Clinician reaction elicitor

Turns clinician reactions into written test criteria.

In audits Layer 1 · Specify
Takes inReal outputs, clinician comments
The agentReaction elicitor
Hands backTaxonomy, draft rubrics, disagreement map

Checked against clinicians

Blind-labelled holdout; second clinician pass on induced criteria.

Where a person decides

Clinicians own the taxonomy; agent proposes.

Works on

All.

Delivered inside a Quality Audit today. Reviewed .

The problem it solves

Teams struggle to write down what 'good' means. Clinicians know a bad note when they see one, but can't always say why. Rubrics invented at a desk miss what actually matters.

How it works

01

Collect reactions

Clinicians mark real outputs pass or fail and add a short comment.

02

Find the patterns

The agent groups comments into failure types, such as omission or wrong negation.

03

Draft criteria

It proposes written criteria, and clinicians edit or reject each one.

An example, illustrative

Before

'This note feels off.'

With the agent

Criterion: the note must list every allergy mentioned in the visit.

What it needs from you

A few dozen real outputs and about an hour of clinician time.

Its limits

It proposes. Clinicians own the taxonomy and can overrule any criterion.

Quick answers

What does the reaction elicitor do?

Turn clinicians' pass/fail and comments on real outputs into a failure taxonomy and candidate criteria.

How is the reaction elicitor checked against clinicians?

Blind-labelled holdout; second clinician pass on induced criteria.

Why not write the rubric ourselves?

You can, and the agent starts from your draft. Reactions to real outputs usually surface criteria you wouldn't have thought of.

How many reactions are enough?

Around 60 reactions is a useful start. More are added where clinicians disagree.

What can the reaction elicitor not do?

Clinicians own the taxonomy; agent proposes. No agent makes a clinical decision.

Use the reaction elicitor on your product