Get started
Start a session
Start a manual coding-agent session with the right repo, branch, prompt, and context.
Use a session when you have a concrete repository change that should move from instruction to reviewable diff. The session owns the sandbox, transcript, branch, validation output, preview, and eventual PR.
Before you start
Have a clear task:
- What should change?
- Which repo and branch should the agent work from?
- What files, screenshots, issues, or product context matter?
- How will you know the result is correct?
Start the run
Select the repository and base branch.
Choose the coding agent and any model/reasoning controls available to your org.
Write the prompt as a concrete task with expected behavior and constraints.
Attach screenshots or files when visual context matters.
Send the session and watch the transcript for progress or questions.
Prompt shape
Good prompts include outcome, constraints, and verification:
Fix the mobile overflow in the session detail header.
Constraints:
- Keep the existing desktop layout.
- Use existing shadcn components and theme tokens.
- Add or update tests for the mobile behavior.
Verification:
- npm run typecheck
- npm run lint
- npm run buildFollow-ups
Sessions are interactive. After a turn completes or pauses, send follow-up instructions instead of starting over. Follow-ups reuse the session context and can continue from the same sandbox when a checkpoint is available.
For agents
When automating against sessions, treat the session as the durable work object. Issues provide context, but the session owns execution state.