platform, many systemspublishedSAP Joule 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.Talk,
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 Core as the management and orchestration layer of an AI architecture: extending Joule Agents in SAP Joule, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. The SAP Knowledge Graph the title names does not appear in that text, so the edges rest on the abstract as published, and whether the session follows the title or the abstract is not known until it is recorded. A TechEd 2026 session (Wednesday 28 October, Berlin; also RA110V, virtual), presented by Jan Portisch and Pavithra G K, written here from SAP's abstract; the recording is not yet published.Talk,
Joule without walls: From personal skills to enterprise interoperabilitypublishedSAP Joule 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.Talk,
Model context protocol (MCP) unlocked: Enable governed access to AI agentspublishedThe MCP Gateway in SAP Integration Suite: the place policy, security and analytics are applied to a curated set of MCP tools before an AI agent reaches enterprise tools and APIs through it, tool governance done in the integration layer and agent access to your systems routed through one gateway. The abstract names the gateway and its three functions and does not say how tools are curated, which policies exist or how the agent authenticates. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Bruno Renzo, Emily Mui, Markus Winter and Sunny Kapoor, written here from SAP's abstract; the recording is not yet published.Talk,
SAP AI Core deep dive: Models, agents, and business context at scalepublishedSAP AI Core read as the management and orchestration layer of an AI architecture, beyond the model runtime: SAP's abstract lists extending Joule Agents, the model library in Joule Studio for contextual reasoning, connecting data products from SAP Business Data Cloud, and embedding AI in SAP S/4HANA. It names the connections and not the APIs behind them. A TechEd 2026 session (Tuesday 27 October, Berlin; also RA107V, virtual), presented by Franziska Dobrigkeit and Hadi Hares, written here from SAP's abstract; the recording is not yet published.Talk,
SAP Integration Suite as the foundation for enterprise agentic AIpublishedSAP Integration Suite as the way an agent reaches systems: SAP's abstract says it gives agents governed access to APIs, events, applications, trading partners and processes across SAP and third-party landscapes, with AI assistance in the design, deployment and operation of the integrations. That is agent access to your systems through middleware; the abstract names no protocol and no gateway. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST104V, virtual), presented by Markus Winter and Udo Paltzer, written here from SAP's abstract; the recording is not yet published.Talk,
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 Core, getting answers from SAP knowledge and that content, then building an expert, loading project files and running guided prompts. The edges are to SAP Joule, of which Joule for Consultants is a part, and to SAP AI Core, named as the connection path; how the data is grounded is left to the session. A TechEd 2026 hands-on session (Wednesday 28 October, Berlin), presented by Anantharaman Ravi, Natalie Han, Sachin Kaura and Yi Hsuan Lin, written here from SAP's abstract; the recording is not yet published.Talk,
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 Core with a workflow built on tabular orchestration and connected to the participant's own data for real-time predictions. A predictive models session with the models as the subject; the abstract does not name the SDK or API the workflow is built with. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Eliott Kalfon, Janick Zaehringer-Frasch, Johannes Hoehne, Katharina Schell, Nilay Mehta and Sherene Tan, written here from SAP's abstract; no recording is announced.Talk,
SAP-RPT-1.5 Is Now Generally Available: More Accurate Predictions, Better Explainability, What's NewpublishedAnnounces general availability of SAP-RPT-1.5, the next release of SAP's foundation model for predictive models over tabular enterprise data: in-context classification and regression with no training step, now with stronger accuracy on high-cardinality columns, a maximum API batch of 512 rows (up from 128), and an "explain by example" mode that surfaces the historical rows that most influenced a prediction rather than ranking feature importance alone. Two variants ship, a default model and a -large model recommended past 100 columns or where accuracy is the priority, and the post previews a coming "tabular orchestration" workflow, targeted for general availability in August 2026, that is meant to select the relevant context rows from millions of historical records automatically.Blog,
