onedevatlasBeta
Browse the atlas
AllCAPUI5ABAPBTP
NewABAP, RAP and ABAP Cloud

New in ABAP

7 days30 days90 daysAll time
In the last 30 days
53new pieces of content21revisions
Change
Kind: Content
Origin
Domain: 2
Clear all
74 changes
DayCapability
Kind ContentDomain AI & AgentsDomain Operations & Runtime

Tue 20
2 changes
Joule for Developers with SAP BTP ABAP Environment-Setup GuidepublishedA step-by-step setup guide for SAP Joule for Developers, ABAP AI capabilities under its Q2 2026 limited-promotion licence: creating a BTP subaccount, adding ABAP environment and HANA compute-unit entitlements, enabling Cloud Foundry, configuring trust to Cloud Identity Services, creating the ABAP environment instance and assigning the developer role, then pointing ABAP Development Tools for Eclipse at the new system. It walks through the resulting Joule chat, predictive code completion, explain, ABAP Unit and CDS test-generation features inside a newly created ABAP Cloud project.Blog,
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
12 changes
🟣 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,
ABAP AI SDK powered by ISLM - How to implement your own AI use cases in ABAPpublishedA Devtoberfest 2026 ABAP-track session (ABA-44) on the ABAP AI SDK: an intelligent scenario development object holds the model and its version, so the ABAP code asks for an API, sends a prompt and reads the completion with its token counts and finish reason, and swapping the model is a change to that object rather than to the code. Four demos go through the ABAP line by line — a bare completion, a system prompt with the temperature set to 0.2, tool calls where the model asks for order details and the result goes back into the message container, and a JSON response schema that returns category, severity and goodwill as fields a program can act on — and a fifth replaces the API with the SDK's own mocks so unit tests run with no network call, which is what the LLM integration edge on the ABAP door rests on. The closing availability matrix separates base scenarios, available across SAP S/4HANA on-premise, private edition, public cloud and the SAP BTP ABAP environment, from the orchestration service and SAP RPT, shown for on-premise and private cloud with transport-based correction instructions back to release 2022 and not yet for the public cloud editions.Talk,
Agentic Loop with Joule for Developers and ADT MCP ServerpublishedA Devtoberfest 2026 session from SAP's ABAP AI team that generates a RAP issue-tracker application by prompting a coding agent. It covers what SAP Joule for Developers, ABAP AI capabilities now ships as MCP tools and which assistants can reach an ABAP system's virtual filesystem, then does the setup twice: turning on the ADT MCP Server and pasting the Joule side-by-side tenant link in ABAP Development Tools for VS Code, and again in ABAP Development Tools for Eclipse, where the custom agent becomes custom instructions. The demo's subject is the guardrails around the loop — an agent.md of phases and human checkpoints, skill files cloned from a GitHub repository for naming, ATC compliance and UI annotations — run through GitHub Copilot until the generated objects are activated, unit-tested and in a transport.Talk,
Show 8 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,
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,
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,
Intelligent App Development at Scale: SAP Fiori Elements + ABAP Development Tools for VS CodepublishedA Devtoberfest 2026 session (UI-33) that builds a RAP service and the SAP Fiori elements app over it from one VS Code workspace, with a coding agent driving two of SAP's MCP servers. The ABAP Development Tools for VS Code edges hold on the demo itself: its virtual file system keeps the ABAP package beside the Fiori project, the ADT MCP Server inside it creates, changes and activates the ABAP objects, and a version not yet released publishes the service binding from the agent instead of by hand. The @sap-ux/fiori-mcp-server edge covers its generators and the three-step workflow it uses for changes — list the functionality available for the application, ask for its JSON schema, then execute it — and the agent guidance edge rests on the skills the Fiori team publishes beside it, on the session's account of what a skill adds that a server does not, and on the analytical chart demo where a skill orchestrates both servers in one task.Talk,
