Agent Runs
How the SpecSource agent works and what it produces.
An agent run is a single execution of SpecSource's AI. It reads a Linear issue, gathers context from your connected tools, and writes a detailed specification.
What triggers a run
- Manual — Click "Run Agent" in the dashboard
- Schedule — Runs on a recurring interval
What happens during a run
- Read the issue — Extracts the issue description, labels, and context from Linear
- Check error data — Searches Sentry for related errors, stack traces, and event history
- Gather code context — Searches GitHub for relevant source files, recent commits, and PRs
- Search for team context — Finds related Slack discussions and prior investigations
- Check for duplicates — Compares against existing Linear issues using embedding-based semantic matching
- Write the specification — Synthesizes all context into a structured specification
- Enrich the Linear issue — Updates the issue with the detailed specification
Each step is logged and visible in the run detail view.
Run statuses
| Status | Meaning |
|---|---|
| Pending | Queued, waiting to execute |
| Running | Currently gathering context and writing the specification |
| Completed | Finished successfully |
| Failed | Something went wrong (check the error message) |
| Unpaid | Credits exhausted — the run was not executed |
Viewing results
Click any run in the Agent Runs page to see:
- Each step the agent took
- What data it found
- The specification it wrote (with a link to Linear)
- Token usage and duration