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 Joule: 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 UI 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.Talk,
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 Joule, 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.Talk,
What a Second Document AI Workshop Taught Me About GovernancepublishedFrom questions raised at a second SAP Document AI 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 Hub.Blog,
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 Services and SAP Cloud Logging, on how enterprise AI is governed and run. The edges are to the two named services and to SAP Joule, 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.Talk,
Why Our First Document AI Exercise Was a Résumé, Not an InvoicepublishedWorking through a SAP Document AI workshop, the author explains why its exercises teach extraction on a résumé before an invoice: a résumé has no stable layout to map fields against, so it forces the point that the tool extracts from a written description of a schema rather than from position-matched templates. Describing the schema is shown to carry real judgment — what a missing end date should become, what a vague field name like "number" costs the model, who in a company should decide these things — and the piece argues that preparing for a project is chiefly a business task of writing down knowledge that otherwise stays in people's heads.Blog,
Zero token architecture for Joule AgentspublishedA pattern for SAP Joule'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.Talk,
calmcpentry revisedThe repository was handed over directly. Written from the README, the repository's own record and the product page at consetto.com. Filed on the BTP door because Cloud ALM has no door of its own and the server deploys to Cloud Foundry, binds XSUAA and resolves a destination there, the same strain recorded on cloud-alm-itsm-mcp. origin_ring is independent because the product page states it: "calmcp is an independent open-source project."MCP server,
Fri 9
40 changes
sap-cloud-integration-pipeline-assistantadded to the atlasAgent skill for the Pipeline Concept in SAP Cloud IntegrationSkill,
sap-cx-developer-companionadded to the atlasAgent skill for SAP Customer Experience APIs, CDS and errorsSkill,
sap-mdk-appsadded to the atlasAgent skill for Mobile Development Kit projectsSkill,
@mariodefe/sap-datasphere-mcpprovides 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.MCP server,
Show 36 more
abap-skillsentry revisedA repository the SAP AI Skills Library collection cache carries as processedBy baseline-2026-09-18 and that was never drafted into the atlas, so the changed registry record of 2026-10-09 is the first occasion to enter it; first_seen keeps the baseline date and no revises flag applies, since there is no published entry to revise. Written from the repository's README, its SKILLS_INDEX.md, the skills directory listing and the abap-cloud SKILL.md; hard rule 7: skills are indexed, never authored here.Skill,
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.Capability,
Agent guidanceecosystems revisedSAP Commerce opened as a product door (docs/concepts/product-doors.md, ADR-0033) and sap-commerce-skill 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.Capability,
AI Core MCP Serverprovides 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.MCP server,
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.Reference architecture,
aicore-skillsdescription revisedThe SAP AI Skills Library registry snapshot of 2026-10-09 lists a fourth skill under plugins/aicore-skills, genai-hub-tabular-orchestration, and plugin.json names four skill directories where the entry of 2026-09-25 described three. Read from that skill's own SKILL.md and plugin.json: the Context Registry layers, the sap-rpt tabular prediction models and the BTP command line it wants for HDL access are added, and the sentence about the DO NOT USE FOR clauses is corrected, because the new skill sends what it declines to genai-hub-orchestration, which plugin.json does not list.Skill,
BTP CF MCP Serverprovides 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.MCP server,
BTP MCP Serverprovides 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.MCP server,
btp-sap-odata-to-mcp-serverprovides 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.MCP server,
CI MCP Serverprovides 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.MCP server,
cloud-alm-itsm-mcpprovides 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.MCP server,
CostingGeek/sap-mcpprovides 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.MCP server,
cpi-mcp-serverprovides 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.MCP server,
