Codes by Shrey

Product Requirements Document

Clinical Roleplay Simulator PRD

A web-based medical communication training tool where learners select a standardized-patient scenario, conduct a simulated consultation through text or voice, and receive AI-generated OSCE-style evaluation.

Product Scope

  • Scenario selection from a fixed case library
  • In-character AI patient responses
  • Browser speech recognition for learner input
  • AI voice playback for patient responses
  • End-of-session structured evaluation

Users

Medical learners and educators

Mode

Text and voice simulation

Feedback

OSCE-style report

Status

MVP prototype

Product Summary

The simulator is designed for communication-skills practice rather than formal assessment. Learners choose a patient scenario, interact through text or voice, and receive structured formative feedback at the end of the session.

Problem

Medical learners need repeated practice for communication-heavy encounters: foundational history taking, cross-cultural communication, psychosocial assessment, shared decision-making, family communication, and difficult news delivery.

Scenario Library

The MVP includes six fixed scenarios with patient demographics, chief complaint, communication focus, description, allergies, medical history, medications, vital signs, and avatar image.

Functional Requirements

  • Present available scenarios and allow selected or random launch.
  • Initialize each conversation with a scenario-specific patient statement.
  • Display patient overview data during the encounter.
  • Append learner and patient messages to a visible transcript.
  • Support browser-native speech recognition where available.
  • Generate and display a structured JSON evaluation report.

Evaluation Categories

Evaluation currently covers history taking, communication skills, rapport building, clinical reasoning, and professionalism, with overall score, grade, strengths, priority improvements, and specific recommendations.

Next Release Priorities

Future work should add authentication, saved session history, transcript and evaluation persistence, educator review dashboards, rubric QA against human-rated samples, scenario authoring, learner progress tracking, and stronger accessibility behavior.