News from Custom Code Migration: ECC to SAP S/4HANA Powered by Agentic AIpublishedA Devtoberfest 2026 session (ABA-23) on what SAP has added to the ECC to SAP S/4HANA custom code migration tools, demonstrated across a live ECC and an S/4HANA system. The first half stays deterministic and explains static analysis in that process: the custom code migration app's scoping over ABAP test cockpit findings, an explain of a legacy report and of an S/4HANA simplification finding, and transferable quick fixes exported from the app and applied on the ECC system through the SAP GUI ATC transaction before conversion. The second half runs the S/4HANA custom code migration agent in ABAP Development Tools for Eclipse: GitHub Copilot drives the ADT MCP Server's ATC and quick-fix tools in a loop, SAP Joule for Developers, ABAP AI capabilities produces the AI code proposals behind it, and only the high-confidence ones are written into the code, the rest left as comments in one transport request.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,
Sun 18
3 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,
SAP S/4HANA Cloud: Scheduling Background Jobs Using Application Job TemplatespublishedWalks through moving S/4HANA Cloud and ABAP Environment job scheduling off ECC's SUBMIT and JOB_OPEN/JOB_SUBMIT/JOB_CLOSE pattern onto the Application Job Framework: a job template built from an ABAP class that implements IF_APJ_DT_EXEC_OBJECT and IF_APJ_RT_EXEC_OBJECT, then scheduled through the Manage Application Job Templates Fiori app or programmatically with CL_APJ_RT_JOB_SCHEDULING_API's SCHEDULE_JOB method. The resulting job is tracked in the Monitor Application Jobs app, where status, logs and failed runs are reviewed.Blog,
Sat 17
20 changes
ABAP + MCP: Let AI Do Real Development in Your SAP Systemexplains 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,
ABAP development tools for Visual Studio Code: Patch 1.0.1 releasedexplains 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,
ABAP development tools for Visual Studio Code: Version 1.1 releasedexplains 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,
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,
Show 16 more
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,
Capturing Background Job Errors in SAP Using the Application Log (SLG0/SLG1)explains revisedDoor scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md).Blog,
Claude Code via MCP: Poor man's Joule, or a practical tool?explains 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,
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,
From SEGW and Legacy UI5 to RAP with ARC-1explains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Blog,
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 to Connect Claude Code to ABAP with Zero-Config MCPexplains 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,
Introducing ARC-1: A Secure ADT MCP Server for Enterprise SAP Developmentexplains 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,
OData to outcomes—Build AI-enabled SAP Fiori apps using SAP Fiori elementsexplains revisedDoor scope derived from the artifacts this piece also explains, so a door page lists it only where it holds (docs/concepts/content-on-doors.md).Talk,
Patterns for using LLMs in ABAP developmentexplains 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,
S/4HANA Observability: Streaming SAP Cloud ALM & LogServ Telemetry to BigQuery & Vertex 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,
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,
Scheduling a Background Job for the BDC Session Method Using RSBDCSUBexplains 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,
Spec first: The disciplined way to develop ABAP with agentsexplains 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,
Transform your configuration of SAP S/4HANA Cloud with agentic 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).Talk,
Using Claude for SAP ABAP development on RFC-only / SAProuter systems (even ECC R/3)explains 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,
Thu 15
2 changes
How to Create an Application Job (APJ) in SAP S/4HANA ABAP — With Single Values & Select OptionspublishedWalks through implementing an Application Job end to end on the ABAP door: a class implements IF_APJ_RT_EXEC_OBJECT for runtime execution and IF_APJ_DT_EXEC_OBJECT to define parameters, covering both single-value parameters and select options, then registers the class as a job catalog entry and template in ADT for scheduling through the Application Jobs Fiori app. Frames Application Jobs as the class-based, ADT-defined successor to the classic SM36/SM37 background job transactions.Blog,
Patterns for using LLMs in ABAP developmentpublishedLars Hvam compares eight ABAP development setups: assistance in SE80 or Eclipse, virtual files and MCP over ADT, a centrally managed MCP service, sandboxes, local Git, Git with read-only system context, and temporary ABAP systems for development and CI. The overview describes where source changes, review and system access happen, including abapGit synchronization and abaplint checks. It is dated March 2026; its risk, cost and autonomy ratings are the writer’s assessments.Doc,
Wed 14
2 changes
