Projects
Recent work, deeper cuts
Detailed breakdowns of the systems, outcomes, and reliability patterns I ship.
Research Paper Judge
Multi-agent AI system that evaluates arXiv research papers and generates peer-review-style reports with PASS/FAIL verdicts and scored dimensions.
Problem
Manual peer review is slow, inconsistent, and doesn't scale — reviewers apply different rubrics, miss key dimensions, and create bottlenecks.
Approach
Built a multi-agent pipeline with two sequential waves: Wave 1 runs Grammar, Novelty (with live Google Search), and Fact-Check agents concurrently; Wave 2 runs Consistency and Authenticity agents in parallel; a final Evaluator agent applies weighted scoring to produce a PASS/FAIL verdict.
Value
Structured, explainable peer-review reports in seconds — traceable per-dimension scores with rationale, not just a verdict.
Dev Debugger
Full-stack RAG-powered developer tool that ingests codebases, runs vector search, and answers debugging queries with AI — built on MERN with a dockerized backend.
Problem
Debugging across large codebases is slow — devs context-switch between docs, search, and code without a unified interface that understands the project.
Approach
Built a full MERN stack tool with an ingestion pipeline (POST /ingest) that indexes codebases into a vector store, a search layer (GET /search) with filters by username, project, and producer, and a RAG endpoint (POST /ai) that runs tool-call to vector search and returns an AI-generated answer.
Value
A project-aware debugging assistant that answers questions grounded in the actual codebase — not generic docs.
Unified LLM Wrapper
A developer-friendly agentic wrapper across providers with reasoning, retries, and fallbacks.
Problem
GenAI apps break when providers fail, outputs drift, and retries aren't standardized.
Approach
Designed a unified interface with routing, retries, and fallbacks built-in.
Value
Faster experimentation, less integration glue, and more reliable production behavior.
Prescription AI Webapp
Decodes handwritten prescriptions into clear text using a vision model + MERN stack.
Problem
Handwritten prescriptions are hard to read and error-prone.
Approach
Used a vision-capable model with a web workflow for clean, readable output.
Value
Improves clarity and reduces errors for patients and pharmacies.
AWS DNS Dashboard
DNS monitoring dashboard using MERN + AWS SDK with CRUD operations.
Problem
DNS visibility and updates were fragmented across tools.
Approach
Built a single dashboard with MERN and AWS SDK integrations.
Value
Gives teams a clear, centralized view of DNS state.
Shoe Store Clone
Responsive landing page built with Tailwind CSS, React, and TypeScript.
Problem
Needed a clean retail UI baseline.
Approach
Built a responsive landing page with Tailwind and React.
Value
Strong baseline for retail product presentation.
ML Projects
Sentiment analysis + stock price prediction with Python tooling.
Problem
Needed model-driven insights from noisy real-world data.
Approach
Built pipelines and models for sentiment and stock prediction.
Value
Demonstrated end-to-end ML modeling and evaluation skills.
Samurai Stimulator
Dual-player browser game built with JavaScript, HTML, CSS.
Problem
Explored event-driven UI and gameplay mechanics.
Approach
Built a lightweight game with vanilla JS and DOM updates.
Value
Showcases interaction design and performance on the web.
Want a custom GenAI system built end-to-end?
Reach out and I will scope it fast, then ship with reliability in mind.