Showcase¶
Discover how organizations and researchers are using GEPA to optimize AI systems across diverse domains. These examples showcase the versatility and impact of reflective prompt evolution.
Living Document
This page is continuously updated with new use cases from the community. Have a GEPA success story? Share it on Discord, Slack, or Twitter/X!
Quick Navigation:
- Enterprise & Production
- AI Coding Agents & Research Tools
- Domain-Specific Applications
- Advanced Capabilities
- Research & Academic
- Media & Press Coverage
- Emerging Applications
- Community Integrations
- Infrastructure & DevOps
- Creative & Generative
- Data Processing & Synthesis
- Community Tutorials
- International Coverage
Enterprise & Production¶
-
DataBricks: 90x Cost Reduction
DataBricks achieved 90x cheaper inference while maintaining or improving performance by optimizing enterprise agents with GEPA.
Key Results:
- Open-source models optimized with GEPA outperform Claude Opus 4.1, Claude Sonnet 4, and GPT-5
- Consistent 3-7% performance gains across all model types
- At 100,000 requests, serving costs represent 95%+ of AI expenditure—GEPA makes this sustainable
-
Dropbox Dash: 45% NMSE Reduction for Relevance Judging
Dropbox used GEPA to optimize their Dash search relevance judge, achieving 45% NMSE reduction on gpt-oss-120b and reducing model adaptation time from weeks to days. For the small gemma-3-12b model, GEPA cut malformed JSON from 40% to under 3% while improving NMSE from 46.88 to 17.26.
Key Results:
- 45% NMSE improvement on gpt-oss-120b (8.83 → 4.86)
- gemma-3-12b: malformed JSON 40% → <3%, NMSE 46.88 → 17.26
- Model adaptation time: 1-2 weeks → 1-2 days
- 10-100x more data labeling at equivalent costs
-
OpenAI Cookbook: Self-Evolving Agents
The official OpenAI Cookbook (Nov 2025) features GEPA for building autonomous self-healing workflows.
What You'll Learn:
- Diagnose why agents fall short of production readiness
- Build automated LLMOps retraining loops
- Combine human review, LLM-as-judge evaluations, and GEPA optimization
-
HuggingFace Cookbook
Comprehensive guide on prompt optimization with DSPy and GEPA.
What's Inside:
- Setting up DSPy with language models
- Processing mathematical problem datasets
- Building Chain-of-Thought reasoning programs
- Error-driven feedback optimization
-
Google ADK Agents Optimization
Tutorial on optimizing Google Agent Development Kit (ADK) agents using GEPA for improved performance.
Key Topics:
- Optimizing agent SOPs (Standard Operating Procedures)
- Integrating GEPA with ADK workflows
- Production deployment patterns
-
Comet-ml Opik Integration
GEPA is integrated into Comet's Opik Agent Optimizer platform as a core optimization algorithm.
Capabilities:
- Optimize prompts, agents, and multimodal systems
- Works alongside MetaPrompt, HRPO, Few-Shot Bayesian optimizers
- Automates prompt editing, testing, and tool refinement
-
BAML Prompt Optimization
BAML integrates GEPA into
baml-cli optimizefor test-driven prompt optimization with multi-objective support (accuracy, latency, tokens). -
Prompt Optimization with Pydantic AI
Tutorial demonstrating GEPA integration with Pydantic AI using
Agent.override()for instruction injection and Pydantic Evals for parallel evaluation.Results: Contact extraction improved from 86% → 97% accuracy
AI Coding Agents & Research Tools¶
-
Production Incident Diagnosis
Arc.computer's ATLAS system uses GEPA-optimized agents to teach LLMs to diagnose production incidents.
Application:
- Automated root cause analysis (RCA)
- Dynamic collection of logs, metrics, and databases
- Reduces manual burden on on-call engineers
-
ATLAS Augmented: +142% Student Performance
GEPA can augment even RL-tuned models. The Intelligence Arc team uses GEPA in their ATLAS framework to improve an already powerful and RL-tuned teacher model.
Key Result:
- +142% student performance improvement when guided by the GEPA-improved teacher
- Demonstrates that GEPA works alongside RL, not just as an alternative
- Shows GEPA's value even for already-optimized models
-
Data Analysis Coding Agents
FireBird Technologies optimized their Auto-Analyst platform using GEPA for improved code execution.
