One agent writes the fix, another reviews it: a two-agent code review workflow in Slack

Al_Grigor · x · 2026-09-26

In a DataTalksClub workshop, Louis Amaudruz demonstrated an agent cross-review setup by putting two different agents in the same Slack channel: a Claude Code agent fixed a GitHub issue and opened a pull request, while a Codex agent reviewed the change. The core question: when one AI agent writes the code, should a different AI review it? Using models from different vendors adds a degree of independence that mimics human review.

Original post →

More from coding & agent

coding & agent channel →