About Manual QA sampling
Most teams review a few conversations per agent each month, using a spreadsheet scorecard.
Best for
Very small teams, or deep coaching sessions on a single call.
About Assay
Checks every call, chat and email against your QA scorecard, links each result to the line in the transcript, and sends uncertain ones to a person.
Best for
QA, compliance and team leads who need every conversation checked, with evidence they can show an auditor.
Side by side
| Question | Manual QA sampling | Assay |
|---|---|---|
| Conversations checked | A sample, usually a few per agent each month | Every call, chat and email |
| Consistency | Varies between reviewers | The same rule applied the same way every time |
| Evidence | Reviewer notes | The exact line in the transcript |
| Reviewer time | Spent listening to routine calls | Spent only on the conversations that need a decision |
| Spotting patterns | Slow, from a small sample | Across every conversation, as they happen |
Descriptions of other products are based on how they describe themselves publicly and may change. If something here is out of date, tell us and we’ll correct it.
Questions
- Is automated QA as accurate as a human reviewer?
- It depends on the rule. Assay reports how often it agrees with your reviewers for each rule, and anything it isn’t sure about goes to a person, so you can see the accuracy rather than take it on trust.
- Do we still need QA reviewers?
- Yes. Reviewers stop listening to routine calls and spend their time on the conversations that failed a rule or need a judgement call.
Try it on your own calls
Tell us about your team. We’ll reply within two working days to set up a trial with 50 of your transcripts and your current scorecard.
- No card or contract for the trial
- Your conversations are never used to train models
- We go through the results with you
Thanks, we’ve got it.
We’ll be in touch within two working days.