Architecture:
- 4 specialized agents: Pre-processing, Statistical Analytics, Machine Learning, Visualization
- Optimized 4 primary signatures covering 90% of all code runs
- Tested across multiple model providers to avoid overfitting
-
Backdoor Detection in AI Code
GEPA enables AI control research by optimizing classifiers to detect backdoors in AI-generated code.
Approach:
- Trusted monitoring using weaker models
- Classification based on suspicion scores
- Safety measured by true positive rate at given false positive rate
-
AI Code Safety Monitoring
GEPA enables monitoring safety of AI-generated code through optimized classifiers.
Capabilities:
- Detect potentially unsafe code patterns
- Monitor code generation in real-time
- Improve detection accuracy with reflective optimization
-
DeepResearch Agent
A production-grade agentic research system combining LangGraph + DSPy + GEPA.
Pipeline:
- Query planning with diverse search queries
- Parallel web search via Exa API
- Summarization, gap analysis, and iterative research rounds
- Module-specific GEPA optimization for each agent role
Domain-Specific Applications¶
-
Healthcare Multi-Agent RAG
Building multi-agent RAG systems for diabetes and COPD using DSPy and GEPA.
System Design:
- Two specialized subagents (disease experts)
- Vector database search for medical documents
- ReAct subagents individually optimized with GEPA
- Lead agent for orchestration
-
OCR Accuracy: Up to 38% Error Reduction
Intrinsic Labs achieved significant OCR error rate reductions across Gemini model classes.
Models Improved:
- Gemini 2.5 Pro
- Gemini 2.5 Flash
- Gemini 2.0 Flash
A grounded benchmark for document-understanding agents under operational constraints.
-
Market Research AI Personas
Simulating realistic focus groups with GEPA-optimized AI personas for market research.
Benefits:
- Eliminates geographic constraints and facility costs
- No moderator bias
- Tests across different personality types
- Research timelines: weeks → hours
-
Fiction Writing with Small Models
Teaching Gemma3-1B to write engaging fiction through GEPA optimization.
Demonstrates that small models can handle creative tasks with the right prompts.
Advanced Capabilities¶
-
Multimodal/VLM Performance (OCR)
GEPA improves Multimodal/VLM Performance for OCR tasks through optimized prompting strategies.
-
Agent Architecture Discovery
GEPA for automated agent architecture discovery - finding optimal agent designs through evolutionary search.
-
Adversarial Prompt Search
GEPA for adversarial prompt search - discovering edge cases and failure modes in AI systems.
Advanced application for AI safety research
-
Unverifiable Tasks (Evaluator-Optimizer)
GEPA for unverifiable tasks using evaluator-optimizer patterns where ground truth is unavailable.
Research & Academic¶
-
Berkeley AI Summit: GEPA Deep Dive
@matei_zaharia presents GEPA at Berkeley AI Summit, explaining how reflective prompt evolution works even with few rollouts.
Key Insight:
"FLOPs are getting cheaper, but rollouts for complex agentic tasks are not. The next frontier of AI will be limited by rollouts budget!"
-
NeurIPS 2025 Workshop: 12.5% → 62.5% Gains
Veris.AI used GEPA in their RAISE framework to achieve 12.5% → 62.5% gains in task correctness accuracy, demonstrating GEPA's immediate practical impact for training reliable domain-specific AI agents through simulated environments.
Key Results:
- RAISE: Simulation-first experiential learning framework
- GEPA prompt optimization for 4 epochs
- Poster session at NeurIPS 2025 San Diego
-
100% on Clock Hands Problem
Achieving perfect accuracy on the challenging clock hands mathematical reasoning problem using GEPA optimization.
Application:
- Complex spatial reasoning
- Mathematical problem-solving
- Demonstrates GEPA on hard reasoning tasks
-
Prompt Optimization Makes Misalignment Legible
Biddulph & Carroll (MATS 8.0 / ICML submission) show that GEPA's optimized system prompts verbalize reward-hacking strategies in plain English, making misalignment detectable and removable — unlike RL, where learned strategies are opaque.
