AvaNUR lets students practice realistic patient encounters with a lifelike AI patient and get structured, rubric-based feedback. Scenarios span motivational interviewing, de-escalation, telehealth, and specialty-specific training.
How it works
Faculty author patient background, hidden context, disclosure rules, behavioral guardrails, and starting patient state.
Preview the case, set the avatar, and launch. A short code goes to the learner.
The learner joins a live audio-video conversation with a lifelike AI patient. Tone, pace, and question style matter.
An AI-assisted evaluation grades the visit against a rubric and surfaces concrete strengths and growth areas.
Faculty review the full transcript, rubric, trajectory shifts, disclosure history, and add instructor notes.
The Encounter
Learners join a live audio-video session with an AI patient rendered by a photorealistic video avatar. The patient responds to tone, pace, and question style. They hold back the way real patients do, disclose when the learner earns it, and stay in character within scenario guardrails.
Learner Feedback
After the session ends, learners see an AI-assisted evaluation across five domains. Each domain comes with a score, a one-line explanation, and concrete strengths and growth areas. Downloadable as PDF or CSV.
Faculty Debrief
Faculty get a parallel view with the full transcript, rubric-based scoring, patient-state trajectories, disclosure history, and a space for instructor notes. Debriefs save as a single review record and can be shared back to the student.
Scenarios
AvaNUR ships with scenarios for motivational interviewing, NP-led encounters, de-escalation, women's health, and language-barrier practice. Faculty can also author custom cases in the built-in scenario builder.
Responsible AI
Scenario guardrails constrain avatar responses to clinically appropriate ranges. Transcripts are reviewed for accuracy and bias. Faculty interpret all AI-generated feedback during debrief. AvaNUR is designed to supplement faculty-led simulation, standardized patients, and clinical learning, not replace them.
Sustainability
Remote, repeatable AI patient encounters reduce the need for students, faculty, and standardized patients to travel for every practice session.
Scenarios can be reused, revised, and shared digitally, limiting disposable materials, printed packets, and one-time-use simulation resources.
Programs can offer more deliberate practice without proportionally increasing physical space, commuting, scheduling overhead, or material consumption.
AcknowledgmentsWith thanks to Dr. Bonnie Hepler; Dr. Ryan Shaw; Dr. Nikki Blodgett; and Kethia Dorceus Pierre, LCSWA.
Questions?
For demos, collaborations, and faculty inquiries.