🚀 SAP AI Core Agent QuickLaunch Series 🚀 - Part0 Prologue

[Ryota_Ito]

Generative AI has broken out of research labs and is now transforming the way business is done. SAP is moving at full speed to embrace this trend and has launched an agent called Joule. In this blog series, I’ll provide a “super-fast hands-on” guide to help you quickly call default models of SAP AI Core and expand them into practical AI agents for real-world business use, so you can understand how these agents work behind the scenes.

Notice
日本語版はこちらです。

📖What You’ll Learn in This Series

• How to Run a Custom AI Agent on SAP AI Core in Seconds
• Implementation Using LangChain, Google Search Tool, and RAG
• Steps to Convert the AI Agent into a REST API, Integrate It into an SAPUI5/Fiori UI, and Deploy to Cloud Foundry

Time Commitment
Each part is designed to be completed in 10–15 minutes

🗺️ Series Roadmap

• Part 0 Prologue [current blog]
• Part 1 Env Setup: SAP AICore & AI Launchpad
• Part 2 Building a Chat Model with LangChain
• Part 3 Agent Tools: Integrating Google Search
• Part 4 RAG Basics ①: HANA Cloud VectorEngine & Embedding
• Part 5 RAG Basics ②: Building Retriever Tool
• Part 6: Converting the AI Agent into a REST API
• Part 7: Building the Chat UI with SAPUI5
• Part 8: Deploying to Cloud Foundry

If you enjoyed this post, please give it a kudos! Your support really motivates me. Also, if there’s anything you’d like to know more about, feel free to leave a comment!

Prologue: Fast‑Track Roadmap to SAP AI Agents

1 | Introduction

The Gen‑AI wave is hitting enterprise apps—and many SAP developers wonder how to spin up their own AI agents on SAP BTP without drowning in docs. The “SAP AI QuickLaunch” series is a lightning‑fast, hands‑on guide that leverages the default‑deployed OpenAI LLM on SAP AI Core so you can launch an AI agent with minimum steps and maximum learning.

2 | What You Will Build

• Chat UI that supports file uploads, understands their content, and responds accordingly
• AI agent with RAG that cites both Google Search and internal docs
• In subsequent articles, we’ll convert the AI Agent into a REST API and integrate it into the UI built with SAPUI5

Architecture

3 | Who Should Read

• SAP BTP Beginners — especially those new to AI Core
• Python Developers at a basic level
• Hands‑on Learners who value speed over theor
  

4 | Prerequisites

• BTP sub-account
• SAP AI Core instance
• SAP AI LaunchPad Subscription
• Python 3.13 and pip
• VSCode, BAS or any IDE

5 | Next Up

Part 1 Env Setup: SAP AICore & AI Launchpad

In Part 1we’ll connect to SAP AI Launchpad using the service key created for the SAP AI Core instance. Then, we’ll proceed to deploy the LLM for running a chat model — no external OpenAI key required. See you soon!

Disclaimer

All the views and opinions in the blog are my own and is made in my personal capacity and that SAP shall not be responsible or liable for any of the contents published in this blog.