Key Findings:
- GEPA prompts that reward-hack also describe the hack in the prompt text
- Sanitizing the prompt (removing misaligned instructions) stops the hacking
- Tested on Hinted MMLU, Targeted Sycophancy, and other environments
-
Automated Risk-of-Bias Assessment of Clinical Trials
Li, Mathrani & Susnjak (2025) use GEPA to optimize prompts for risk-of-bias assessment across 7 RoB domains and multiple LLMs, achieving 30–40% improvement in key domains over manually crafted prompts.
Key Results:
- Highest overall accuracy across 100 randomized controlled trials
- Models: Mistral Small 3.1, GPT-oss-20b, GPT-4 Nano/Mini
- Inspectable execution traces via DSPy + GEPA
-
Clinical NER: GEPA vs Domain-Specific Transformers (IEEE BigData 2025)
Varghese & Shang (University of Missouri, IEEE BigData 2025) benchmark GEPA optimization against fine-tuned Bio+ClinicalBERT on the n2c2 Track 2 ADE dataset, reporting up to 12.5% improvement in zero-shot clinical NER from GEPA optimization.
Key Results:
- GEPA improved zero-shot F1 by up to 12.5%
- Switching reflection model from GPT-4o-mini to GPT-4.1-mini raised few-shot F1 from 41.4% to 45.4%
- Fine-tuned domain models still lead, but GEPA narrows the gap without any training data
-
Empowering Small Models for GPU Parallelization
Jhaveri & Lopes (2026) use GEPA to evolve prompts so that small "nano" LLMs can generate correct OpenACC pragmas, improving GPT-4.1 Nano compilation rate from 66.7% to 93.3% and GPT-5 Nano to 100% on the PolyBench suite.
Key Results:
- 21% increase in programs achieving GPU speedups over CPU
- GEPA makes cheap models match expensive ones on HPC code generation
-
Prompt Optimisation for Error Detection in Medical Notes
Myles, Schrempf & Harris-Birtill (2026) use GEPA as the primary optimization method, improving GPT-5 accuracy from 0.669 to 0.785 and Qwen3-32B from 0.578 to 0.690 on the MEDEC benchmark, approaching medical doctor performance.
Key Results:
- ~17–20% relative accuracy gains from GEPA optimization
- State-of-the-art on clinical error detection
Media & Press Coverage¶
-
VentureBeat: GEPA Optimizes LLMs Without Costly RL
VentureBeat coverage of GEPA's approach to optimizing LLMs without expensive reinforcement learning.
Highlights:
- Explains reflective prompt evolution to a broader audience
- Discusses cost and efficiency benefits
- Industry perspective on GEPA's impact
-
DAIR.AI: Top AI Papers of the Week
GEPA featured in DAIR.AI's "Top AI Papers of The Week" roundup, alongside other breakthrough research.
Recognition:
- Listed among Graph-R1, AlphaEarth, Self-Evolving Agents
- Highlighted natural language reflection approach
-
DSPy Weekly Newsletter
GEPA regularly featured in the DSPy Weekly newsletter, tracking adoption and new use cases.
Coverage:
- Issue #4: "GEPA is 🌶️🔥 and on a hype 🚄 as people discover GEPA"
- Regular updates on community applications
-
LinkedIn AI Talk: Automatic Prompt Optimization
Vaibhav Gupta (CEO @ Boundary / BAML) provides a detailed GEPA tutorial, first explaining the algorithm and then walking through a code example.
What's Covered:
- GEPA algorithm explanation
- Step-by-step code walkthrough
- Practical implementation guidance
Emerging Applications¶
-
The State of AI Coding 2025
GEPA was highlighted in Greptile's comprehensive State of AI Coding 2025 report as a key advancement in AI coding capabilities.
Key Insight:
GEPA evolves prompts via trace analysis, matching RL performance with far fewer rollouts—making it ideal for coding agent optimization.
-
Model Migration Workflows
GEPA is proving valuable for migrating existing LLM-based workflows to new models across model families.
Pattern:
- Keep your DSPy program structure
- Change only the LM initialization
- Re-run GEPA optimization for the new model
- Much faster than manually re-tuning prompts
This is especially useful as new models are released and organizations need to migrate quickly.
