What each station actually does under the hood

Ask modeA read-only mode for asking questions about a codebase without changing files; the safe way to explore unfamiliar or legacy code. Press Enter for the full definition. makes zero file changes: it lets you have a conversation with the codebase. That makes it the safe day-one move for a legacy repo.

Use the real prompt, "explain this repo, use diagrams where appropriate", and let the agent map the monolith. This wins over the senior who worries nobody understands the code.

Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. asks design and scope questions, then pauses when the request conflicts with the repo.

Stage a real gap: the PRDProduct Requirements Document. The spec describing what to build, for whom and why, before implementation starts. Increasingly the artifact you hand an AI agent as the source of truth for a feature. Press Enter for the full definition. assumes authenticated users, but the repo has no auth. The agent asks whether to build auth or ship a local-first V1. That proves it challenges the plan instead of blindly executing it.

A cloud agent can open a browser, test the change, capture a walk-through video plus screenshots and correct its own console errors.

It attaches those artifacts, type-checks and test results to the PR for human review. That evidence makes end-to-end agent work reviewable and supports Cursor's reported ~30-40% internal cloud-agent PR share.

Forked-repo CI checks appear inside the cloud agent UI, where you can ask why a check failed and watch the agent rerun, diagnose and fix it in front of the room.

A first-party automation can start this when CI breaks. The broken check becomes proof that the gate fires while a human keeps the merge key.