Skip to content
RAKIB.
ProjectsAI Interview Platform & SaaS

MockMate AI - Intelligent Interview Coach

Voice-first technical interview coach delivering realistic simulation and instant rubric feedback.

2026·Full Stack Developer
mockmate-ai-self.vercel.app
MockMate AI - Intelligent Interview Coach — case study preview

Executive Summary

The Challenge

Practicing for technical interviews alone makes it hard to assess your own responses objectively, and cloud transcription adds unnecessary cost.

The Solution

Browser-native Web Speech API for zero-cost transcription, Google Gemini 2.5 Flash with strict JSON schema for structured feedback, and MongoDB for session persistence.

Measurable Impact

Fast rubric evaluation, zero transcription cost through browser-native speech, and structured feedback with score, critique, and model answers.

Technologies

Frontend
Next.js 15TypeScriptTailwind CSS v4Shadcn UIWeb Speech API
Backend
Server ActionsGoogle Gemini 2.5Clerk AuthStripe Payments
Database
MongoDBMongoose
DevOps
Vercel

Key Decisions

Why Server Actions over API Routes?

Since we needed direct, low-latency database mutations from the client form, Server Actions eliminated the need to maintain boilerplate API routes.

Why Gemini 2.5 Flash?

Interview feedback requires near-instant responses. Gemini Flash offered the perfect balance of speed and high reasoning capabilities over heavier models.

Why native Speech Recognition?

Instead of dealing with heavy audio file uploads and server-side transcription, using the browser API handled it locally with zero cost and zero latency.

Retrospective

Hardest Part

Handling edge cases with browser compatibility for the native Speech Recognition API, especially across different mobile devices.

Biggest Insight

Achieving reliable AI outputs in production requires treating schemas as contracts. Enforcing strict JSON schema validation and atomic credit decrement before LLM calls eliminated hallucinations and edge-case double spending.

Do Differently

I would implement WebSockets for streaming the AI response word-by-word instead of waiting for the full JSON block to load.

Key Highlights

AI Question Generation

Generates 5 unique technical questions based on Job Role & Tech Stack.

Voice-to-Text Engine

Records user answers in real-time using browser-native Speech API.

Instant AI Feedback

Analyzes answers to provide 1-10 ratings and improvement tips.

Interview History

Dashboard to track performance trends and review past feedback.

Next Project

Cisco Chemicals - B2B Manufacturing Platform

Interested in discussing this project or exploring collaboration? Let's talk