-
Evaluator-Optimizer Pattern
@hammer_mt shares the powerful Evaluator-Optimizer pattern for fuzzy generative tasks where evals are informal and subjective.
Use Case:
- Creative writing tasks
- Persona generation
- Tasks without ground-truth labels
-
Program Synthesis & Kernel Optimization
GEPA shows promise for program synthesis tasks:
Applications:
- CUDA kernel optimization
- AMD NPU kernel generation
- Outperforms RAG and iterative refinement (Section 6 of paper)
Especially valuable for tasks with expensive rollouts (simulation, long runtime).
-
GPU Parallelization (OpenACC)
Jhaveri & @cristalopes applied GEPA to GPU optimization, targeting OpenACC parallelization.
Results:
- Boosted GPT-5 Nano to generate pragmas improving compilation success from 87% → 100%
- Models saw up to 50% increase in # functional GPU speedups
Demonstrates GEPA's applicability to code synthesis beyond prompts.
-
Material Science Applications
GEPA being explored for material science workflows where simulations are costly.
Why GEPA:
- High sample efficiency
- Works with expensive evaluation functions
- Can optimize simulation parameters
Exploratory use case from the research community
-
Continuous Learning & Self-Improvement
GEPA enables continual learning patterns:
Emerging Pattern:
- Deploy optimized agent
- Collect feedback from production
- Batch feedback and re-optimize
- Redeploy improved agent
Works alongside RL (see BetterTogether paper) for even better results.
-
Letta: Continual Learning in Token Space
Letta's blog post explores continual learning in token space, discussing how GEPA and similar approaches enable agents to learn and improve over time.
Concepts:
- Memory-augmented agents
- Long-term learning patterns
- Token-space optimization
Community Integrations¶
-
Weaviate Podcast #127: Deep Dive on GEPA
Comprehensive podcast episode covering GEPA in depth with Lakshya A. Agrawal.
Topics Covered:
- Natural Language Rewards
- Reflective prompt evolution principles
- Production deployment patterns
-
Weaviate GEPA Hands-On Notebook
Interactive notebook demonstrating GEPA for reranking optimization in RAG pipelines.
What's Inside:
- End-to-end GEPA optimization
- Integration with Weaviate vector store
- Practical reranking examples
-
LangStruct GEPA Examples
Strong examples demonstrating GEPA's effectiveness with Gemini Flash and other models.
-
GEPA in Go
Full Go implementation of DSPy concepts including GEPA optimization.
Features:
- Native Go implementation
- MIT licensed
- Includes CLI tools and examples
-
Observable JavaScript
Interactive JavaScript notebooks exploring GEPA for web-based optimization.
By Tom Larkworthy (Tech Lead, formerly Firebase/Google)
Explore reflective prompt evolution directly in your browser.
-
Context Compression
Experiments using GEPA for context compression to reduce token usage while maintaining quality.
Explore novel approaches to efficient prompt engineering.
-
bandit_dspy
DSPy library for security-aware LLM development using Bandit principles.
Part of the EvalOps ecosystem for AI evaluation and development tools.
-
SuperOptiX-AI
SuperOptiX uses GEPA as its framework-agnostic optimizer across multiple agent frameworks including DSPy, OpenAI SDK, CrewAI, Google ADK, and more.
Infrastructure & DevOps¶
-
Multi-Cloud Data Transfer Cost Optimization
The ADRS team used GEPA to minimize multi-cloud data transfer costs.
Results:
- GEPA autonomously evolved a naive replication strategy into a sophisticated "shared-tree" topology
- 31% cost reduction with just $5 of optimization spend
- Demonstrates GEPA's ability to optimize complex infrastructure configurations
-
Sales Support Multi-Agent Routing
Databricks used GEPA to optimize a sales-support multi-agent system's routing component.
Key Results:
- 75% relative gains in routing accuracy
- Demonstrates multi-agent orchestration optimization
- Production-ready deployment patterns
-
Self-Improving Agent Systems (GEPA + TRM)
Building self-improving AI agents that combine GEPA with TRM (Test-time Reasoning Modification) for both orchestration optimization and reasoning enhancement.
