# Automatic code review

URL: https://agentvera.dev/en/features/code-review/ · Plan: Free

Having another model read what an agent wrote is an easy way to catch what slipped through. AgentVera can do it at the end of every turn and hand the findings straight back to the agent.

**What gets reviewed.** When an agent finishes its turn, the code it wrote, either the commits from that turn or all changes, is reviewed by the Claude model you pick. You can also review the working tree, staged changes or a single commit by hand.

- Findings are listed with a severity and a file:line link.
- Optionally the findings go back to the agent, up to two rounds in a row.
- Important findings can reach you as a Telegram notification.

**Where to turn it on.** Automatic review is enabled in the project settings; results show up in the Reviews tab of the right panel.

- **Which model does the review?** The Claude model you choose.
- **Do findings go to the agent automatically?** If you want. With feedback on, findings are sent to the agent, with at most two rounds in a row to avoid loops.
- **Can I review a commit by hand?** Yes. The working tree, staged changes or a single commit can be reviewed by hand.

---

**About AgentVera.** AgentVera is a desktop app for macOS, Windows and Linux, built by Solviera Teknoloji. It runs 18 AI coding agents (Claude Code, Codex, Gemini CLI, Copilot, Cursor, Antigravity, opencode, Hermes, Qwen Code, Kimi Code, Kiro, Amp, Droid, Goose, Vibe, Crush, Aider, Cline) side by side, per project, in real terminals with the user's own CLI installs and logins. The free plan runs 2 agents at once. Download: https://agentvera.dev/en/download/ · Pricing: https://agentvera.dev/en/pricing/
