Quickstart
Ship a Fuze Agent in five minutes. Sensible defaults, full compliance evidence, no ceremony.
Ship a working agent in five minutes. The defaults are safe, every model call, tool execution, and policy decision still goes through the hash-chained evidence pipeline. Swap in production policies and retention when you're ready; the API doesn't change.
1. Install
2. Get a Mistral key
Sign in at console.mistral.ai, create an API key, and put it in MISTRAL_API_KEY. The free tier is enough to follow this page.
3. Write the agent
Save as agent.ts:
4. Run it
You should see the run status, the structured output, and the number of evidence spans recorded.
5. What just happened
- Hash-chained evidence: each model call, tool execution, and policy decision was recorded as a span.
agent.records()returns the full chain, every record'sprevHashmatches the previous record'shash. - Policy gate ran: the default
quickstartconfiguration uses an allow-allStaticPolicyEngine. You'll see a one-time warning on stderr reminding you to define a real policy before production. - Same evidence shape as production: the only difference between quickstart and a hand-wired agent is who picks the defaults. Tools are classified
public, retention is the shortfuze.quickstart.v1policy, lawful basis isconsent. Switch any of these by dropping back todefineAgent/defineTool.
Next steps
- How it works, the loop, evidence pipeline, and policy gate explained.
- First agent tutorial, define your own tool and verify the chain.
- API reference, the full
defineAgent/defineToolsurface for production use.