Joule Work Desktop with Conversations, the composer, and the available work sources.

Testing Joule Work Desktop with Microsoft 365, Local Files, and SAP

You have probably seen Joule Work Desktop on LinkedIn by now. Sebastian Steinhaeuser showed how it prepares him for a customer meeting. Philipp Herzig called it the new SAP GUI, with a smile, and demonstrated a workflow across email, a spreadsheet, a Space, and PowerPoint. Joule Work Desktop is now available to SAP employees after a test with more than 6,000 colleagues. Selected customers can also use it through the Early Adopter Care program on macOS and Windows. ...

August 12, 2026 · 9 min · 1778 words · Marian Zeis
UI5 has entered the chat presentation title slide with Marian Zeis and Mike Zaschka.

UI5 Has Entered the Chat: Building Interactive MCP Apps for SAP

AI can appear in a user interface in several ways. It can add a focused feature such as summarization to a traditional application. It can sit next to the application as a copilot. Or the AI conversation itself can become the main interface. That last case raises an interesting question: if the AI host owns the frame, how can an MCP server provide more than text and JSON? MCP Apps provide an answer. They let an MCP tool return an interactive web interface that a compatible host renders inside the conversation. For our UI5con session, Mike Zaschka and I explored how this model fits SAP user interfaces and built five samples, starting with plain HTML and ending with an ARC-1 transport review. ...

July 13, 2026 · 10 min · 2091 words · Marian Zeis
ARC-1 on SAP BTP Cloud Foundry architecture with VS Code, XSUAA, Destination Service, Connectivity Service, Cloud Connector, and an on-premise SAP ABAP system.

Creating an ARC-1 BTP Diagram with Codex and a draw.io Skill

I wanted one practical thing: an editable draw.io diagram for ARC-1 on SAP BTP that looks like it belongs in the SAP Architecture Center. My first attempts with generic diagram prompts were not really useful. They often had dark backgrounds, icons that were too large, and arrows running through boxes. I wanted something closer to the SAP examples: a white canvas, the right BTP areas and service icons, understandable flows, and an editable draw.io file that I could still correct by hand. ...

July 9, 2026 · 9 min · 1901 words · Marian Zeis
SAP API Hub, SAP Notes, SAP Docs, SAP Roadmap, and ARC-1 feeding evidence into an SAP API Policy alignment check.

A Clearer View of Your SAP Integrations Under the New API Policy

In April, SAP published a new API Policy (v.4.2026a). If you run SAP integrations of any kind, like middleware, custom extensions, analytics pipelines, RPA, or anything with “AI agent” in the name, you have probably already had the uncomfortable conversation. Are we still allowed to do that, and can we safely start the next project this way? The honest answer is that nobody can fully answer that for you. That is the real problem. ...

June 2, 2026 · 12 min · 2435 words · Marian Zeis
Before You Upgrade S/4HANA static UI5 checks with MCP.

Before You Upgrade S/4HANA: Static UI5 Checks with MCP

Series note: This post is part of my AI ABAP development series. It reuses the legacy UI5 app from the SEGW to RAP migration demo, but this time the focus is only on the UI5 version upgrade problem. In the SEGW to RAP post I used a deliberately old freestyle UI5 app as migration material. It runs on SAPUI5 1.84.59 and contains many patterns that were normal in older projects: jQuery.sap.require, global formatters, synchronous bootstrap, Belize theme, older manifest versions, and a few small controller workarounds. ...

May 20, 2026 · 7 min · 1389 words · Marian Zeis
Diagram showing a safer ABAP AI development pattern with a local IDE and LLM, git repository, CI/CD, and a read-only ADT MCP server connected to the SAP system.

ABAP and Agentic AI: The Hidden Problem in Real Projects

Series note: This post is part of my AI ABAP development series, where I go from AI development in general, to ABAP-specific problems, and then to ARC-1. In the first post of this series, I wrote more generally about how I use AI today, why context matters so much, and why I am still not fully convinced by the more maximalist agentic hype. Here I want to get more concrete. Because SAP development is not one thing, and that matters a lot for AI. ...

April 22, 2026 · 13 min · 2625 words · Marian Zeis
Screenshot of the AI development workflow with ChatGPT, Claude Code, and MCP servers.

How I Use AI for Development and Why Context Matters

Series note: This post is part of my AI ABAP development series, where I go from AI development in general, to ABAP-specific problems, and then to ARC-1. When it comes to AI, I do not really think about magic. I think more about another colleague helping me out. Sometimes that means architecture. Sometimes implementation. Sometimes testing, review, CI/CD, or deployment. But this only works with trust, and trust needs communication. If I do not know something, I ask. If code looks strange, I ask. If tests fail, I ask. ...

April 20, 2026 · 10 min · 2037 words · Marian Zeis
Screenshot of the sap-ai-mcp-servers README showing the overview tables and categories.

SAP MCP Servers: The Missing Overview

If you are searching for SAP MCP Servers (Model Context Protocol), you quickly run into the same problem: Which SAP MCP servers exist (official and community), and what other SAP AI tooling should you know about? That is why I like this new repo: marianfoo/sap-ai-mcp-servers: SAP MCP Servers and SAP AI Skills list It is a curated list of SAP MCP servers, SAP AI skills, and adjacent developer tools. The README is structured as tables so you can scan by category, compare licenses, and see what is actively maintained. ...

March 5, 2026 · 2 min · 239 words · Marian Zeis
Bar chart showing cumulative ABAP understanding success rates by model and feedback round.

SAP’s ABAP-1 Loses Every ABAP Benchmark, Even “Explaining”

Previous post (code generation benchmark): Benchmarking LLMs for ABAP Live benchmark results (old + new): abap-llm-benchmark.marianzeis.de In my first evaluation (based on the TH Köln benchmark paper), I extended the original setup with additional models and focused on a very concrete question: how well can LLMs generate ABAP code that actually compiles and passes ABAP Unit tests? I also tested SAP’s model ABAP-1, and it performed very poorly for code generation. To be fair: SAP also states this in the documentation. ABAP-1 is primarily meant for explaining ABAP code not for reliably generating full working implementations. ...

March 3, 2026 · 5 min · 1005 words · Marian Zeis
Screenshot showing the integration of SAP RAP actions in the AI agent workflow.

Building an Enterprise-Ready SAP AI Agent with Open Source

There is currently a huge hype around the new MCP (Model Context Protocol) servers. I’ve built one for SAP Docs, and there are excellent community projects like the ADT API MCP Server. These tools are fantastic for individual developers. You install them, connect them to your IDE or a local LLM, and suddenly your AI assistant knows about SAP. Architecture overview (in one picture) Before diving into the details, here is the high-level architecture I’m aiming for: ...

March 3, 2026 · 8 min · 1681 words · Marian Zeis