Guides
Learn the platform, one piece at a time.
Each guide is self-contained. Follow them in order for the full round-trip, or jump straight to the one you need.
Prompts
Versioned, templated message sets. Move a production alias between versions without redeploying your app.
Read the guideGateway
One OpenAI-compatible endpoint in front of every provider. Bring your own keys; get routing, cost, and caching.
Read the guideTracing
Every call recorded as a trace with spans — model, tokens, latency, cost. Report your own spans too.
Read the guideTools
Callable functions, versioned like prompts, that you attach to a prompt and hand to the model.
Read the guideEvaluation
Build datasets from real feedback or a CSV/JSON file, and run experiments to compare prompt or model versions on quality.
Read the guideAudit
Every recorded change in the team — keys, members, gateway, secrets, prompts and tools — filtered by area, event or person.
Read the guideGet oriented
New here?
Quickstart
From signup to your first rendered, traced LLM call in about ten minutes.
02Core concepts
Prompts, versions, aliases, the gateway, and traces — how they fit together.
03API reference
Every endpoint, curl-verified, with exact request and response shapes.
04Connect Claude with MCP
Manage prompts, run them and read their traces by asking an AI assistant.