# Reading your score

What to take from a graded roleplay, what to ignore, and how to turn a weak criterion into an actual improvement.

Source: https://replicatelabs.ai/docs/roleplay/reading-your-score
Last updated: 2026-09-03

---

After a roleplay you get a graded read: a score, a breakdown by criterion, and feedback pointing at moments in the conversation.

The number is the least useful part of it.

## Three habits

<figure class="dfig">
<div class="dframe">
<div class="danat">
<div class="danat-row"><b>Read the evidence</b><span>A criterion marked down with a quoted exchange is a coachable thing. The overall figure is not. Go to the quotes first and the total last, or ideally not at all.</span></div>
<div class="danat-row"><b>Look for the repeat</b><span>One weak criterion in one roleplay is noise. The same criterion weak across four is a skill gap worth an hour. Judge yourself on the pattern, not the session.</span></div>
<div class="danat-row"><b>Do not chase the number</b><span>Playing to the rubric produces someone who is good at roleplays. Work the criterion, not the score.</span></div>
</div>
</div>
<figcaption><b>How to read a graded conversation.</b> The score exists to point you at the criteria; it is a signpost, not the destination.</figcaption>
</figure>

## Turning a weak criterion into something useful

The most valuable twenty minutes after a roleplay is not another roleplay. It is a conversation with your coach about the specific thing that let you down.

<figure class="dfig">
<div class="dframe dark">
<div class="dflow">
<div class="dstep"><span class="dstep-n">1</span><b>Name it precisely</b><span>Not "my discovery was weak". "I was marked down on confirming impact."</span></div>
<div class="dstep"><span class="dstep-n">2</span><b>Take the quote</b><span>Bring the actual exchange the grader flagged. "Here is what I said. Show me what it should have sounded like."</span></div>
<div class="dstep"><span class="dstep-n">3</span><b>Get the words</b><span>Ask for the two or three questions you should have asked, phrased the way you would say them.</span></div>
<div class="dstep"><span class="dstep-n">4</span><b>Re-run</b><span>Now the second attempt is practising something different rather than the same thing more fluently.</span></div>
</div>
</div>
<figcaption><b>Score to improvement.</b> Without step two the conversation stays abstract and nothing changes.</figcaption>
</figure>

## A low score that is not about you

Three cases worth recognising before you take it personally.

- **You ran four minutes.** The grader had four minutes of evidence. It is not a read on your ability.
- **The scorecard was edited between attempts.** You are being graded against a different standard. See [Scorecards](/docs/roleplay/scorecards).
- **You practised the wrong scenario.** If the roleplay's scorecard grades a discovery conversation and you ran it as a negotiation, the criteria will mark you down for not doing something you were never trying to do.

## What a good trajectory looks like

Not a rising line. What you want is a **narrowing spread**: your weakest criterion coming up towards the rest, and the same criterion no longer being the weak one three sessions later.

A rising average with the same criterion at the bottom every time means you are getting better at the things you were already good at.
