SAP is giving every learner one free attempt at the new SAP Certified - Joule Studio Developer (C_JSD) certification, but only until Dec 31, 2026. Here is everything you need to claim it, prepare for it and use your single attempt well.
Whose permissions does an AI tool use when it reads your business data?With a shared technical user, every question runs with the same, usually too broad, access. This step-by-step guide shows how an MCP server can query SAP Datasphere as the logged-...
Previously, we published a blog post on Jev vs. RPT where we shared how our research teams have shown that tabular foundation models can be few-shot deciders and that SAP-RPT-1.6 outperformed purpose-built decision models on real enterprise workflows...
Model Context Protocol (MCP) servers are essential building blocks in agentic engineering scenarios. The MCP protocol is used in the architecture of AI-native or AI-enabled software solutions, and also by the developers building and maintaining said ...
Struggling to find your Joule Work Desktop Admin URL or landed on a link that no longer works? The URL can change over time due to tenant migrations or re-provisioning, so bookmarks quickly become unreliable. In this short guide, learn exactly where ...
A tiny shell script that hooks into Claude Code and sends you a macOS notification (or an Outlook email) the moment a long-running task finishes with Claude's own summary of what was done.
One free attempt at SAP Certified - Joule Studio Developer (C_JSD) until December 31, 2026. How to claim it, how the 24-hour practice window works and what to study first. English and Portuguese.
I connected Claude Code to a real SAP S/4HANA on-premise system through the SAP Cloud Connector and an MCP server on SAP Integration Suite. Here's how a question travels from a prompt to the SAP system, the three things that broke along the way, and...
SAP is expanding its tabular AI capabilities with updates to the SAP-RPT AI model family with the zero-shot time series forecasting model SAP-RPT-TS. It a pretrained tabular foundation model, thus simply by supplying only a snapshot of historical da...
OCR can read text, but enterprise processes need more: document classification, structured extraction, validation, exception handling, and reliable integration. This article explains how SAP Document AI and SAP Integration Suite can work together to ...
Managing Multiple Company Codes with SAP Document AILarge enterprises rarely process documents in a single legal entity. Accounts payable teams handle supplier invoices across dozens of company codes. HR shared services process onboarding documents f...
Installing GitHub Copilot in Eclipse ADT and Connecting it to Enterprise GitHub (GHE)As you already know that GitHub Copilot brings AI-powered code assistance directly into Eclipse ADT, helping developers write code faster and improve productivity.Wh...
As enterprises embrace Agentic AI, a critical architectural question emerges: Should AI agents do everything, or should they work alongside established integration platforms?In this article, I explore how SAP Integration Suite , API-centric integrati...
Use SAP AI Core chat models in VS Code Chat without a Copilot plan. SAPilot handles the connection; model usage still follows SAP AI Core billing or credits.
Joule, Knowledge Graph, Business Data Cloud, AI Agent Hub: what does each one do? A plain-language guide to the components of SAP Business AI and how they work together.
In my earlier articles, we explored how CAP agents can remember useful information across conversations and find relevant passages in documents using vector stores. But knowledge work often continues beyond finding an answer.A project assistant or a ...
Part 3 of 3 — "AI‑Guided Supplier Selection in SAP S/4HANA". Part 1: the in‑transaction assistant (ME51N). Part 2: the SAP BTP + AI Core "brain". This part: the standalone RAP + Fiori Elements app. (Prototype / proof‑of‑concept — a custom extension, ...
Part 2 of 3 — "AI‑Guided Supplier Selection in SAP S/4HANA". Part 1: the in‑transaction assistant (ME51N). This part: the SAP BTP + AI Core service that decides. Part 3: the standalone RAP + Fiori app. (Prototype / proof‑of‑concept — a custom extensi...
Buyers pick the Desired Vendor on a purchase requisition mostly from memory — while the delivery‑performance data that should drive that choice sits unused in S/4. We put an explainable AI recommendation right into ME51N: the moment a material is ent...
I wanted a small LLM on my Mac Mini that writes ABAP SQL. Didn't work out.
I built an internal AI data tool at SAP. It runs on BTP, talks to six live data sources, and lets any PM on my team ask questions in plain English. This is what modern PM work looks like when you treat AI as infrastructure.
What if any business user could query SAP data in plain English no transaction codes, no ABAP, no SQL? In this post, I walk through a reusable MCP pattern that exposes standard SAP tables as natural-language-accessible tools inside Joule Work Desktop...
Five field notes from a few months of agents on top of the ADT API in my S/4HANA 2023 lab, and five questions I would like to hear your answers to.
Most development frameworks put evaluation at the end. For deterministic software, that was late but recoverable. For agentic AI built with coding agents, it is the wrong sequence - and the cost shows up in production, not in the review.
Tracing a battery recall with SAP HANA Graph and testing an AI agent’s remedy plan.
