Evaluations automatically reviews your Voice AI's calls and gives each one a grade. Instead of listening back to every call to check how your bot is doing, you get a graded list that shows you where things went well and where they didn't.
Think of it as a second pair of ears on your Voice AI. It goes through completed calls, summarises each one, and flags the calls worth a closer look, so you can spend your time on the ones that need it rather than hunting for them.
Evaluations is a testing and maintenance tool. It only looks at calls that have already happened, so it has no effect on your live Voice AI or on the caller experience.
🔍 What are Evaluations?
Every call your Voice AI handles can be scored on how well it dealt with the caller. Each evaluation gives you three things: a short summary of what the call was about, when it started, and a grade.
The three grades
The grade is a quick signal of how the call went. There are three:
Grade | What it usually means | What to do |
Good | The Voice AI handled the call well. It answered accurately and stayed on task. | Nothing. These are working as intended. |
Warning | Mostly fine, but something minor is worth a look, such as a slightly off or incomplete answer. | Skim it when you have time. Fix if it's part of a pattern. |
Needs Attention | The Voice AI likely got something wrong or handled the call poorly. | Review it and act. This is where improvements matter most. |
📊 Reading the Evaluations page
The Evaluations page has a filter panel on the left and a results list on the right.
1. Filter to what you need
Use the filters to narrow the list down before you start reviewing.
- Start date / End date: set the date range of calls you want to review.
- Grades: choose which grades to show. Select Needs Attention and Warning on their own to jump straight to the calls that need work.
- Apply filters: click this to update the list. Nothing changes until you do.
2. Review the results
Each row is one call, shown with its summary, start time and grade.
- Summary: a short description of what the caller wanted (e.g. "Customer wants human help").
- Started: the date and time the call began.
- Grade: Good, Warning or Needs Attention.
Click the arrow on the right of any row to open its full evaluation.
3. Check the Evaluation
Expanding a row shows the Grades breakdown: the individual checks behind the grade, each with its own score (for example, "Tools used correctly: 3/3" or "Customer issue resolved: 0/1"). For Voice AI these checks are:
- System stability: the technical health of the call, such as audio and connection quality.
- Tools used correctly: whether the bot chose the right tools for the caller's request.
- Tools worked correctly: whether those tools returned what they should have.
- Escalated correctly: whether the bot handed off to a human at the right time.
- Customer issue resolved: whether the caller's problem was actually solved.
The overall grade is a summary of these checks, so the breakdown tells you exactly why a call was graded the way it was.
🔄 Evaluating more calls
By default, your calls are evaluated automatically. Every account gets 100 free evaluation minutes, and calls are evaluated until that limit is reached. To evaluate more calls, use the Evaluate More Interactions button in the top right of the page.
Evaluating more calls can take a moment to process. Once it's done, the new results appear in the list and you can filter them like any other.
⚙️ Adjusting the sampling rate
By default, every call is evaluated. If you'd rather evaluate only a portion of your calls, for example to make your free minutes go further, you can lower the sampling rate.
Changing the sampling rate
Go to Settings, then Company Configs, then Supervisor Controls, and find Voice AI Evaluation Sampling Rate.
- Enter the percentage of interactions to evaluate, from 0 to 100.
- Click Submit to save.
A rate of 100 evaluates every call. A lower rate evaluates fewer, so set it to match how much of your allowance you want to use.
💡 Getting the most out of Evaluations
Evaluations is most useful when you act on what it shows you, not just read it.
Top tips:
- Start with the reds. Filter to Needs Attention first, then Warning. That's where your time is best spent.
- Look for patterns. If several calls fail in the same way (a request the bot can't handle, a handoff it keeps missing), that's a prompt or Tools problem, not a one-off.
- Feed fixes back in. When you spot a recurring issue, update your Voice AI's prompt or Tools to address it, then evaluate a fresh batch of calls to see if the grades improve.
- Check it regularly. A quick review on a schedule catches issues before your callers do.
❓ Frequently Asked Questions
Where do I find Voice AI Evaluations?
Open your Voice AI bot and click the grey View Voice AI Evaluations button near the bottom of the page (next to Save).
What do the three grades mean?
Good means the call was handled well. Warning means there's something minor worth a look. Needs Attention means the bot likely got something wrong and the call is worth reviewing.
What does the "Evaluate More Interactions" button do?
It runs evaluations on further calls and adds the results to the list, so you can review calls that haven't been graded yet.
How many evaluations do I get?
Every account gets 100 free evaluation minutes. By default your calls are evaluated automatically until that limit is reached.
Does running Evaluations affect my live Voice AI?
No. Evaluations only reviews calls that have already finished. It doesn't change your Voice AI's behaviour, and callers never notice it.
What should I do about a call graded "Needs Attention"?
Open the call to see what happened, work out what the bot got wrong, and update your prompt or Tools to fix it. Then evaluate more calls to check the change worked.