drawio-skill-sapentry revisedA repository the SAP AI Skills Library collection cache carries as processedBy baseline-2026-09-18 and that was never drafted into the atlas, so the changed registry record of 2026-10-09 is the first occasion to enter it; first_seen keeps the baseline date and no revises flag applies, since there is no published entry to revise. Written from the repository's README, its LICENSE and the skill's own SKILL.md; hard rule 7: skills are indexed, never authored here. It is a fourth independent BTP diagram skill beside marianfoo-btp-drawio-skill, lemaiwo-btp-drawio-skill and miyasuta-claude-drawio-btp-diagram, and GitHub reports it as not a fork of any of them.Skill,
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.Reference architecture,
hana-mcp-serverprovides 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.MCP server,
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.Reference architecture,
MCP Server for SAP BTP Administrationprovides 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.MCP server,
mcp-integration-suiteprovides 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.MCP server,
mcp-is-tpmprovides 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.MCP server,
mcp-sap-cpiprovides 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.MCP server,
mcp-sap-datasphere-serverprovides 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.MCP server,
mcp-sap-focusedrunprovides 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.MCP server,
midasol/sap-mcp-serverprovides 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.MCP server,
odata_mcpprovides 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.MCP server,
odata_mcp_goprovides 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.MCP server,
odata-mcp-proxyprovides 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.MCP server,
SAP LeanIX MCP Serverprovides 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.MCP server,
sap_analytics_cloud_mcpprovides 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.MCP server,
sap-bdc-mcpprovides 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.MCP server,
sap-bdc-mcp-serverprovides 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.MCP server,
sap-cloud-integration-pipeline-assistantentry revisedA new repository in the SAP AI Skills Library registry snapshot of 2026-10-09, registering one skill at skills/sap-cloud-integration-pipeline-assistant; the repository documents the same skill under .github/skills/ and .claude/skills/, which is where a reader copies it from. Written from the repository's own README; hard rule 7: skills are indexed, never authored here.Skill,
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.Skill,
sap-mdk-appsentry revisedA repository new to the SAP AI Skills Library registry snapshot of 2026-10-09, with no prior processed record in the collection cache, registering one skill at skills/sap-mdk-apps. Written from the repository's README and that skill's own SKILL.md; hard rule 7: skills are indexed, never authored here. Placed behind the BTP door, where the atlas already holds @sap/mdk-tools and @sap/mdk-mcp-server.Skill,
sap-pi-mcp-serverprovides 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.MCP server,
sap-tutorials-contententry revisedA repository the SAP AI Skills Library collection cache carries as processedBy baseline-2026-09-18 and that was never drafted into the atlas, so the changed registry record of 2026-10-09 is the first occasion to enter it; first_seen keeps the baseline date and no revises flag applies, since there is no published entry to revise. One of the three skills the repository registers: the other two name no SAP stack and stay out. Written from the skill's own SKILL.md and GitHub's record for the repository and the sap-tutorials organisation, which GitHub marks verified with the email sapdocs@sap.com and the tutorial navigator as its site. Hard rule 7: skills are indexed, never authored here.Skill,
Tue 6
1 change
sap-ai-dev-toolkitdescription, provides, requires, connects, type properties revisedRe-read against the README, tools.md and inventory.md at 0.9.3, published the same day; the entry was written on 2026-10-01 against 0.7.9, and npm records 41 releases in the eleven days since 0.2.5. Three cited sentences no longer exist in the source: the feature row now reads "Discover BAS destinations or local SAP GUI systems", the architecture flow now names "VSP + configured route (BAS, CF, or local SAP GUI)", and the row quoted for authentication ("No credentials in mcp.json") has become "Credential-aware setup", which states the BAS and local halves separately. So Business Application Studio is now a conditional requirement rather than an unconditional one, and the single destination authentication mode is joined by the local ones the README documents. The fourteen facets, the curated ADT surface and every other guardrail quote were re-verified unchanged.MCP server,
