SAP-RPT-1.6, Tabular Orchestration, and RPT Playground API: Now Available

SAP-RPT-1.6, Tabular Orchestration and a higher RPT Playground API limit are now live. Together, these cover the full arc from experimentation to production. 

Why Clean Core Became an AI Precondition (Series 3, Part 1: Clean Core + AI)

Clean Core used to be sold as ERP upgrade hygiene. In 2026, it became something closer to a precondition — the RISE with SAP deals closing this year (Airbus, Shell, Morgan Stanley, Eli Lilly) aren't just modernizing infrastructure, they're building t...

From Predictions to Real Decisions: How SAP RPT-1.5 and Joule Agents Orchestrate AI Workflows

A deep-dive into building AI workflows in Joule that turn tabular structured data into key supply chain decision engines using SAP-RPT-1.5 Tabular AI model. 

Your AI Agent Wants to Talk to SuccessFactors. Start With the Security Boundary using MCP | Part - 1

Connect your AI agents (Joule, Claude, Gemini, Cursor etc) with SAP SuccessFactors. Part 2 (architecture) coming soon.

Agent-to-Agent Protocol (A2A): From First Principles to Production

Most AI systems stop at a single agent talking to a single model. A2A is the open protocol that lets agents from different frameworks and teams discover each other, delegate work, and exchange results. This article shows you how to build it from scra...

The Exit Interview Already Knows Who's Leaving. Nobody Reads It Until It's Too Late.

Predicting employee attrition on SAP SuccessFactors-style data, using SAP's open-source ConTextTab (SAP-RPT-1-OSS) to read HR fields as meaning, not just numbers.

The Invoice Already Knows the SAP PO. Artificial Intelligence Finds the Right Line.

The PO is known. The line isn't. That's the real matching problem.Modern eInvoices tell SAP which Purchase Order they belong to, but not the exact PO line. As a result, AP teams spend countless hours manually matching invoice lines during month-end c...

Let's try creating a UI5 Task Form for SAP Build Process Automation using AI.

Hello everyone! Have you tried the newly added AI Chat feature in SAP Build Code yet?It's incredibly convenient, isn't it?I received a request to write a blog post introducing how to use it. However, since it's pretty self-explanatory and others have...

AIを使用してSAP Build Process AutomationのUI5 Task Formを作ってみる

皆様、新たに追加されたSAP Build CodeのAIチャット機能は使ってみましたでしょうか？便利ですね。使い方を紹介するブログを書いてというリクエストがあったのですが、説明するまでも無いでしょうし、CAPやUI5のアプリの作り方を紹介するのも既に他の方がやられているのでなにか無いかと考えたときに、SAP Build Process AutomationのUI5 Task Formは作成できるのかと気になりましたので、AIチャット機能で作れるかやってみました。SAP Build Process...

Humanoidd robots are a catalyst, not the solution

The hype is on on humanoid robots - price drops make them payable, increasing capabilities, better sensors, more computing power and stroner batteries make them affordable and applicable in a variety of use cases - but is the humanoid robot the answe...

SAP Build Code新機能：AI Chat

SAP Build Codeに新機能が搭載されましたのでご紹介したいと思います。この機能はbuild-codeプランあるいはbuild-defaultプランのSAP Business Application Studio (=SAP Build Code)で使用可能な機能です。SAP Business Application Studioのstandardプランでは使用することが出来ません。SAP Build CodeにAI Chat機能としてチャットによるプログラミング・作業アシスト機能が搭載...

How to Connect Claude Code to ABAP with Zero-Config MCP

You might have already seen excellent, master guide on the SAP Community Portal explaining how to link Claude to SAP. While that guide broke open the doors for vibe coding in ABAP, it required developers to manually manage external Node.js projects, ...

Can AI Tell Your FI Ticket from Your MM Ticket? Does BYOM (Bring Your Own Model) helps?

Can a BYOM AI model tell your FI ticket from your MM ticket? A BERT-based classifier trained on SAP support tickets sorts incoming issues into 9 modules. FI, MM, SD, HR, ABAP, BASIS, INTEGRATION, and more with 82%+ accuracy, and gets smarter every ti...

SAP Joule for Developers, ABAP AI capabilities including agentic capabilities is now available!