Capturing Background Job Errors in SAP Using the Application Log (SLG0/SLG1)publishedWalks through ABAP's Application Log framework for recording errors from a background job that has no screen to show them on: defining an Object and Sub-object in SLG0, then building the log in code with BAL_LOG_CREATE, adding a free-text or message-class entry with BAL_LOG_MSG_ADD_FREE_TEXT or BAL_LOG_MSG_ADD, and persisting it with BAL_DB_SAVE so it survives after the job finishes. The worked example is a report inserting student records into a custom table, scheduled via SM36 and reviewed afterwards in SLG1, filtered by the Object and Sub-object that created it.Blog,
Scheduling a Background Job for the BDC Session Method Using RSBDCSUBpublishedWalks through uploading data with GUI_UPLOAD, building a BDC session with BDC_OPEN_GROUP, BDC_INSERT and BDC_CLOSE_GROUP, then scheduling the standard program RSBDCSUB as a background job with JOB_OPEN, SUBMIT ... VIA JOB and JOB_CLOSE so the session processes without manual SM35 intervention. Shows the resulting job's status and spool read back through SM37, the way a reader confirms afterwards that a scheduled job actually ran.Blog,
Tue 13
1 change
ABAP + MCP: Let AI Do Real Development in Your SAP Systempublishedabap-adt-mcp is an open-source MCP server that gives an AI agent full ABAP development capability over ADT: it searches, reads, edits, activates and unit-tests objects, and runs ATC checks, on a connected S/4HANA Cloud or on-premise system, acting as the signed-in developer. It runs on abap-adt-api, the same REST client Eclipse's own ADT tooling uses, and sits beside SAP's own ADT MCP Server, shipped with ADT for VS Code and Eclipse under a different server key, and marianfoo's abap-docs, a read-only server over the ABAP Keyword Documentation and Clean ABAP. Each destination carries a policy — read-only, allowed packages, denied tables and tools — the server checks before every call, and an optional audit file logs each tool call with its outcome and policy gate.Blog,
Sun 11
24 changes
Agent-led custom code migration: From planning to mass adaptationpublishedThe Custom Code Migration Agent in SAP Joule for Developers, ABAP AI capabilities, applied to moving custom code from SAP ERP Central Component to SAP Cloud ERP Private: the abstract describes a toolchain that starts with planning in SAP Cloud ALM and ends in mass remediation by the agent, with newer custom code management features shown alongside. Which findings the agent remediates, and how far it goes without a developer, the abstract does not say. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Marco Matha and Olga Dolinskaja, written here from SAP's abstract; the recording is not yet published.Talk,
AI-first, API-first: What changes when AI becomes the userpublishedWhat changes in an architecture when an AI agent is the caller: AI-first and API-first principles, SAP's API governance, extensibility and the composable enterprise, with lessons the speaker draws from SAP's and other enterprise AI initiatives. The extensibility edge rests on the abstract naming extensibility as a principle and nothing more specific; no API, product or tool is named, so the talk is attached to the broadest concern it touches. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Tomasz Wilk, 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,
Build agentic SAP extensions with Google CloudpublishedGoogle Cloud's architectures for agentic AI apps on SAP with a clean core: SAP Business AI Platform, SAP S/4HANA and SAP Business Data Cloud joined with BigQuery, Gemini and Google's Agent Development Kit. The abstract names zero-copy data agents, developer API workflows and ABAP extensions for AI integration, the last of which is the Extensibility concern; Business Data Cloud is the one atlas entry it names, and how any piece connects to another is not stated. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Ekaterina Kruse, Ian Moria and Stany Winkler, written here from SAP's abstract; the recording is not yet published.Talk,
Show 20 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,
Deploy, review, break, fix: Govern cloud transports with agility and AIpublishedFive BTP services in one delivery chain, as the abstract lays it out: a transport is triggered in SAP Content Agent Service, tested in SAP Cloud Transport Management, its failure is raised by SAP Alert Notification service for SAP BTP and remediated by a SAP Joule agent with SAP Automation Pilot, and SAP Cloud Logging keeps the history for root-cause analysis. The chain from alert to remediation is the operations automation concern; what the Joule agent decides on its own is not in the abstract. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Biser Simeonov, Daniel Funkert, Sven Rullmann and Thorsten Sandfuchs, written here from SAP's abstract; the recording is not yet published.Talk,
