Codes by Shrey

Product Requirements Document

Clinical Roleplay Simulator PRD

A virtual standardized patient simulator for medical communication training, designed around scenario-specific patients, transcript-aware dialogue, voice support, prompt experimentation, and formative OSCE-style evaluation.

Current Scope

  • Generic VSP mode plus scenario-driven cases
  • Multi-turn text and voice interaction
  • Editable patient system prompts
  • End-of-session OSCE-style evaluation
  • Static HTML proof-of-concept entry point

Users

Medical learners and educators

Goal

Repeatable communication practice

System

FastAPI, scenarios, voice, evaluation

Status

MVP prototype

Product Summary

The simulator gives learners a low-friction way to practice patient communication without live standardized patients. The revamped implementation supports defined patient cases, transcript-aware responses, optional voice workflows, prompt customization, and structured feedback after the encounter.

Problem

OSCE-style practice is expensive, scheduled, and difficult to repeat. Basic chat demos are easier to access, but they often lack scenario fidelity, patient consistency, and useful evaluation. The product bridges those gaps with a lightweight simulation environment.

Core Requirements

  • Expose a list of public scenarios from the backend.
  • Allow the learner to select either Generic VSP Mode or a structured patient scenario.
  • Preserve transcript history so patient responses stay coherent across turns.
  • Support typed messages, microphone input, and optional audio playback.
  • Generate structured evaluation JSON from the transcript and selected scenario.
  • Render evaluation feedback in a readable report.

Product Principles

Keep the entry point simple, preserve backward compatibility with the original generic VSP workflow, make patients specific, expose prompt experimentation for builders, and treat AI evaluation as formative learning rather than credentialing.

Success Metrics

  • Scenario load success rate
  • Text and voice conversation completion rates
  • Evaluation completion rate
  • Average learner turns per session
  • User-rated scenario realism and evaluation usefulness
  • Prompt override usage by builders or educators

Next Release Priorities

Priorities include transcript persistence, saved evaluations, a more extensible scenario format, stronger safety and consistency constraints, a modern frontend shell, and side-by-side tools for prompt experiments.