Score resolved support conversations against your own rubric, with a dispute trail your team can trust
Every resolved conversation gets a quality score, judged against a bar your team defines.
Conversation quality reviews your resolved support conversations and scores each one from 0 to 100, so coaching conversations start from evidence instead of anecdotes. It lives in the Service hub under Service → Conversation quality, in three tabs: Scores (what was scored, and any dispute about it), Rubrics (what conversations are judged on), and Lanes (which scoring lanes run).
A rolling list of scored conversations, with the workspace average alongside.
Resolved conversations are scored overnight and appear in the Scores tab, newest first. A summary row shows the workspace average, open disputes, and overturned scores, and you can narrow the list to All, Low, or Disputed conversations. Opening a score shows the per-criterion breakdown behind the number, so a 62 is never just a 62: you can see which criteria earned it.
Deterministic checks that always apply, and an AI review of the conversation itself.
The Lanes tab holds a switch for each lane. Managers can turn either lane off for the whole workspace, and a one-lane change never resets the other. With both lanes on, every resolved conversation carries both the deterministic checks and the AI review.
Define what a good conversation means for your team, and test it before it goes live.
Until you author a rubric, conversations are scored on the built-in criteria: empathy, sentiment, comprehension, and resolution. A rubric replaces that default with your own bar: a set of criteria, each with a weight, and optionally marked critical (a conversation that misses a critical criterion fails outright, whatever its other marks).
In the Rubrics tab, add criteria with weights and set the pass threshold. New rubrics always start inactive and untested: nothing is graded on your draft while you shape it.
Test dry-runs the rubric against your last few closed conversations without writing a single score. The report shows how matches distribute across your criteria and warns when one criterion soaks up most of the signal (several criteria asking the same question) or never fires at all (too narrow to matter).
Activation is refused until the rubric has been tested, because going live changes how everyone's work is graded from that moment on. One rubric is active at a time; activating a new one stands the previous one down.
A score that grades a person's work has to be contestable by that person.
The agent a score is about can dispute it with a note saying why they disagree. A manager then rules on the dispute: upheld leaves the score standing, and overturned records that the team decided the score was wrong. Nothing is deleted or rewritten at any step: the original score, the objection, and the ruling all stay on the record, which is what makes the number defensible when it comes up in a coaching conversation.