Review your first conversations in Inbox
Use the first live transcripts in Inbox to confirm routing, answer quality, and the places where the rollout still needs guardrails.
Read a small sample deeply
The first few live conversations matter more than a large transcript pile. Read them end to end so you see how the agent opens, resolves, and escalates.
Look for friction: slow starts, unclear policy language, or turns where the customer asked something the knowledge base did not cover.
Label what went right and wrong
- Correct answer with clear supporting context.
- Correct escalation when the agent should stop.
- Missing knowledge or a vague answer that needs cleanup.
Set a review rhythm for the first week
Daily review is enough for phase one. The important thing is consistency: identify what to fix, update the right Agent Builder section, and then verify the change in the next transcript sample. For recurring behavior gaps, capture the fix as a memory in Train.
Why are there no conversations in Inbox after setup?
The usual causes are a disconnected channel, no real test traffic, or a route mismatch between the live channel and the intended agent. Check channel health first, then send a real message.
Read your first analytics baseline
Use the first Analytics pass to understand demand, activity, and where the workspace is healthy versus merely configured.
Manage workspace settings and access
Keep the workspace operable by confirming who owns rollout decisions, who can change configuration, and where tenant settings affect the live experience.
Understand billing and usage basics
Read plan posture, capacity, and early usage signals in Billing without turning the first pass into a finance project.