AI Medical Training · Assisted Consultation


ChatGeneT runs realistic, multi-turn consultations so junior clinicians can practice the hardest part of medicine: asking the right questions. Patients that lead with their worries, open up unevenly, and stay true to their history, available on demand.

0
Partner hospitals
0
Clinicians trained
0/5
CSAT score
0%
Hallucination rate
The product

A virtual patient that talks like a real one.

Each session is a full multi-turn encounter. The simulated patient leads with what worries it most, volunteers history unevenly, asks its own questions, and sometimes holds back, exactly the way a real person does in the room. It is a safe place to build judgment before a clinician ever sits across from a patient.

  • Leads with the chief complaint, not a tidy symptom list
  • Shows emotion and asks its own questions
  • Can hesitate or decline to answer, like a real patient
  • Stays faithful to a fixed medical record on every turn
Try a guided session
Simulated Patient · Case #2471 LIVE
Patient Doctor, I’ve had this tight chest feeling for about three days now. It comes and goes.
Clinician Does anything make it worse, like exercise or stress?
Patient Now that you mention it… it’s worse when I climb the stairs at work. Rest helps.
Clinician Any history of high blood pressure or heart problems in your family?
Patient My father had a heart attack at 58. I’ve been meaning to get checked but never did.
Patient Is this something serious, doctor? I’ll be honest, I’m a little worried.
0.31% hallucination 0.87 anthropomorphism
What it powers

One simulator, the full training lifecycle.

Standardized onboarding

New clinicians ramp on the same vetted cases, so every hire starts from a consistent, certifiable baseline instead of whatever walks through the door.

Competency assessment

Objective, repeatable evaluation across the same scenarios turns informal judgment into a measurable, defensible signal of readiness.

Assisted consultation

Lifelike practice sharpens history-taking and reasoning, raising the quality and efficiency of real consultations once clinicians are on the floor.

How it works

Real conversations in, a believable patient out.

Prompting a model to act sick is not enough. We learn how real patients actually talk, then build that behavior into the simulator and hold it to a measurable bar before it ships.

01

Learn from real consultations

We distill patient dialogue strategies from real doctor and patient conversations: how patients open, what they volunteer, when they push back, and how they show worry.

02

Synthesize and fine-tune

Those strategies, paired with structured case records, generate training dialogues. The simulator is fine-tuned entirely on this curated, fully anonymized data.

03

Control behavior

Tight evaluation holds the simulator to a 0.31% hallucination rate and a 0.87 anthropomorphism score, so dialogue stays faithful to the record and human in feel.

04

Operationalize iteration

Annotation and review become a repeatable pipeline, so case coverage expands and quality improves with every release.

Research

The inquiry phase is where consultations are won or lost.

Most medical AI is judged on the diagnosis. Our work focuses on the step before it: the questions. What we found reshapes how clinicians should be trained and assessed.

The core finding

Inquiry quality sets the ceiling. A clinician with excellent diagnostic instinct still fails when the questioning is poor, and sharp questioning is wasted on weak reasoning. The weaker of the two decides the outcome.

3-5
Inquiry rounds that work

Accuracy climbs as a clinician asks more, but only up to the point a real patient will stay engaged. Beyond that, people disengage.

01

Chief complaint

Opening the encounter and surfacing the main concern the patient came in with.

02

Specifying symptoms

Pinning down the character, timing, and severity of what the patient has already raised.

03

Accompanying symptoms

Probing related signs that widen or narrow the differential before committing.

04

Family & history

Drawing out background and risk factors that can shift the diagnosis entirely.

Where a clinician spends their questions, across these four types, measurably changes the diagnosis they reach. ChatGeneT makes that skill practiceable and measurable.

How we measure realism

Believable is not a vibe. We score it.

0%
Hallucination rate

Share of replies that contradict the patient’s own record. Lower is better, and ours sits far below earlier systems.

0
Anthropomorphism

How human the patient feels: emotion, initiative, and natural phrasing, scored from 0 to 1.

Real
Engagement

Real patients sometimes sidestep a question. We preserve that instead of forcing tidy answers, so practice matches the clinic.

Why ChatGeneT

A new standard for clinical training.

ChatGeneT
Traditional training
Availability
On demand, 24/7
Limited by mentor & patient time
Consistency
Same standard everywhere
Varies by site and mentor
Assessment
Objective & repeatable
Informal, hard to certify
Case coverage
Configurable, broad
Whatever happens to present
Scale
500+ clinicians, 30+ hospitals
One trainee at a time
Results

Measured quality, real adoption.

0/5
CSAT satisfaction

High satisfaction from clinicians training on the simulator.

0
Clinicians supported

Standardized onboarding and assessment at scale.

0
Partner hospitals

Deployed for onboarding and assessment across partner sites.

0
Curated dialogues

Real consultation behavior distilled into the training corpus.

“Realistic multi-turn patient dialogue gave our junior clinicians a consistent way to practice and be assessed, training and assisted consultation finally on the same standard.”

Partner with us

Bring standardized clinical training to your hospital.

We work with hospitals to roll out ChatGeneT for onboarding and competency assessment. Reach out to see the simulator in action.

Thanks! We'll be in touch.
Our team typically responds within two business days.