Reference Layer
Your knowledge.
Their context.
Give your agent the relevant documents so it can answer with your company context and cite its sources.
The widget service uses JWT bearer tokens for auth. After deployment, always verify the /health endpoint returns 200.
Your company context
Your documentation, searchable. Agents read and cite it. You control what they see.
Org-scoped full-text search
Agents search knowledge with keyword FTS. Results are read-only (agents can't write). Search history is durable. You can see what every run retrieved.
Wiki generation
UseAgent builds wikis from your repositories. Structure is validated and repaired (bounded model turns). Published wikis are searchable and retrievable by agents.
Draft-first knowledge capture
High-value runs propose knowledge entries. You review them in the learning lane before publishing. Nothing auto-publishes.
SEE IT WORK
One agent. Real tasks.
UseAgentExample workflowOur widget service returns 500 on DELETE /widgets/:id when the widget has 3 or more linked components. Fix it.
Clone and search
Cloned repo, found DELETE handler in handlers/widgets.ts. Searched error logs. Every 500 has 'permission check failed' after component count check.
Reproduce locally
Set up test DB with 3 linked components, sent DELETE request, confirmed 500. Traced the stack: permission middleware runs after cascade check, causing the 500.
Fix the order
Moved permission check before cascade. Added test case: DELETE with 3+ components now returns 204. Old test suite still green.
Open PR
Created PR #487: 'Fix widget delete with linked components'. Added test case to prevent regression.
Questions, answered.
Can agents modify knowledge?
No. Agents can only read. Knowledge capture happens after the run, via the learning lane, and requires human review before publishing.
How do I add my own docs?
Upload files, link a repository, or create manually. Everything is org-scoped. You can revise or archive entries anytime.
When will vector search work?
Keyword FTS is live now. Vector embeddings (semantic search) are ready to ship pending an OpenAI API key for the org.
Start with one task.
See what you can hand off.
Explore a completed run, or join the early-access list to hear about getting your team started.