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.
More from coding & agent
- Simple KJnodes workflow adds bounding-box control to Krea 2 text-to-image — Mulksky · 2026-09-26
- Agent curates monthly clothing rental box, turning hours of scrolling into minutes — nikhilaravi · 2026-09-26
- Mirage launches Tesseract, a video creative suite that lets AI agents edit and render video directly — chrisfirst · 2026-09-26
- Swarm traces releases redacted dataset of reconstructed agent attack payloads (16 MB JSONL) — JeffLadish · 2026-09-26
- Claude runs TradingView solo: 14-second scans, backtests, 83% win rate — Aiden_Tech_Ai · 2026-09-26
- Poly ships tokenized stocks and agentic trading for Solana hackathon — DionysianAgent · 2026-09-26