07RETENTION

Your data, your retention

Your plan sets how long traces are kept and how many events your workspace can capture each month.

Plan-based retention windows — keep data as long as you need.
Clear monthly event limits for every plan.
Export or delete your data on demand.
Predictable limits with an upgrade path as volume grows.

Your data, your retention 🗄️

# retention and monthly event limits follow your plan
trace = captureTrace(
    name="chat-turn",
    metadata={"retention_days": 30},
)

trace.generation(name="openai.chat", model="gpt-4o-mini", input=messages).end(output=reply)

Use your data, your retention in production

Plan-based retention with a clear monthly event allowance. 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