Enriching AI models with SAP AI Core in SAP Business Data CloudpublishedThe integration between SAP Business Data Cloud and SAP AI Core, through which data products with their semantics feed AI models for benchmarking, custom AI development and agentic analytics and applications. The abstract names the two products and the three uses and states nothing about how the data reaches AI Core or what the integration consists of. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by San Tran and Sandy Tran, written here from SAP's abstract; the recording is not yet published.Talk,
Extending SAP Autonomous SuitepublishedExtensibility across SAP Autonomous Suite: AI-enabled development in SAP Build solutions, the ABAP Cloud model among them, as the way extensions are designed, generated and deployed, and a direction for making extensions ready for agentic AI. The abstract names the suite, SAP Build and the ABAP Cloud model and no single feature, so the edges are to Extensibility, the concern, and to SAP Build Code, the SAP Build solution held here in which Joule generates and deploys development; which other SAP Build solutions the session shows is not stated. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Alexander Rother and Khaled MUSILHY, 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,
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,
Level up app development: ABAP Cloud model innovations and Joule solutionpublishedThe ABAP RESTful application programming model, in SAP's abstract, generates multi-node business objects and adds event-driven side effects, collaborative draft, background processing and analytical tables, with the SAP Joule for Developers, ABAP AI capabilities add-on used to speed development up. The generated business objects are the transactional model concern; the abstract names each feature and says nothing about how it is used. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Anne Keller, Carine Tchoutouo Djomo, Frank Jentsch and Marina Blank, written here from SAP's abstract; the recording is not yet published.Talk,
Migrate and modernize your custom code using RISE with SAP and agentic AIpublishedThe Custom Code Migration Agent in SAP Joule for Developers, ABAP AI capabilities, shown on the RISE with SAP path that moves custom extensions from SAP ERP Central Component to SAP Cloud ERP Private: the abstract says the agent adapts the code through MCP tools and the AI for ABAP features in the custom code tools, and that the adapted code is then reworked along the clean core approach, the concern ABAP Cloud readiness covers. Which MCP tools, and what the clean core step changes in the code, the abstract leaves open. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Hitesh Bindal, Ingo Braeuninger, Jonas Helin of GitHub, Olga Dolinskaja and Thomas Fiedler, written here from SAP's abstract; the recording is not yet published.Talk,
Navigating the road map for SAP Cloud ERP: Today, next, and beyondpublishedSAP's near-term and long-term plans for SAP Cloud ERP by theme: embedded AI, process automation, lifecycle management and extensibility, with timelines and adoption paths toward what SAP calls the Autonomous Enterprise. SAP Cloud ERP has no artifact here, so the edges are to the two concerns the road map names, Extensibility and Process automation; the abstract names no product or feature under either, and whether its process automation is SAP Build Process Automation is not stated. A TechEd 2026 session (Tuesday 27 October, Berlin; also TM815V, virtual), presented by Lawrence Martin and Sasa Markovic, written here from SAP's abstract; the recording is not yet published.Talk,
OData to outcomes—Build AI-enabled SAP Fiori apps using SAP Fiori elementspublishedA Fiori elements app built through SAP's MCP servers: the OData V4 service comes from the MCP server for RAP, which the atlas holds as the ADT MCP Server, or from @cap-js/mcp-server for CAP, and the UI from @sap-ux/fiori-mcp-server, with annotations and actions added before the app is tied to SAP's AI features. Agent access to your code on both the service and the UI side; SAP's abstract names the servers and the steps and says nothing about which AI features or which agent host. A TechEd 2026 session (Thursday 29 October, Berlin), presented by Benedikt Schoelch, Sebastian Steinhauer, Sebastian Werner and Stefan Engelhardt, 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 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,
Ship your own sandboxed AI operations agent to Kyma in two hourspublishedAn operations agent built and then broken on purpose: the abstract has participants deploy a reasoning agent to SAP BTP, Kyma runtime, connect it to SAP AI Core, give it observability over the runtime and cause a failure for it to diagnose, the operations automation concern with an agent doing the diagnosis. Patterns for cost control and monitoring are promised at the end; the agent framework and how the sandbox is drawn are not named. A TechEd 2026 session (Tuesday 27 October, Berlin, two hours), presented by Christian Lechner, Piotr Tesny, Thorsten Sandfuchs and Vipin VijayKumar, written here from SAP's abstract; the recording is not yet published.Talk,
