Simon Willison • 11/6/2025

Code research projects with async coding agents like Claude Code and Codex

Read Original

This article discusses a pattern for using Large Language Models (LLMs) as asynchronous coding agents for code research. The author explains how agents like Claude Code and Codex can be given a research goal, set to work autonomously in a dedicated GitHub repository, and file a pull request with their findings. This method is effective because the executed code provides definitive answers, making it ideal for testing feasibility and building proofs-of-concept.

0 comments
#Claude Code #LLM Agents #Asynchronous Coding
Code research projects with async coding agents like Claude Code and Codex

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
React vs Browser APIs (Mental Model)
Jivbcoop • 3 votes
2
React, useEffect, and Stale Closures: How to Avoid Them with Dependencies and useRef
Jivbcoop • 2 votes
3
Building Type-Safe Compound Components
TkDodo Dominik Dorfmeister • 2 votes
4
Using Browser Apis In React Practical Guide
Jivbcoop • 1 votes
5
Better react-hook-form Smart Form Components
Maarten Hus • 1 votes
6
Introducing RSC Explorer
Dan Abramov • 1 votes
7
The Pulse: Cloudflare’s latest outage proves dangers of global configuration changes (again)
The Pragmatic Engineer Gergely Orosz • 1 votes