Patient simulator

Plays real patients, with messy wording.

Takes inCustomer transcripts, personas
The agentPatient simulator
Hands backSimulated chats and calls with realism score

Checked against clinicians

Realism against held-out real transcripts; clinician Turing test; check simulated-vs-real performance gap.

Where a person decides

Never used alone for sign-off (Oxford gap).

Works on

Chat, triage, voice, mental health.

In development. Early access is open. Reviewed .

The problem it solves

Real patients write messy messages. Testing with neat scripted prompts overstates how well a chatbot will do.

How it works

01

Take a clinical case

A case defines the true condition and the facts a patient would know.

02

Play the patient

The agent writes it many ways: vague, anxious, with wrong terms, in other languages.

03

Score the conversation

Outputs are graded for triage correctness and safe advice.

An example, illustrative

Before

'I have chest pain radiating to my left arm.'

With the agent

'my chest feels tight and my arm is weird, probably nothing?'

What it needs from you

Clinician-written cases and the chat endpoint to test.

Its limits

Simulated patients differ from real ones. We measure that gap rather than assume it away.

Quick answers

What does the patient simulator do?

Generate realistic, wording-varied patient and caregiver conversations.

How is the patient simulator checked against clinicians?

Realism against held-out real transcripts; clinician Turing test; check simulated-vs-real performance gap.

Does simulation replace real users?

No. It tests many more phrasings cheaply, then real-user checks confirm.

How realistic is it?

We compare simulated and real conversations and report the gap.

What can the patient simulator not do?

Never used alone for sign-off (Oxford gap). No agent makes a clinical decision.

Get early access to the patient simulator