Case studies · 10 · 2026
Case studies.
Long-form write-ups of the AI products I shipped end-to-end — read as product + market research, not just build logs. Each one walks the same arc: Market → Problem → Constraints → Architecture → Trade-offs → Goals → Outcome, with cited 2026 market numbers, competitive positioning, and — where it exists — the underlying research embedded in-browser.
Real-time AI mock interviews with low-latency voice, LLM-driven resume tailoring per JD, job matching, and university partnerships. Smart Recruiter unified backend.
516 TS files / ~101k LoC~17k LoC Python WebRTC microservice
- Real-time AI voice mock interviews — Pipecat + LiveKit + Claude + ElevenLabs + Deepgram
- LLM-driven resume tailoring per JD with RAG over candidate documents
- Job matching, application tracker, interview prep, upskilling paths
- Resume parsing pipeline: Tesseract OCR + pdf-parse + mammoth
- Multi-payment integration: Razorpay, Stripe, Apple Pay
NestJS
FastAPI
Pipecat
LiveKit
Claude (Anthropic SDK)
ElevenLabs
Deepgram
OpenRouter
MongoDB
BullMQ
AWS
13-app monorepo running an Indian junior-college group end to end: attendance, exams, AI question generation, handwritten-paper grading, analytics and parent comms. Live across 12 campuses.
13 apps4,735 students live7.6M exam answers
- 447 of the repo's 2,688 merged PRs are mine; most commits of any contributor
- Admissions CRM with an AI voice agent that calls new enquiries in five minutes (~220k LoC)
- IPE: AI grading of handwritten answer sheets, 12,847 marks reviewed by faculty in prod
- Hono API (152 route modules), Drizzle over Postgres — 323 tables, 216 migrations
- 125,299 questions in the bank, 78% AI-drafted, none published without faculty approval
Next.js 15
React 19
Expo SDK 55
Hono
Effect v3
Drizzle ORM
PostgreSQL
Redis
BullMQ
Claude
LiveKit
AWS ECS Fargate
Northway TechLive
AI Voice Caddie ft. Andy North (2× US Open Champion)
Senior Software Developer & Team Lead · VoiceQube
Voice-enabled golf companion: hands-free course navigation, contextual AI shot recommendations from course / weather / player history, AI shot recording with analytics.
- Real-time voice caddie via LiveKit + WebRTC stack
- MongoDB geospatial indexing for live GPS course position
- AWS Lambda + MediaConvert for shot video capture and processing
- Production-grade across 40,000+ golf courses (event-driven backend)
- Voice + intent stack with Anthropic Claude in the loop
LiveKit
WebRTC
Pipecat
ElevenLabs
Deepgram
Claude
MongoDB (geospatial)
AWS Lambda
MediaConvert
CloudFront
Co-founded multi-market wedding / events platform. iOS, Android, web; ML-powered planning, vendor marketplace, viral QR photo-sharing. Founding engineering leader.
- Architected end-to-end across iOS, Android, web, vendor ecosystem
- ML-powered planning workflows and intelligent vendor matching
- Viral QR photo-sharing for live event capture
- Live on App Store and Google Play; multi-market customer base
- Established engineering culture, CI/CD automation, technical roadmap
React Native (Expo)
Next.js
NestJS
MongoDB
AWS
Stripe
ML pipelines
Behavior-change app for tobacco cessation funded by the Indian Council of Medical Research (ICMR). Personalized AI chat coach, progress tracking, goal setting, and 24/7 motivation pathway. Built under guidance of Dr. Anil V. Ankola; ICMR STS-backed research project.
1st Place AIDEC3rd Place AIDECICMR STS
- Personalized AI chat coach with server-side key handling (Apple-compliant)
- Care-pathway with goal setting, progress tracking, motivation, flexibility
- ICMR STS-funded research project; psychometric analysis and UX study
- Award-winning: AIDEC 1st place, 3rd place, plus ICMR Short-Term Studentship
- Open-source react-native boilerplate ancestry (rodriguescarson-maeda)
React Native (Expo)
TypeScript
Redux Toolkit
Gemini API
Supabase Edge Functions
Vercel
Mobile app at the intersection of oral health and HIV care — behavior change and care-pathway tooling for an underserved patient population. Same care-pathway pattern as SmokeMukti, applied to a new clinical domain.
