Async research projects with coding agents
Asynchronous coding agents are given open research questions, write and run experiments in a dedicated repo, and report findings.
- Agent or tool
- Claude Code
- Topic
- Software Development
- Reported on
- Blog
- Added
- 2026-10-15
Why it matters
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 221 sightings filed under Software Development on Agent Sightings (number 190 by interest), and one of 255 involving Claude Code.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Claude Code or any similar agent and adjust the details to your situation.
Investigate whether <library> can do <task>. Write small experiments, run them, and commit a README with findings, code and what didn't work.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Source
Read the original first-hand account on Blog: https://simonwillison.net/2025/Nov/6/async-code-research/. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
Browse more like this
Related sightings
- A contractor's personal Claude Code agent allegedly ran inside a secure Pentagon system for two months
- Claude Code's 3-word status line reportedly burns 15 to 20% of tokens
- Office Hours: Asynchronous coding and the end of the IDE with Spotify
- Rocket Money on building agents that fix their own code
- Book the best-priced flight and later refund it
- Build a DIY slide tower with a subagent