Reports and coaching feedback · Autessa Roleplay
Delivery measures
Autessa Roleplay measures delivery from the transcript: speaking pace, filler words, talk ratio, hedging phrases, longest turn and questions asked, each with a plain-language read. These are counted, not judged, so the same transcript gives the same numbers every time.
The problem it solves
How you say it matters, and it is hard to hear yourself
Most reps do not know they talk 70% of the call, say "basically" every other sentence, or soften every ask with "I guess". These habits are easy to count and hard to notice. Counting them from the transcript gives an honest mirror without an AI opinion in the way.
What you get
- Pace in words per minute: comfortable, too fast (over 175) or too slow (under 110).
- Filler words, total and per 100 words: um, uh, like, you know, I mean, sort of, kind of, basically, actually, literally and more.
- Talk time: your share versus theirs, with a nudge to stay under half on discovery-style calls.
- Hedging: phrases like "I guess", "just wondering", "sorry to bother" and "does that make sense".
- Longest turn in words, flagged over 150.
- Questions asked, flagged at zero.
- Each tile has a plain read, such as "Clean delivery" or "Pause instead of filling."
- Kept apart from the rubric: the scorer is told never to recount them.
The run-through
How does delivery measures work?
- SCENE 1
Talk
Run any voice or text session.
- SCENE 2
Count
When the session ends, delivery measures are counted from the trainee's turns.
- SCENE 3
Read
The report shows each measure as a tile with a value and a short note.
The cue sheet
Measures and thresholds
| Option | What it does |
|---|---|
| Pace | Words per minute. Over 175 reads as fast, under 110 as slow. |
| Filler words | Count and rate per 100 words. Over 2 is "a few", over 4 is "noticeable". |
| Talk time | Your share of the words. Over 65% or under 30% is flagged. |
| Hedging | Softening phrases. More than 3 is flagged. |
| Longest turn | Words in your longest stretch. Over 150 suggests breaking it up with a question. |
| Questions asked | How many questions you asked. Zero is flagged. |
The cast
Who can do what?
| Who | Can |
|---|---|
| Trainee | See their delivery measures on every report. |
| Coach | See delivery measures on everyone's reports. |
Questions
Questions about delivery measures
Is talk ratio judged by AI?
No. Talk ratio, filler words, pace, hedging, longest turn and questions are all counted from the transcript, so the same transcript always gives the same numbers.
What counts as a filler word?
Words and phrases such as um, uh, er, ah, hmm, like, you know, I mean, sort of, kind of, basically, actually and literally.
What is a good talk ratio for a discovery call?
The report nudges you to keep your share under half on discovery-style calls, and flags anything over 65%.
100% customizable, code and all
Make Autessa Roleplay fully your own.
Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.
Start free and make it yours