- Care-pathway design adapted from SmokeMukti to oral-health × HIV intersection
- Live on both App Store and Google Play
- Built on Expo / React Native with Redux Toolkit and React Navigation 6
- iOS build via EAS; Apple-compliant data and login flows
Expo 54
React Native
Redux Toolkit
React Navigation 6
TypeScript
EAS
Full-stack relationship platform for couples — mobile (Expo) plus a web presence on Cloudflare, backed by Supabase. Albums, love letters, mood tracking, date planning, mediation, and weekly stories, with opt-in AI helpers for quizzes, translation, and writing.
- AI-native architecture — Groq for fast couples-specific prompts, Claude for safety-critical paths; AI features opt-in and configurable
- Supabase Realtime for live shared albums, notes, and couple-specific collaboration
- Multilingual from day one — 8 locales (en, es, pt, hi, tl, ar, ko, fr) including RTL
- Rich feature set: albums, love letters, games, mood tracking, date planning, gift ideas, mediation, memory books, weekly story generation
- Web on Cloudflare (Astro + Workers) + mobile via Expo over a shared Postgres backend with edge functions
React Native (Expo)
Astro
Cloudflare
Supabase
Postgres
Groq (Llama 3.3)
Claude (Anthropic SDK)
i18next
NativeWind
TypeScript
Privacy-first mental-wellness app — journaling, mood tracking, breathing and grounding exercises, and an AI support companion with safety guardrails. All data stays on-device by default; nothing syncs to a backend.
- AI mental-health companion on Groq (Llama 3.3 70B) with a guardrailed system prompt that refuses diagnoses, medication advice, and harmful content
- Crisis-signal detection auto-surfaces SOS resources; prompt-injection hard refusal and per-message clamping at the edge
- Breathing and 5-4-3-2-1 grounding exercises animated with Reanimated 4
- Daily mood check-ins with streak tracking and trend visualization
- Privacy-first — chat, mood, journal, and check-in data stored locally, with one-tap erase
React Native (Expo 54)
React 19
Expo Router
Reanimated 4
Vercel Edge Functions
Groq (Llama 3.3 70B)
Firebase Auth
TypeScript
Location-based food discovery app surfacing restaurants, hotels, and street-food spots curated by a food traveler. Map-based discovery, saved lists, an AI dining concierge, photo/review contributions, and in-app payments.
- Google Maps integration — geolocation, clustered nearby discovery, and direct navigation
- AI dining concierge on Groq over Vercel Functions, with seeded places injected as RAG context
- Influencer-curated spots with a Supabase seed pipeline; photo uploads, reviews, and saved lists
- Google OAuth + Apple Sign-In across Web, iOS, and Android
- RevenueCat Pro tiers for consumers + Stripe vendor/brand-deal checkout
React Native (Expo 54)
React 19
react-native-maps
Google Maps API
Supabase
Vercel Functions
Groq (Llama 3.3)
RevenueCat
Stripe
Styled Components
TypeScript
HealthifyMe-style calorie and nutrition tracker — AI photo 'Snap' logging that turns a meal photo into macros, barcode scanning over Open Food Facts, water / weight / exercise tracking, and Apple Health / Health Connect sync. Multilingual from day one.
- AI Snap — photo → macros via a Supabase Edge Function calling Claude (analyze-food)
- Barcode scanning over Open Food Facts for instant nutrition lookup
- Apple Health (HealthKit) + Android Health Connect two-way sync
- Onboarding-driven calorie budget with macro rings and gifted-charts trends
- Anonymous bootstrap → email / Apple auth, RevenueCat subscriptions, i18n from day one
React Native (Expo 54)
React 19
Expo Router
Supabase
Supabase Edge Functions
Claude (Anthropic SDK)
TanStack Query
Zustand
RevenueCat
i18next
TypeScript
Want a case study like this for your product? See all projects or book a call.
All projects