Skip to main content
Reports answers the operational questions the Dashboard does not: how fast customers get a first reply, how many conversations the AI agent closes without a human, why conversations are handed over, and how each teammate performs. Every report covers a date range you choose and can be exported as CSV.

​
Before you start

  • Reports are visible to every predefined role (Owner, Admin, Manager, Agent and Viewer all have Analytics view access). See Team and roles.
  • Reports use your workspace timezone (Settings → Profile → Timezone) for day boundaries and peak hours. Business-hours figures also use Working Hours from Settings → General. See Workspace settings.
  • Test conversations (the Test Conversations folder in the Inbox) are excluded from every report.

​
Pick a date range

Use the picker at the top right: 7d, 30d (default), 90d or Custom with From and To. Dates are inclusive calendar days, so 1–7 March is seven full days. A range longer than 180 days is not allowed; the page shows “Date range cannot exceed 180 days. Please select a shorter range.” and no report loads until you shorten it. The selected tab and dates are kept in the page address, so you can bookmark or share a link to a specific report and period.

​
Volume

What came in, from where, and when.
  • Conversations Over Time: conversations started per day. Export CSV downloads a Date, Conversations file.
  • By Source: counts per origin of the conversation, shown as the stored source code: WHATSAPP, WIDGET (Website Chat), TEMPLATE (started by a template you sent), API, SANDBOX (the test number) or AGENT. Conversations without a source show as “Unknown”.
  • By Tag: the ten most common conversation tags; untagged conversations are grouped as “Untagged”. Tags are managed in Tags and macros.
  • Peak Hours: conversations started per hour of the day (0:00 to 23:00) in your workspace timezone. Use it to plan shifts.

​
Response Time

How long customers wait for a first reply, and how long conversations take to close. The four < 1 min, < 5 min, < 30 min and < 1 hour cards show the percentage of conversations that received a reply whose first reply arrived within that time. Conversations that were never answered are not part of these percentages.
  • First Response Time Trend: median first response per day. Export CSV downloads Date, Median FRT (sec), Avg FRT (sec), Conversations.
  • AI First Response and Human First Response: the median and the number of conversations in which the first reply came from the AI agent or from a teammate.
First-response calculations count the first reply from the AI agent or a teammate after the customer’s first message. Follow-ups, handover notices, internal notes, rejected AI drafts and internal tool steps are ignored, and replies that took longer than seven days are dropped.

​
Resolution

How much the AI agent handles on its own, and why conversations are handed over to your team. Every conversation is classified by who actually replied:
  • Handling Breakdown: a pie of AI Only, Hybrid and Human Only.
  • Deflection Trend: the deflection rate per day. Export CSV downloads Date, Total, AI Only, Deflection Rate %.
  • Escalation Reasons: a count per reason. The reasons that can appear are ai tool (the agent used its handover tool), credit exhaustion (the workspace ran out of credits), media unsupported (the customer sent a file type the agent cannot read), evaluator failure (the AI Manager rejected the reply), ai completion failure (the reply could not be generated), no agent (no agent was connected to the channel) and security (the Guard blocked the conversation).
  • Deflection by Tag: Total, AI Only and Deflection Rate for each conversation tag, so you can see which topics the agent handles well.
To reduce handovers, review the agent’s Capabilities (Handover, Guard, AI Manager) and its Knowledge Base.

​
Agents

One row per human teammate who handled at least one conversation in the range. A conversation is attributed to the last teammate who was assigned to it. Export CSV downloads the table with the average first response as an extra column. If nobody on the team handled a conversation, the tab shows “No human agent activity”.

​
Export All Conversations

Export All Conversations (top right) downloads one row per conversation in the range, newest first, with these columns: Agent Name, Conversation ID, Tag, Source, Customer Name, Customer Phone, FRT (Calendar), FRT (Business Hours), Resolution Time, First Response At, Initiated At, Resolved At, Messages and Handling (ai_only, hybrid or human_only). Timestamps are in your workspace timezone. The export contains at most 10,000 conversations. When the range has more, the confirmation reads “N / total rows exported (truncated)”; narrow the range and export again.

​
Troubleshooting