SAP Joule for Developers, ABAP AI capabilities have already generated strong interest across the SAP ecosystem, enabling customers to achieve remarkable results, as demonstrated by the success story from Bosch.Following our Sapphire announcements, de...

Claude Generates So Much — Here's How I Actually Keep Up

Claude Generates So Much - Here's How I Actually Keep UpAI is producing an almost comical amount of output these days. In a single session, Claude can scaffold a feature, write the tests, refactor two files, explain the architecture, and suggest thre...

Document Grounding Joule Custom Agent using SAP AI Core and Microsoft SharePoint - No AWS S3 Needed

Document Grounding Joule Custom Agent using SAP AI Core and Microsoft SharePoint - No AWS S3 Needed

How I Built an AI Agent That Generates SAP Analytical Artifacts (CDS VDM → Cube → Analytic Query)

How I Built an AI Agent That Generates SAP Analytical Artifacts (CDS VDM → Cube → Analytic Query) via OData — Part 1 of 2: Architecture and First ArtifactHow I stopped writing CDS Views by hand and started generating the whole S/4HANA analytical stac...

Using Claude and GPT-4o in SAP Generative AI Hub: A Complete Setup Guide

Step-by-step guide to deploying Claude Sonnet 4, Claude Haiku 4.5, and GPT-4o through SAP AI Core and the Generative AI Hub — with working Python code, model selection guidance for SAP-specific use cases, and a practical comparison table. Updated fol...

From Manual Testing to AI-Assisted QA in SAP: A Practical Journey

Exploring how AI can actually help in SAP QA, from writing test cases to debugging automation, with real learnings and limitations from my experience.

AI: Steps to Setup Python Programming

Introduction: Python is a general purpose and easy to read high level programming language. Python is used in many areas, including web development, automation, artificial intelligence, and, most importantly, data science it is also skillful at clean...

SAP RPT-1 - Why Enterprise AI Needs More Than Generative Models?

Why Relational Intelligence Is Becoming Mission‑Critical?

Production Agentic SAP Systems: Monitoring, Cost, Failure, and Scale (Series 2, Part 6 - complete)

The final part of the Agentic AI in Practice series covers the production operational layer — agent health monitoring with HANA Cloud metrics, token cost management with hard budget limits, failure handling with exponential backoff and fallback model...

Building AI Agents and Agentic Workflows with Human-in-the-Loop: A Beginner's Guide to Mastra

A hands-on introduction to Mastra, a TypeScript framework for building production-ready AI agents. Learn how to wire up tools, persist conversation memory, and coordinate multi-step workflows using SAP AI Core and Hyperspace AI, all while building a ...

Human-in-the-Loop SAP Agents: Approval, Escalation, and Audit (Series 2, Part 5 of 6)

Five production patterns for keeping humans in control of agentic SAP systems — LangGraph interrupt() approval workflows, confidence-based autonomous vs. escalation routing, smart role-based escalation via Teams and email, timeout and fallback handli...

Agentic Memory Unpacked: Families, Types, Architectures, and Lifecycle

Where do AI agents store what they've learned? How do memories form, evolve, and get retrieved? In the second part of my agentic memory series, I unpack memory families, content taxonomies, organizational architectures, and the full memory lifecycle.

Agentic AI for SAP Data Migration: From Assessment to Sign-Off (Series 2, Part 4 of 6)

Five migration agents built with LangGraph and SAP AI Core covering the full migration lifecycle — landscape complexity assessment, data quality validation with AI-driven ambiguity resolution, migration runbook generation, real-time execution monitor...

How I Connected Claude AI to My SAP ABAP System Using MCP — A Complete Windows Guide

A step-by-step guide to connecting Claude AI directly to your SAP ABAP system using MCP (Model Context Protocol) on Windows. Learn how to install Claude Code CLI, set up two open-source ABAP MCP servers, and configure Claude Desktop to read, write, a...

SAP Agentic AI in Practice: Building the SAP Exception Log Triage Agent (Part 3 of 6)

Router + sub-agent multi-agent system for SAP exception triage — SM21 system log specialist, SM37 job failure specialist, cross-log correlation layer, reactive triage on demand, and proactive monitoring with anomaly detection and auto-escalation via ...