Your agents are running. But are they running right? The final post in the series covers the observability and governance layer that lets enterprise teams answer that question — continuously.
Building a secure AI platform is a solved problem if you never let anyone use it. The hard part is what comes next.The second post in the Security Governance in Action series covers the practitioner layer — using agents, building custom extensions, a...
Most enterprise AI conversations start at the prompt. This one starts earlier.The first post in the Security Governance in Action series covers the trust layer SAP engineers before a user sends a single message — agent validation, governed provisioni...
Using a small AI agent eval to explore double-counting and measures.
This blog explores how companies are putting MCP(Model Context Protocol) into practice, drawing on insights from AGNTCon + MCPCon Europe. It covers protocol evolution, tool discovery, skills and agent execution, alongside our work on Open Resource Di...
Three weeks ago a logistic regression beat eight LLMs at reading job postings. I gave it a rematch against a model built for tables. TabPFN-3.5 beat the lion, beat GPT-6 Astra and Claude Fable on the same postings, ran in 12 seconds per thousand, cos...
Agent-ready Fiori: does WebMCP pay off for an AI Agent?
Enterprise workflows are weighed down by thousands of routine micro-decisions—routing a support ticket, verifying a supplier edit, or flagging an invoice for review. Rigid rule engines become brittle as edge cases multiply, while general-purpose LLMs...
Here are 5 learning resources that helped me get started with SAP Build and Joule Studio this month.
Letting the LLM decide what to fetch works. It's also non-deterministic, sequentially slow, and hard to audit.A short note on declarative pre-fetch as the default for enterprise agents and where tool calling is still the right answer
A CAP Agent can continue a conversation and, with a long-term Memory Store which I made 2 weeks ago, can remember useful information across conversations. But a support agent also needs to answer questions from product guides, troubleshooting notes, ...
A personal location pipeline on SAP HANA Cloud spatial, CAP, RAP and Fiori Elements. Built with Claude Code.
There is a long-standing debate about the use of IA and productivity in the corporate environment. This article explores the real-life experiences of an AI Consultant and how the mix of experience, collaboration, and reskilling generated outstanding ...
Hi. I'm Andréa Molina, an SAP engineer with 20+ years of experience, working hands-on with BTP, UX, and AI. I shared my An Engineering Manifesto for AI-Assisted SAP Development — Let's Build It Together blog with 19 principles, examples and code pat...
Trying the CAP-level agents from the September 2026 CAP release with a custom RAP service.
AI helps us learn and write code. We have been shipping code faster than ever. Someone with no IT background can create software now. But software is not just code. It is structure, security, governance and much more. We deal with sensitive data. An ...
My AI agent could draw boxes, but not SAP. So I gave it the SAP BTP icons and the SAP diagram rules. Meet ARC-DRAW, an open-source MCP server, and see how you can help make it better.
With the announcement that PI-Sheets fall under SAP’s compatibility scope—and therefore usage rights expire at the end of 2030—customers are now faced with an important question: What is the right path forward for existing PI Sheet implementations?
When we started this blog post series, we asked a hard question: how do we keep humans meaningfully involved as AI systems get more autonomous every day? Today, that question is more urgent than ever. SAP’s vision of the Autonomous Enterprise promise...
Are you building or even running a business ABAP Cloud AI scenario as described in Swathy's blog about the ABAP AI SDK powered by ISLM?Embedding Generative AI capabilities directly into ABAP Cloud applications has never been more accessible, and the ...
With SAP TechEd 2026 coming up, explore learning opportunities to build your skills in SAP Business AI and Joule. Discover the future of work with Joule and deepen your understanding of AI reasoning, foundation models, and enterprise knowledge. Cont...
With the September 2026 release of CAP, CAP now has a first-class plugin for building AI agents directly within CAP applications. You can annotate a CDS service with @AGent, expose it through the A2A protocol, use CAP service capabilities such as act...
A Beginner's Guide — For Every SAP Consultant, Every Module, Every Role
SAP has spent 2026 building governance infrastructure for AI agents — a verification workflow through AI Agent Hub, policy enforcement through MCP Gateway. Both promise trust badges and audit trails. Neither can deliver on that promise against an obj...
| User | Count |
|---|---|
| 27 | |
| 10 | |
| 9 | |
| 9 | |
| 9 | |
| 9 | |
| 7 | |
| 7 | |
| 7 | |
| 6 |
ChristophMorgen
:
Zero-shot time series forecasting with SAP-RPT-TS ...
ulka_rathi359f4
denismih
:
CAP Agents that collaborates with humans - Announc...
Harish_Ramachan| Subject | Likes |
|---|---|
| 20 | |
| 9 | |
| 7 | |
| 7 | |
| 6 | |
| 5 | |
| 5 | |
| 5 |
