Enigma - AI Viva Platform

Tech Stack

Next.js, TypeScript, Python, Supabase, Tailwind

Role

Full Stack Developer

Date

November 2026

Enigma is an AI-powered assessment platform that verifies genuine student understanding through interactive voice vivas. Powered by an independent Python/FastAPI intelligence pipeline, it extracts core concepts from submissions, conducts adaptive follow-up questioning, and generates evidence-based diagnostic reports.

About Enigma

Enigma AI Viva Dashboard
[Challenge]

The Gap Between Submission and Mastery

A submitted assignment or codebase proves an output exists, not that the student understands how it works. Traditional written exams rely on generic question banks, while manual one-on-one vivas require too much faculty time to scale. Meanwhile, AI-authorship detectors are unreliable. Educators needed a scalable way to test whether students can actually explain, defend, and reason about their own work.

Assessment Challenge
[Solution]

Interactive Voice-Based AI Vivas

I engineered the AI intelligence layer for Enigma—an end-to-end oral assessment platform built around real classroom workflows. Teachers create classes with unique join codes and publish assignments. Once a student attaches their work, Enigma analyzes the document and conducts a personalized voice viva that probes their conceptual reasoning in real time.

[Architecture]

Modular Monolith & Independent AI Service

To keep orchestration clean and scalable, we decoupled the core web application from the AI compute layer. Next.js and Supabase act as a secure Backend-for-Frontend (BFF) handling authentication, classroom access control, and state transitions, while communicating over strict OpenAPI contracts with my independent Python and FastAPI AI service.

[AI Pipeline]

Concept Extraction & Adaptive Questioning

Instead of asking static questions, the FastAPI pipeline parses each student's submitted PDF, extracts key technical concepts and implementation decisions, and generates difficulty-calibrated primary questions. During the session, the engine evaluates each spoken answer and dynamically generates follow-up probes to investigate vague explanations or test edge-case scenarios.

[Diagnostics]

Evidence-Based Assessment Reports

Enigma goes beyond keyword matching by evaluating conceptual accuracy, reasoning depth, and alignment with the submitted work. At the end of every viva, the system compiles a structured diagnostic report detailing demonstrated strengths, partial understandings, specific misconceptions, and targeted recommendations for both students and teachers.

Process

[01]

Document Intelligence

Built Python pipelines to parse uploaded academic PDFs, extract core topics, algorithms, and architectural decisions, and map testable learning objectives.

[02]

Structured Question Engine

Designed Pydantic-validated LLM workflows using Groq and Gemini to generate personalized, multi-difficulty viva questions grounded strictly in the student's work.

[03]

Voice & STT Integration

Integrated low-latency Speech-to-Text processing over private Supabase audio storage to transcribe student responses reliably before evaluation.

[04]

Adaptive Follow-Up Logic

Engineered state-aware evaluation prompts that detect misconceptions and trigger targeted follow-up questions rather than moving blindly to the next topic.

[05]

Classroom & BFF Contracts

Aligned FastAPI endpoints with Next.js Route Handlers via shared OpenAPI and Zod schemas to support teacher class codes, assignment tracking, and final reports.

[Results]

Scalable Oral Assessment

Enigma turns every written assignment into an interactive oral defense without adding manual grading overhead for instructors. By combining classroom management with an autonomous, evidence-based AI examiner, the platform gives teachers clear visibility into genuine student comprehension while giving learners actionable feedback.

Enigma Platform Results

100%

Relevant Questions

3-Tier

Concept Mastery Diagnostics

2-Way

Adaptive Voice Questioning

Zero

Client-Side LLM Exposure