01INSTRUMENT

Trace any app in 5 lines

The fastest way to see what your AI app is actually doing. Add two HTTP calls or install the Currai coding-agent skill — the first captured session appears immediately.

No Currai runtime dependency or framework lock-in.
Create sessions and nested events with two language-neutral endpoints.
Use short timeouts so telemetry never blocks a product request.
Add sampling and redaction for production.

↗Instrument your app

Send your first trace 🧵

from app.telemetry import captureTrace

# captureTrace POSTs to Currai's native HTTP endpoints
trace = captureTrace(name="chat-turn", user_id="user-1")
trace.update(metadata={"app_version": "1.4.0"})

Use trace any app in 5 lines in production

Send sessions and agent events from any language with native HTTP. Currai keeps this information connected to the conversation, user, session, and supporting trace so product and engineering teams can investigate the same evidence.

Start with one production workflow, verify the captured data, and use the resulting evidence to find recurring friction, debug failures, and measure whether each release improves the agent experience.

Follow the Currai getting-started guide to connect a real agent, then review the AI agent monitoring playbook for a practical production workflow.

↗Get Started