Tutorials¶

Welcome to the GEPA tutorials! These hands-on notebooks will help you learn GEPA through practical examples.

Available Tutorials¶

Learn how to use GEPA to evolve entire DSPy programs, including custom signatures, modules, and control flow logic.

DSPy Full Program Evolution - Evolve a complete DSPy program from a basic ChainOfThought to a sophisticated multi-step reasoning system. This tutorial demonstrates how GEPA can improve a program from 67% to 93% accuracy on the MATH benchmark.

ARC AGI Example - Apply GEPA to the ARC (Abstraction and Reasoning Corpus) challenge, demonstrating how to optimize programs for complex reasoning tasks.

For more tutorials, especially those focused on the DSPy integration, see:

dspy.GEPA Tutorials - Official DSPy tutorials with executable notebooks
GEPA for AIME (Math) - Optimize prompts for competition math (+10% improvement on AIME 2025)
GEPA for Structured Information Extraction - Enterprise task optimization
GEPA for Privacy-Conscious Delegation - Papillon benchmark (+9% with just 3 examples)
GEPA for Code Backdoor Classification - AI control applications
GEPA Advanced Guide - Multimodal, custom proposers, and advanced configuration

Non-Obvious Things About GEPA - Deep insights and lessons learned by @realsanketp
Enterprise Agents with DSPy and GEPA - Production deployment patterns by @slavozard
Multi-Agent RAG for Healthcare - Diabetes and COPD agents
Context Engineering for AI Coding Agents - Data analysis agent optimization by @ArslanSAAS
Teaching Small LLMs to Write Fiction - Creative writing with Gemma3-1B
AI Voice Evolution & Authenticity - Multi-objective voice optimization
GEPA in Observable JavaScript - Interactive browser-based GEPA by @tomlarkworthy
OCR Optimization Research - 38% error reduction with Gemini models by Intrinsic Labs
GEPA for AI Code Safety - Tutorial notebook by @hi_ZachParent
Solving Agent Tool Sprawl with DSPy - GEPA optimization of tools and routes
XKCD Comics with DSPy and GEPA - Fun application of GEPA
Databricks Sales Support Multi-Agent - 75% routing accuracy improvement
DeepResearch Agent - LangGraph + DSPy + GEPA research system by @RajaPatnaik
Self-Improving AI Agents - GEPA for orchestration, TRM for reasoning
Context Compression Experiments - GEPA for optimizing context compression prompts by @gridinoc
Google ADK Training with GEPA - Optimizing Google Agent Development Kit agents

DSPy + GEPA Skill - Quick way to try DSPy + GEPA without setup. Simply install and start experimenting! Created by @raveeshbhalla
Arbor: Agent Architecture Discovery - GEPA-integrated tool for discovering optimal agent architectures, well-integrated into DSPy by @NoahZiems

Weaviate: GEPA for Listwise Reranker & Evaluator-Optimizer Pattern - Step-by-step optimization tutorial including fuzzy generative tasks by @hammer_mt
Matei Zaharia at Berkeley AI Summit - GEPA and reflective prompt evolution with few rollouts
Weaviate Podcast #127: Deep Dive on GEPA - High-level overview with Lakshya A. Agrawal
GEPA Paper Walkthrough (ReallyEasyAI) - Detailed paper explanation
Karl Weinmeister: GEPA Short - Quick overview of GEPA for agent improvement

To run these tutorials locally:

# Install GEPA with full dependencies
pip install gepa[full]

# Install Jupyter
pip install jupyter

# Start Jupyter
jupyter notebook

Then navigate to the tutorial notebook you want to run.

Before starting the tutorials, ensure you have:

API Keys: Most tutorials require an OpenAI API key (or other LLM provider)
```
export OPENAI_API_KEY="your-key-here"
```
Python Environment: Python 3.10+ with GEPA installed
```
pip install gepa[full]
```
Optional: Install DSPy for the DSPy-specific tutorials
```
pip install dspy
```