# Agent In the Loop

- **Event:** [Hackathon: Build Your AI Teammate with CodeRabbit & Cline](https://cerebralvalley.ai/e/build-ai-teammates-hackathon)
- **When:** Sep 13 at 9:00 AM – Sep 14 at 5:00 PM (PDT)
- **Where:** Location TBA
- **Team:** [Andres Nino](https://cerebralvalley.ai/u/andres)
- **GitHub:** https://github.com/AndresNinou/agent-in-the-loop
- **Demo video:** https://www.canva.com/design/DAGy-s7bUKw/-mibwqUOVUCwXZ8tQXcy5A/edit?utm_content=DAGy-s7bUKw&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton
- **Gallery:** https://cerebralvalley.ai/e/build-ai-teammates-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/build-ai-teammates-hackathon/hackathon/gallery/19

Agent in the Loop — Orchestrate. Verify. Ship. (controsl and runs vscode isolated extensions and controls E2E)

Tired of “Fixed! ✅” that isn’t? Agent in the Loop is a control-room for autonomous coding agents that kills false positives and surfaces only work that’s actually done.

We launch isolated VS Code environments in parallel, pairing Cline (implementer) with CodeRabbit (reviewer). A referee routes messages via MCP tools—cline, coderabbit, claude-code—and accepts one truth source: make verify. If it isn’t green, it isn’t real.

Why it works:

Parallel orchestration: multiple agent instances attack the task from different angles.

Independent QA: claude-code runs make verify in a clean env—no excuses.

Evidence-first UI: QA chips, diff preview, and a concise trail of agent messages.

Reviewer in the loop: rework is automatic; you only review when it’s verified.

Stop babysitting tests. Start reviewing results. Turn 0.5× days back into 10× output.

---

Markdown version of https://cerebralvalley.ai/e/build-ai-teammates-hackathon/hackathon/gallery/19. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt