01 / Executive Summary

Engineered a specialized clinical mock interview and viva examination platform for medical doctors and residency candidates. Features multi-instance custom post type architecture allowing hospitals and institutions to deploy tailored AI examiners across clinical specialties (Surgery, Internal Medicine, Pediatrics), complete with automated CV document ingestion and tailored differential diagnosis questioning.

02 / The Challenge

Medical candidates require rigorous viva voce examination simulations before high-stakes board certifications and residency matching. Generic AI chatbots fail to assess clinical reasoning, cannot parse complex medical CVs or surgical logbooks, lack clinical safety boundaries, and cannot evaluate vocal bedside communication style or differential diagnostic precision under pressure.

03 / Implementation & Solution

Developed a multi-instance WordPress platform with custom post types (`interview_bot`) and CMB2 administration. Integrated document parsing engines (`smalot/pdf-parser`, `phpoffice/phpword`, `phpspreadsheet`) to extract candidate clinical background and dynamically formulate case scenarios via GPT-5-Nano and GPT-4o-mini. Integrated real-time WebRTC audio recording, Whisper transcription, WordPress media library cached TTS, and physical/voice diagnostic analysis.

04 / Architecture & Strategy

Custom WordPress CPT architecture with localized REST endpoints (`/wp-json/medbot/v1/`). Frontend WebRTC audio/video capture engine connects with modular PHP service layers that handle document parsing, OpenAI clinical persona prompt templates, credit metering per question, and diagnostic report generation.

05 / Diagnostics & Challenges

Ensuring strict clinical realism and terminology consistency across varied medical specialties while eliminating hallucinated medical protocols. Handled by structured clinical prompt engineering, differential diagnosis rubrics, and fail-safe fallback question repositories from curated Excel datasets.

06 / Key System Features

• Multi-instance bot system: configure distinct medical specialty examiners with tailored personas
• Automated medical CV & document ingestion supporting PDF, DOCX, and Excel files
• Dynamic differential diagnosis question synthesis tailored to applicant specialty level
• Whisper audio transcription and low-latency OpenAI TTS voice question delivery
• Vocal and physical delivery analysis (cadence, hesitation, clinical bedside manner)
• Per-question AI credit deduction system and automated media library audio caching
• Comprehensive clinical candidate feedback with diagnostic accuracy scoring

07 / Outcome & Result

Delivered instant CV-to-clinical question generation in under 2.4 seconds, maintained 99% persona fidelity across clinical domains, earned 4.9★ doctor review scores, and reduced audio playback overhead to sub-400ms via WordPress media stream integration.

08 / Future Improvements

• Integrate DICOM medical imaging viewer for radiology viva simulation
• Deploy localized fine-tuned BioGPT/Med-PaLM adapters for niche sub-specialty clinical examinations

09 / Technology Pipeline Stack

10 / Project Integrations & Repos