GEPA logo

GEPA

Optimize any text — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. If you can measure it, you can optimize it.

blogcmpnd21 Jul 2026

The Unreasonable Effectiveness of Separating the Task from the Model

This talk is about separating the task, the job to be done, from the implementation details: the model, harness, tactics, and other elements that are constantly changing.

Isaac Miller, Maxime Rivest
cmpnd.ai

More in Skills & Prompts

View all tools
Agent Skills logo

Agent Skills

A curated collection of agent-skills

Skills & Prompts
Caveman logo

Caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Token OptimizationSkills & Prompts
Compound Engineering logo

Compound Engineering

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

Skills & Prompts

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.