Architecture:
- GEPA for orchestration/prompt optimization
- TRM for reasoning enhancement
- Continuous monitoring and feedback loops
- Automated retraining without human intervention
Creative & Generative Applications¶
-
AI Voice/Persona Discovery
GEPA's multi-objective guided optimization can find an authentic "AI voice" using an 8-dimensional score representing different voice characteristics.
Dimensions Optimized:
- Point of view
- Authority level
- Cadence and rhythm
- And 5 more characteristics
-
Human-Like Response Generation
GEPA+DSPy can optimize AI to generate human-like responses, passing sophisticated detection systems.
Application:
- More natural conversational AI
- Better user engagement
- Authentic persona maintenance
Community-reported application
-
Non-Obvious GEPA Insights
Deep dive into non-obvious lessons learned from practical GEPA usage, covering edge cases, unexpected behaviors, and advanced patterns.
Data Processing & Synthesis¶
-
Synthetic Data Generation
Use GEPA to optimize query generation pipelines for creating high-quality synthetic datasets.
Example: Sanskrit NLP
- GEPA+DSPy optimizes a query generation pipeline
- Differentiates between document pairs
- Generated 50k samples for Gemma embedding fine-tuning
-
Text2SQL Optimization
GEPA has been successfully used for Text2SQL tasks with a system prompt/user prompt breakdown.
Pattern:
- System prompt specifies the task (evolved by GEPA)
- User prompt contains dynamic content
- Alternatively: use DSPy signature for text2sql
-
Enterprise Agents Blog
Building enterprise agents for real-world workflows with GEPA: tackling unstructured data, task decomposition, and context blowup.
Key Topics:
- Modular agent design
- Low-data optimization strategies
- Cost-effective deployment
Community Tutorials & Guides¶
-
DSPy 3 + GEPA: Advanced RAG Framework
Comprehensive guide on building powerful AI agents with DSPy 3 and GEPA.
What's Covered:
- Auto reasoning and prompting
- Step-by-step agent building
- Professional-level RAG optimization
-
Teaching AI to Spot Fake XKCD Comics
Fun, accessible explanation of GEPA concepts with XKCD-inspired visualizations.
-
20% Improvement in Structured Extraction with DSPy + GEPA
Achieving 20+ percentage-point improvement in exact match accuracy for structured extraction tasks using DSPy and GEPA.
Key Insight:
The benefit is not only improved performance, but that optimization allows transferring capability to cheaper models while retaining acceptable accuracy, improving the cost profile of applications.
-
GEPA Impact Analysis: 81% → 90% Accuracy
Practical analysis achieving 81% → 90% accuracy on sales call transcript analysis in just 3 hours and ~$0.50.
Key Insight:
"I stopped thinking of prompts as things I write and started thinking of them as things I evolve. My job shifted from 'craft the perfect prompt' to 'define what good looks like and let the system find it.'"
GEPA's genetic mutations work best with precise feedback—targeted feedback like "you're conflating greetings with rapport" produces targeted fixes.
-
Lakshya's GEPA Blog
Personal blog post explaining GEPA concepts and applications.
-
GEPA for De-identification
Tutorial on using GEPA for PII de-identification tasks with DSPy.
-
SQL Generator with GEPA
Building optimized Text2SQL systems with DSPy and GEPA.
International Coverage¶
GEPA has gained significant attention in the global AI community, with tutorials, blogs, and discussions in multiple languages.
-
Japanese AI Community
GEPA has seen strong adoption in the Japanese AI community with multiple tutorials and explanations.
Resources:
- GEPA Explained (Japanese) - Video explaining GEPA's reflective learning approach
- MLflow + GEPA on Databricks Free Edition - Qiita tutorial
- Naruto-Style Dialogues with GEPA - Creative application
- Multiple AI Daily News Japan features
-
Chinese AI Community
GEPA has been featured in Chinese AI publications and discussions.
Resources:
- GEPA Revolutionary Breakthrough - 35x efficiency improvement explained
- Technical translations and explanations
Get Started¶
Ready to optimize your own AI systems with GEPA?
-
Quick Start Guide
Get up and running with GEPA in minutes.
-
Create Custom Adapters
Integrate GEPA with your specific system.
-
API Reference
Complete documentation of all GEPA components.
-
Join the Community
Connect with other GEPA users and contributors.