Spec first: The disciplined way to develop ABAP with agentspublishedSpec-driven ABAP development with a new AWS Toolkit for Eclipse plug-in powered by Kiro, in SAP's words, working inside ABAP Development Tools for Eclipse: SAP's abstract says it reads the codebase, helps with new features, explains legacy code, refactors and generates tests, for S/4HANA modernisation or a new business feature. It answers agent access to your code from inside Eclipse; the plug-in itself is not yet in the atlas, and the abstract does not say how it reaches the ABAP system. A TechEd 2026 session (Tuesday 27 October, Berlin), presented by Jon Friesen and Stephan Kremer, written here from SAP's abstract; the recording is not yet published.Talk,
Strategy for agent-led development in ABAPpublishedSAP Joule for Developers, ABAP AI capabilities moving ABAP development in ADT from AI-assisted to agent-led, across greenfield work and the migration and modernisation of existing solutions: SAP's strategy session for its ABAP AI add-on. The abstract states the direction and names no feature or release date. A TechEd 2026 session (Tuesday 27 October, Berlin; also ST124V, virtual), presented by Alexander Rother and Sonja Lienard, written here from SAP's abstract; the recording is not yet published.Talk,
The journey with clean core continues for SAP Cloud ERP PrivatepublishedClean core in SAP S/4HANA Cloud Private Edition as it stands in 2026: what is new in extensibility, new capabilities in the dashboard for the RISE with SAP Methodology, how AI helps make custom code compliant with clean core, and new guidance on data, integration and clean core in relation to SAP's API policy. The edges are to Extensibility, the concern the session is about, and to ABAP Cloud readiness, the concern behind making custom code compliant; the abstract names no tool for either and the dashboard is not held here. A TechEd 2026 session (Wednesday 28 October, Berlin; also TM108V, virtual), presented by Markus Goebel and Olga Dolinskaja, written here from SAP's abstract; the recording is not yet published.Talk,
Transform your configuration of SAP S/4HANA Cloud with agentic AIpublishedThe Configuration Assistant for SAP Cloud ERP, hands-on: an agent that validates insights from an organisation's data and maps toward a target business configuration, under the heading of agentic data management, with data preparation, transparency and governance as the stated aims. The atlas holds no entry for the Configuration Assistant and no concern for business configuration of an ERP, so the edge is to Agent access to your systems, the nearest concern, an agent working on a system's data and configuration; the abstract's configuration is not the per-environment application settings the atlas files under that word. The abstract is the same text as TM100 and states aims and no exercise detail. A TechEd 2026 hands-on session (Thursday 29 October, Berlin), presented by Felix Peter, Joerg Rupprecht, Joerg Singler and Simone Mundt, written here from SAP's abstract; the recording is not yet published.Talk,
Use change and deployment management in an ABAP environment with confidencepublishedSAP Cloud Transport Management with SAP Cloud ALM as the governed way to move changes from a cloud-optimised ABAP environment into production: the abstract says the session sets out the process, where it differs from classic transport mechanisms, the current state of every content type it carries, and an outlook on deploying agents through it, which is the transport management concern on the cloud side. What each content type covers, and when agent deployment arrives, is not stated. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Moritz Gysler and Sven Rullmann, written here from SAP's abstract; the recording is not yet published.Talk,
What's next in extensibility for SAP Autonomous SuitepublishedAgent-driven extensibility across SAP Autonomous Suite as SAP sees it ahead: what is coming for making extensions ready for agentic AI and how SAP's assistants are meant to help with it. The edge is to Extensibility, the concern; the abstract names no assistant, no feature and no date. A TechEd 2026 session (Wednesday 28 October, Berlin), presented by Alexander Rother and Oren Shatil, written here from SAP's abstract; the recording is not yet published.Talk,
Fri 9
2 changes
Unleashing ABAP Potential: An introduction to Extension Libraries (XCO)publishedIntroduces ABAP's Extension Libraries (XCO), a library framework that puts reusable functionality behind one interface. The post places it as part of the ABAP RESTful Application Programming Model but versatile enough for other ABAP contexts, and says it works in both on-premise ABAP and the ABAP environment on SAP Business Technology Platform. It walks through a worked Logging example: xco_log=>factory->create_new_log opens a log keyed by object, subobject and external ID, logger->add_message appends a typed message, and logger->add_last_symsg attaches a problem class and level of detail for later traceability.Blog,