SAP Agentic AI in Practice: Building the SAP Migration Assessment Agent (Part 2 of 6)

From single ReAct agent to LangGraph state machine with conditional routing — assessing custom code, table complexity, configuration footprint, and integration dependencies to produce a scored S/4HANA migration readiness report with human-in-the-loop...

SAP Agentic AI in Practice: Concepts, Architecture, and Your First LangGraph Agent (Part 1 of 6)

What agentic AI means in SAP contexts, when to use an agent vs a skill vs a pipeline, the complete LangGraph + AI Core architecture, and a working ReAct agent that autonomously assesses SAP HANA data quality — all in Part 1 of the new series.

SAP AI Core: Deployment and Configuration Errors and How to Fix Them (Part 2 of 2)

Six deployment and configuration errors after authentication is working — 404 on RUNNING deployments, two AI Core instance confusion diagnosed via resource group instance_id labels, orchestration vs foundation-models scenario mismatch, resource group...

SAP AI Core: Authentication Errors and How to Fix Them (Part 1 of 2)

Six authentication errors between your first curl command and a working SAP AI Core bearer token — PowerShell alias conflicts, curly quote corruption, single quote failures, silent empty responses, missing /oauth/token path, and RBAC denial — with th...

Extracting Structured Knowledge from Document (Sales SOPs) Using LLM— A Plug-and-Play Python App

Sales Standard Operating Procedures (SOPs) are goldmines of organizational knowledge — they define who does what, which products are sold, how deals are closed, and which tools the team uses. But this knowledge is buried in unstructured prose, spread...

SAP Generative AI Hub: Extending Joule with Custom Skills & AI Agents (Part 6 of 6 -Series Complete)

The final part of this series surfaces the AI stack from Parts 1–5 through Joule — building custom Joule skills backed by the CAP service from Part 5, assembling a multi-skill agent for knowledge base Q&A and exception log triage, covering prerequisi...

SAP Generative AI Hub: Building AI-Powered CAP Applications on BTP (Part 5 of 6)

End-to-end architecture for AI-powered SAP extension applications using CAP — project setup, AI Core service binding, HANA Cloud persistence, Generative AI Hub integration in service handlers, SAP Integration Suite connectivity, and Cloud Foundry dep...

SAP Generative AI Hub: RAG on SAP Data with HANA Cloud Vector Store (Part 4 of 6)

End-to-end RAG pipeline on SAP data — REAL_VECTOR schema setup, SAP embedding model via AI Core, document chunking, COSINE_SIMILARITY search, and four working use cases: knowledge base search, data dictionary retrieval, transport log search, and mast...

How I teach Claude Code to work my way

In November 2025, I started using Claude Code differently. Instead of just throwing prompts at it and hoping for the best, I began building skills — little workflow playbooks written in markdown that tell the AI how to approach a problem, not just wh...

Meet RPT-1 — SAP's Quiet Revolution in Enterprise AI

SAP RPT-1 · The next big thing in enterprise AIYour data is smarter than you think.RPT-1 just proved it.Six reasons this changes everything.What if your ERP could predict outcomes without a single data scientist — just by looking at a few example row...

SAP Generative AI Hub: Building Prompt Pipelines for SAP Workflows (Part 3 of 6)

Four multi-step prompt pipelines for real SAP workloads — exception log triage, HANA code review, document processing, and master data enrichment — using sequential chaining and chain-of-thought reasoning with the generative-ai-hub-sdk and LangChain.

Major New Version of the hana-cli: How It Was Built with the Help of AI (and a Lot of Human Review)

AI code generation helped the hana-cli project add more features in two months than I'd been able to deliver in the last two years; but quality still came from discipline, architecture, and a ton of testing.

SAP Generative AI Hub: Using the Python SDK for SAP Data Tasks (Part 2 of 6)

Five working Python code examples for real SAP workloads — exception log summarization, HANA query analysis, ABAP/SQL code generation, master data classification, and structured data extraction — using the generative-ai-hub-sdk across SAP AI Launchpa...

What is Agentic Memory?

Agentic memory enables AI to remember past interactions, but its real value lies in knowing precisely which information to store and when. This article defines the concept of 'agentic memory,' outlines key use cases such as personalization and agenti...

How Metadata Enrichment can enhance SAP HANA Cloud Vector Engine on GenAI scenarios