Engineering
AI Support Agent
From a deployment error to a tested draft fix, before anyone files it.
Reads deployment events, open issues and code to find bugs nobody filed yet. Each one comes back as a draft pull request with a test that fails before the fix and passes after, linked from Linear.
- 40/wkBugs found
- 10/wkDraft fix pull requests
FactoriesProduct bugs
IdleIllustrative runReading
POST /api/checkoutVercel - 1h ago
TypeError: Cannot read properties of undefined (reading 'currency')Fixlib/pricing.ts
Regression test
- Draft pull requests
- 0
- Unconfirmed bugs
- 0
Draft pull requestyour-org/your-app
fix(checkout): price a cart that has no region yet
fix/checkout-missing-region into main
New Linear issue ENG-431, labeled bug
Related solutions
See how teams in this category put agents to work.
Integrations
3 integrations- GitHubConnects in chat
- LinearOptionalConnects in chat
- VercelOptionalConnects in chat
Get started with AI Support Agent
Pick an example, connect your tools, and review the first run.
Set up the AI Support Agent agent template for this project. Follow /SKILL.md for the exact CLI commands.
Goal: A table per run: bug, source, root cause, draft pull request, Linear issue and test result.
1. Install the CLI if it is not on PATH, check that I am signed in, and select my team and project.
2. Connect these integrations when asked: GitHub, Linear (Optional), Vercel (Optional).
3. List the first-party workflow templates. If `triage-line` is listed, instantiate it with `--path.slug triage-line` and start the run; otherwise create a project from this template at /new?template=triage-line&preset=product-bugs.
4. Share the run id, follow the run until it finishes, and summarize its outputs and changes.
Ask me before spending FTAI or changing anything outside this repository.
Launch from Claude Code, Codex, Cursor, and other agents.