No.5
AI role-play Conversation practice ● Live AI

Practice Partner

You don’t get better at hard conversations by reading about them. Here you practice one with a customer named Jordan, who is having a bad week and does not care that you are new. A rubric scores what you actually said, and you can rerun it as many times as you like.

Audience · Customer-facing associates
Format · AI conversation + rubric
Design model · Deliberate practice
Scenario: The late order · Jordan ({{ modeLabel }})
Turn {{ turnLabel }}
{{ m.who }}
{{ m.text }}
{{ busyWho }}
Your reply — say it in your own words
Your reply
Live rubric
{{ rubricHint }}
{{ r.name }}
{{ r.score }}
{{ r.note }}
Coach's read
{{ summaryText }}
WHAT THE RUBRIC HEARD
T{{ h.turn }} · {{ h.dimension }} — “{{ h.quote }}”

This demo is running live: Jordan is played by an LLM working from a persona brief with guardrails, and your transcript is scored against the same rubric you see on the right. Every rep is different, and every score is explainable.

{{ scriptedNote }}

XAPI STATEMENT LOG — what an LRS would receive from this session
{{ xapiCount }} statements
// interact with the demo above — statements stream here as they would to a Learning Record Store
{{ x.ts }} learner {{ x.verb }} "{{ x.obj }}" {{ x.res }}
Designer's note

Why I made these choices

Private reps first

I designed for private reps because role-playing in front of peers is performance, not practice. Removing the audience lets people try the sentence they would be embarrassed to fumble in a workshop.

Behaviors, not vibes

I wrote the rubric to score only what a transcript can prove. Did you name the feeling, say what happens next, and avoid promising what the system cannot keep. "Sounded empathetic" appears nowhere in it.

Consistency is the point

Human role-play partners drift. Some go easy, some go brutal. I wrote a persona brief that holds difficulty constant across a thousand learners, which makes scores comparable and progress measurable for the first time.

The theory underneath
Psychological safety · Edmondson

People do not practice honestly while being watched by peers who will remember. A private AI partner removes the social risk, which is what makes real rehearsal possible.

Behavioral objectives · Mager

Every rubric line is an observable action a transcript can prove. Vague criteria produce vague feedback, so "sounded empathetic" was banned from the start.

Deliberate practice · Ericsson

Unlimited reps with consistent difficulty and immediate scoring is the closest a conversation skill gets to a practice range. The persona brief keeps the opponent identical for every learner.