Sandbox demo
Your First Multi-Agent Run
A small feature, four agents, one merged PR.
Watch a small feature flow through the full roster: planner reads the issue, builder writes the code, reviewer flags one issue, builder fixes it, deployer ships to staging and opens the PR. Total wall-clock time: about 8 minutes for a feature you'd take an hour on solo.
Sandbox transcript
Press Play to replay this transcript step-by-step.
0 / 10
The transcript is canned — no real API calls. The point is to internalize the loop: user → plan → tool → result → answer.
Check your understanding
Q1. What did the reviewer's flag about COMMIT_SHA prevent?
· Score 100% on the quiz.