SemAgentReports
Admin Panel → Reports shows how the widget is doing: conversation volume, resolution rate, satisfaction and the mix of questions.
Headline numbers
| Measure | Window |
|---|---|
| Conversations | the date range you picked |
| Open conversations | right now |
| Human takeovers | all time |
The date range does not affect everything, and the screen says so. Your range only affects the conversation count and the question categories. Resolution and escalation cover the last 7 days; satisfaction covers all time. Each card states its own window — otherwise the picker would look like it governed numbers it does not.
Performance
| Measure | Target | Window |
|---|---|---|
| Resolution rate | above 80% | last 7 days |
| Escalation rate | below 15% | last 7 days |
| Average response time | under 3s | last 7 days |
The targets are references, not commitments; your own good/bad threshold may differ.
Customer satisfaction
The score collected at the end of a chat: average, satisfaction rate and total ratings. With no ratings the rate is not computed — printing "0% satisfaction" would paint a false picture when nobody has voted.
Question categories
Incoming questions are classified automatically: Order tracking · Product question · Return/cancel · Customer info · General support · Escalation · Other. The distribution follows your selected range and shows what customers actually ask — a good guide to where your knowledge base needs weight.
Reports tell you what happened; Answer Review tells you whether the answers were good. Different questions: volume versus quality.