Analytics dashboards
The Analytics page charts trends across many calls, with chart fields, starter templates and the source filter.
The workspace Analytics page shows one dashboard at a time, a grid of charts across your calls. It answers the questions a single transcript cannot: how busy is the agent, how long are calls running, how often do they succeed, and how fast is it responding. The control bar narrows the grid to one or more agents and a time range. Its source filter starts on Customer conversations and switches to test conversations, scenario runs, or everything except scenario runs. To read one call instead, see Calls.
How a chart is built
Add chart builds each chart from one Data field, bucketed by Group by, optionally split into series by Compare by, and reduced by Show as.
| Choice | Options |
|---|---|
| Data field | Duration, successful conversations, outcome, caller mood, reply time, topic, disconnection reason, failure reason, reviewed, check score and hot keywords. |
| Group by | Day, week, hour, agent, outcome, caller mood, topic, drop-off point, and others. |
| Compare by | None, or a category such as outcome, caller mood, topic or agent. |
| Show as | Count, average, sum, median, 95th percentile. |
Chart types are line, bar, stacked bar, pie, number, KPI (number and trend), recent calls, leaderboard and list.
Data field Reply time (ms)
Group by Day
Show as Median
Chart type Line chartStarter dashboards
Add a chart yourself, or start a new dashboard from a template that ships a themed set of charts in one click. For example:
- Operations: call volume over time, by hour and by agent, plus average duration and top topics.
- Quality & outcomes: success rate and its trend, outcome mix, sentiment, drop-off points and review coverage.
- Reply time & call length: median and 95th percentile reply time with average call length over time.
- Executive at-a-glance: the headline numbers (total calls, average duration, median latency) with a weekly trend.
Where the latency numbers come from
Response latency and time-to-first-audio are measured by the runtime on every call. Latency surfaces here as the Reply time field (the Reply time & call length template plots the median and 95th percentile). The full per-stage waterfall is on each call's Performance tab and the Evals scoring views.