Klarity.ai / DevContext.AI

AI Repository Intelligence for Recruiters
TYPESCRIPTAWSLLMs
// Problem

Recruiters and interviewers struggle to understand architectural decisions, code complexity, and individual contributions just by looking at a GitHub repository.

// Solution

A 3-stage AI intelligence pipeline that transforms GitHub repos into recruiter-ready reports and simulated interview sessions.

// Overview

DevContext.AI is an intelligence platform that analyzes GitHub repositories to generate employability scores, code-quality metrics, and mock interviews. The system uses a grounded AI approach, referencing specific files and line numbers to avoid hallucination, and distinguishes between developer code and boilerplate framework code. It utilizes a multi-model strategy via Amazon Bedrock (Claude Haiku for fast reviews, Sonnet for deep architecture analysis).

// Breakdown
01
Pipeline

3-stage pipeline: Project Review (~30s), Intelligence Report, and Interview Simulation.

02
Grounding

AI claims are grounded in actual repository evidence (file paths and line numbers) to prevent hallucination.

03
Scale Targets

Designed for 10+ concurrent analyses, 50MB repositories, and >50K tokens.

04
Architecture

React frontend, AWS SAM serverless backend, DynamoDB, and WebSocket protocols.

// At a Glance
Speed
~30s initial
Models
Claude Family
Backend
AWS Serverless
Context
>50k tokens
// Tech Stack
ReactTypeScriptAWS SAMAmazon BedrockClaude 3.5 SonnetDynamoDB