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,
Sun 4
1 change
Clean Core IndexpublishedDescribes a company-built KPI, the Clean Core Index, that scores existing custom ABAP code by object type — reports, function modules, SAPScript/Smartforms, ATC S/4 readiness-check findings, user exits and modifications — each weighted by a severity the author sets for redesign effort and upgrade risk, with counts read off CDS views built for the purpose. The index is the author's own definition rather than an official one and does not by itself certify public-cloud readiness, but tracking it weekly shows where custom code still blocks a move to ABAP Cloud and lets progress be read per module or per object type.Blog,
Sat 3
2 changes
ABAP's Parallel Processing Frameworks: Practical Guide to Performance Tuning of Mass Data ProcessingpublishedSurveys ABAP's two parallel processing technologies, asynchronous RFC (aRFC) and the queued, exactly-once background RFC (bgRFC), and the six frameworks built on top of them, SPTA, SHDB, CL_ABAP_PARALLEL, the Background Processing Framework, the Parallel Processing Framework and the Mass Data Framework, each by its own entry point: a function module, a factory class or a Customizing transaction. A Qualitative Weight and Summ matrix then compares the frameworks across criteria such as package creation, load balancing and documentation quality, stated as the author's own subjective scoring for one project rather than a ranking.Blog,
Enhancing Standard BAPIs: When and How to Do ItpublishedWalks through why a standard BAPI needs enhancing — a missing field, an extra validation, logic before or after the call, or a performance tweak — and five ways ABAP offers to do it: a BAdI found in SE18/SE19, an append structure for extra fields, a classic user exit wired through SMOD/CMOD, a wrapper function module copied from the original, or an implicit enhancement when no other extension point exists. Each technique gets its own steps, and two carry a short ABAP code example.Blog,
Fri 2
2 changes
Clean Core清洁核心概况介绍publishedExplains Clean Core as SAP's architecture methodology for decoupling custom code from standard code, and walks through the A-D grading SAP uses for a single extension's cleanliness: D for direct modification of standard tables, programs, classes or functions, or disallowed patterns such as implicit enhancements; C for internally developed functions calling unreleased APIs; B for using only SAP's classic or released APIs (BAPI, ALV Grid, BAdI); A for side-by-side extensions reached only through released interfaces onto the SAP Build extension suite. It lays out a six-step roadmap for reaching Clean Core — inventorying existing extensions, setting a reduction target, surveying SAP's extension routes (SAP GUI SE80, Fiori custom fields and logic, BTP high/low-code, workflow/RPA), writing a decision tree, splitting new development from legacy migration, and reviewing periodically — while noting that in-app development is not inherently unclean and that real decisions should weigh ROI rather than follow the theory absolutely.Blog,
S/4HANA公有云版的内部ABAP拓展publishedArgues that S/4HANA Cloud public edition's in-app ABAP extensibility is still real ABAP development, just under stricter rules: developer extensions require ABAP Development Tools rather than SAP GUI transactions, data models are defined as CDS views instead of SE11 tables, business logic is a RAP behavior definition instead of a function module, and service exposure is an auto-generated OData service from a Service Definition instead of a hand-built RFC/BAPI. The piece walks a worked example — a Fiori app that triggers the Purchase Requisition API — through CDS, RAP, OData activation on SAP Gateway, and authorization via business catalogues, and frames the whitelist of released APIs and CDS views as upgrade-safety rather than a restriction.Blog,

Tue 29
1 change
S/4HANA Observability: Streaming SAP Cloud ALM & LogServ Telemetry to BigQuery & Vertex AIpublishedWalks through pulling SAP Cloud ALM's Outbound Logs, Metrics and Traces APIs — OAuth 2.0 client-credentials auth, protobuf-encoded OTLP payloads, and the guardrails needed against its rate limits and 24 GB/30-day retention baseline — plus SAP LogServ's infrastructure logs, into Google BigQuery for multi-year, cross-domain storage. A time-window SQL join then correlates ABAP exceptions, health metrics, infrastructure events and ITSM tickets, with the joined record passed to Vertex AI (Gemini) to draft a structured incident dossier.Blog,
The last 30 days. Older changes stay in each entry's history.
AtomJSON