Klarity
AI Repository Intelligence for Technical Recruiting
- Author
- Rounak Neema
- Category
- Recruiting Tech
- Language
- React / AWS Serverless
- Status
- active
Project Ref: devcontextStatus: active
Turn Code Into Context.
src/
├── scanner/
│ ├── network.go ← ANALYZING...
│ └── fingerprint.go
├── plugins/
└── storage/
Architecture0%░░░░░░░░░░░░░░░░░░░░
Security0%░░░░░░░░░░░░░░░░░░░░
Complexity0%░░░░░░░░░░░░░░░░░░░░
Authenticity0%░░░░░░░░░░░░░░░░░░░░
┌─ GROUNDING ASSERTION ─┐
'The scanner uses bounded concurrency.'
Evidence: scanner/network.go Lines 45–89
VERIFIED — 3 direct references found
Structured Facts
- Built by
- Rounak Neema
- Primary Stack
- React & AWS Serverless
- AI Engine
- Amazon Bedrock / Claude
- Key Differentiator
- Repository Grounding
Metric_1 // Speed
~30s initial
Metric_2 // Models
Claude Family
Metric_3 // Backend
AWS Serverless
Metric_4 // Context
>50k tokens
The Challenge
Recruiters and interviewers struggle to understand architectural decisions, code complexity, and individual contributions just by looking at a GitHub repository.
The Solution
A 3-stage AI intelligence pipeline that transforms GitHub repos into recruiter-ready reports and simulated interview sessions.
System Context
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).
Pipeline
3-stage pipeline: Project Review (~30s), Intelligence Report, and Interview Simulation.
Grounding
AI claims are grounded in actual repository evidence (file paths and line numbers) to prevent hallucination.
Scale Targets
Designed for 10+ concurrent analyses, 50MB repositories, and >50K tokens.
Architecture
React frontend, AWS SAM serverless backend, DynamoDB, and WebSocket protocols.
Frequently Asked Questions
What is Klarity?
Klarity is an AI Repository Intelligence tool designed for technical recruiting to provide accurate insights.
How does it prevent hallucinated assessments?
It utilizes repository grounding to anchor AI responses in actual codebase reality, significantly reducing hallucinated assessments.
How does repository grounding work?
Repository grounding works by analyzing the candidate's actual code repository, understanding its context, and feeding this precise context to the AI (Amazon Bedrock / Claude).
What is the primary tech stack?
The primary stack includes React for the frontend and AWS Serverless for scalable backend processing.
Who built Klarity?
Klarity was built by Rounak Neema.
What AI models does Klarity use?
Klarity leverages Amazon Bedrock and Claude for its AI capabilities.
What is the key differentiator of Klarity?
The key differentiator is its robust repository grounding mechanism.