teched2025-AI161
An SAP TechEd 2025 hands-on session that benchmarks, evaluates and optimises prompts across models with the generative AI hub capability in SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp.
The exercises work from the generative AI hub capability in SAP AI CoreSAP AI CoreSAP's AI service on BTP: the runtime for AI assets, and through the Generative AI Hub inside it the access to foundation models, the orchestration service with its templating, masking, filtering and grounding modules, the Prompt Registry and Document Grounding.sap official, btp — its prompt editor, prompt registry and benchmarking tools — from inside SAP AI LaunchpadSAP AI LaunchpadThe SaaS front end over SAP AI Core on BTP: a Model Library, Grounding Management for document pipelines, Workspaces that connect AI runtimes, and ML Operations for the lifecycle of a scenario.sap official, btp, where a prompt is evaluated, optimised and compared across models on one surface. After a getting-started step, four exercises run in order: setup, evaluate the original prompt, optimise it, evaluate the optimised one. It runs against an SAP AI Launchpad instance and a technical user the session provides, and the README says repeating it outside the session needs your own SAP AI Launchpad instance.
Facts
Where it sits
Who is behind it
In the atlas: maintains 222@SAP-samplesmaintainerAjay SorengContributes to this
In the atlas: contributes to 36@ajaysorengAjinkya PatilContributes to this
In the atlas: contributes to 112@ajinkyapatil8190fdobrigkeitContributes to this
In the atlas: contributes to 1@fdobrigkeitGajraj MohiniContributes to this
In the atlas: contributes to 1@gajraj-mMaheswar147Contributes to this
In the atlas: contributes to 1@mahesh12393sam-1-0Contributes to this
In the atlas: contributes to 1@samruddhi-106 contributors
What it declares
Every artifact
- Type
- Sample
- Origin
- By SAP
- Use as
- A reference
As a sample
- Form
- Workshop or CodeJam material
Connections
Checking an AI feature still behaves after a model or prompt change
AI runtime on BTP with the Generative AI Hub
SaaS front end over SAP AI Core
Download
README
quoted from SAP-samples/teched2025-AI161 under Apache-2.0, readAI161 - Hands-on: Benchmark, evaluate, and optimize prompts across models
Description
This repository contains the material for the SAP TechEd 2025 session called AI161 - Hands-on: Benchmark, evaluate, and optimize prompts across models.
Overview
This session introduces attendees to our new AI Core services for prompt optimizations and evaluation.
Get hands-on experience with the prompt editor, registry, and benchmarking tools available from the generative AI hub capability in SAP AI Core. You can compare models, evaluate performance, and optimize prompts. Learn how to build resilient, model-agnostic AI workflows and avoid vendor lock-in.
Requirements
The exercise is designed to be done in the SAP AI Launchpad. For the Hands-on session it is designed for we have provided an SAP AI Launchpad and a technical user to login. If you want to repeat this tutorial outside of the hands-on session you will require your own AI Launchpad instance.
Exercises
Let's get started with the exercises!
- Getting Started
- Exercise 1 - Setup
- Exercise 2 - Evaluate the original prompt
- Exercise 3 - Optimize the original prompt
- Exercise 4 - Evaluate the optimized prompt
IMPORTANT
Contributing
Please read the CONTRIBUTING.md to understand the contribution guidelines.
Code of Conduct
Please read the SAP Open Source Code of Conduct.
How to obtain support
Support for the content in this repository is available during the actual time of the online session for which this content has been designed. Otherwise, you may request support via the Issues tab.
License
Copyright (c) 2025 SAP SE or an SAP affiliate company. All rights reserved. This project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the LICENSE file.
Details
Sources
Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.
Compatibility and provenance
History in the atlas
- First seen.
For your agent
- Ref
artifact:sap-samples-teched2025-ai161- JSON
- /artifacts/sap-samples-teched2025-ai161.json
- MCP
- Connecting an agent