What Metrics Means Here
Metrics are aggregates computed over completed calls. Per-call records are the raw material — see call logs and post-call analysis. This page covers the numbers you read to decide whether a Finn is working, and the ways those numbers mislead you.
The Four Headline Numbers
| Metric | Definition | What a bad value means |
|---|---|---|
| Success rate | Calls achieving the goal / calls that connected and completed | Finn behaviour problem: prompt, guardrails, or closing |
| Completion rate | Calls reaching a real human and getting through the conversation / calls attempted | List quality or calling hours. Not a Finn problem |
| Average duration | Mean length of completed calls | Under 20s, Finn getting hung up on or terminating early. Over 5min, Finn rambling or not closing |
| Cost per successful outcome | Total cost / count of successful calls | The economic truth. Everything else is diagnostic |
Success rate is defined by you, not by the platform. It is computed against the primary success field you defined in post-call analysis. If your primary success field is appointment_booked, success rate is the fraction of connected-and-completed calls where appointment_booked = true. Change that field definition and every historical success rate on the page changes meaning. See analysis fields.
Success rate and completion rate share no denominator. Completion rate counts attempts; success rate counts only calls that connected and completed. A campaign can post 90% success on 8% completion and still be a failure. Read them together.
Where Each View Lives
Metrics are read in the dashboard. There is no metrics aggregate endpoint.
| Page | Scope |
|---|---|
| Dashboard (home) | All deployments, high level |
| Analytics | Cross-deployment trends, time series, leaderboards |
| Deployment Analytics | One deployment, with per-call drill-in |
| Finn Analytics | One Finn across all its deployments |
| Call History | Every call, searchable |
| Live Deployments | Real-time counts and active calls |
To get metrics into your own systems, use the per-deployment CSV or the PDF report (exports), or stream completed-call events to your endpoint (post-call webhook).
Distributions, Not Just Averages
Each post-call analysis field gets a distribution chart, typed by the field:
| Field type | Chart |
|---|---|
| Boolean | Bar chart of true/false |
| Enum | Stacked bar of categories |
| String | Word cloud plus a sample of five |
| Number | Histogram plus median |
The string sample-of-five is a sample. Do not treat it as the range of answers.
Where These Numbers Go Wrong
Live numbers move. While a deployment is running, success rate is computed against calls completed so far. It fluctuates as more calls finish. Wait for the deployment to complete, or for at least 100 calls, before concluding anything.
Small denominators lie. Success rate on 12 calls is noise. The 100-call threshold is a floor for reading a number at all, not a guarantee of significance.
Aggregates are cached. The dashboard shows a Cached badge when the data is not freshly computed. Click Refresh to force a recompute.
| Data | Cache TTL |
|---|---|
| Deployment list | 5 minutes |
| Per-deployment summary | 1 minute |
| Per-call records | Never cached, always live |
If a number you just changed something to affect has not moved, check the badge before assuming the change did nothing.
Drift is usually the list, not the Finn. Gradual degradation in success rate over weeks most often means the audience is going stale. The Finn config did not change. Check call outcomes and completion rate before rewriting prompts.
Editing a transcript edits the record. Correcting a transcript line updates the analytics record it feeds. Numbers computed before the edit will not match numbers computed after.
Reading a Bad Campaign
Work in this order. Each step rules out a cause before you spend effort on the next.
- Check completion rate first. Low completion with healthy success-among-completed is a list or calling-hours problem, and no prompt change fixes it.
- Check average duration. Very short means hangups early, so audit the welcome message.
- Check whether any post-call analysis field is flagged as extraction-failed disproportionately. That is a transcript or instruction problem, not an outcome problem.
- Sort the call table by sentiment ascending and listen to the worst five. Patterns usually show within three calls.
- Diff against a known-good Finn. Run the same audience on a baseline Finn for 50 calls and compare the same four numbers.
Do not try to read every call. A working campaign produces thousands. Read the headline numbers, then the ten best and ten worst calls.
Related
- Post-call analysis — defining the fields metrics are computed from
- Analysis fields — field types and the primary success field
- Monitoring — live health rather than retrospective aggregates
- Evaluations — testing a Finn before it produces metrics
- Exports — CSV and PDF output