Thu 1
2 changes
sap-ai-dev-toolkitadded to the atlasMCP proxy pinning an agent's ABAP tools to one SAP systemMCP server,
sap-ai-dev-toolkitentry revisedDrafted from the repository's own README and LICENSE after the URL was handed over directly. Typed as an MCP server because what it gives an agent is a generated stdio entry per BAS destination; the setup command and the HANA inspector ship in the same package.MCP server,

Tue 29
4 changes
sap-fiori-iosadded to the atlasAgent skill mapping Fiori iOS UI Kit nodes in Figma to SwiftUISkill,
sap-knowledge-pipelineadded to the atlasPython library turning OData or HANA records into chunked documentsPackage,
sap-fiori-iosentry revisedRead out of the SAP AI Skills Library repository, which the atlas holds as source:sap-ai-skills-library rather than as an artifact because the registry keeps other people's code in their own repositories. This skill is SAP's own code in that repository, so it is entered from its SKILL.md, README and references directory, as plugins/aicore-skills was on 2026-09-25. The BTP door is where the atlas answers native iOS work (capability:mobile-apps names the SAP BTP SDK for iOS), and capability:agent-guidance exists on that door. Hard rule 7: skills are indexed, never authored here.Skill,
sap-knowledge-pipelineentry revisedHanded over as a URL. Filed behind the BTP door because what it reads is an SAP OData service and SAP HANA, and neither the library nor its recipes touch CAP, UI5 or ABAP; the repository's own topics are rag, rag-pipeline, sap, sap-btp and sap-hana. One edge, retrieval-augmented generation: the capability's CAP coverage says the layer above the vector, splitting long text into chunks and deciding what goes into the prompt, is hand-written in every entry there, and that layer is what this library is. Data import and export was considered and left off, since that capability is about a file somebody supplies rather than records read out of a live service, and OData is about serving a model as OData rather than consuming one. The optional SAP hdbcli driver is named in the prose and carries no edge: SAP's Node.js driver is the artifact @sap/hana-client, so its Python sibling belongs in the graph the same way and not as an external, which is an editorial decision rather than one for this batch.Package,
Mon 28
3 changes
ARC-DRAWadded to the atlasMCP server drawing BTP solution diagrams on a draw.io canvasMCP server,
ARC-DRAWdescription revisedThe README declares the status early (v0.x), installation from source and testing with Claude Code alone, and the entry carried none of it. The maturity label is the maintainer's own, dated here, and the live-canvas requirement is what separates this option from the ones that write a file.MCP server,
Architecture diagramscore coverage, facets revisedEvery provider edge on this capability was re-read against its own documentation in this pass.Capability,
Sun 27
9 changes
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".Capability,
BTP MCP Serverprovides revisedThe README lists create, update and delete on subaccounts and directories and entitlement assignment; the only edge was to the MCP-server capability, so the account-provisioning page did not list it.MCP server,
CI/CD pipelinesecosystems revisedThe capire audit of 2026-09-27 proposed CI/CD as a CAP concern and found this capability already on the BTP door, where the service is. capire's Deploy using CI/CD Pipelines guide is the CAP door's own answer, cds add github-actions and the service's ready-made CAP pipeline; three content entries about CAP pipelines had been filed under deployment for want of the door. Added by the maintainer's decision.Capability,
CostingGeek/sap-mcpdescription, connects, type properties revisedRead from the README and from saptools.py, which were the entry's sources from the start and state all three: the Claude Desktop config launches it from a local directory, the server runs on stdio, and the key travels in an apikey header. tool_count is left out — the README enumerates one tool and states no number, and the field rests on a stated count elsewhere in the corpus.MCP server,
Show 5 more
MCP Server for SAP BTP Administrationprovides revisedSAP's page says the server manages the BTP account structure, which is what account provisioning is; the only edge was to the MCP-server capability, so the account-provisioning page did not list it.MCP server,
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.Capability,
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.Service,
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.Reference architecture,
Testingcore coverage revisedcapire audit 2026-09-27: a page this capability owns was cited nowhere.Capability,
The last 30 days. Older changes stay in each entry's history.
AtomJSON