Nik Patel

Mood-aware Bhagavad Gita companion (React + Claude API)

A mobile-first reading companion that surfaces verses based on the reader's current emotional state, in 10 Indian languages.

Built a React app for daily Gita study where users can describe how they're feeling — anxious, grateful, lost, restless — and get contextually relevant verses surfaced from the full text. Each verse comes with translation, transliteration, and AI-generated context using the Anthropic API. Multi-language support across 10 Indian languages with proper script rendering and right-to-left handling where needed. Light/dark/system theme toggle that respects OS-level preferences.

The interesting engineering: keeping the Claude API calls cheap enough to be free for users (request batching, prompt caching, response trimming), and making the language-switching feel instant rather than fetch-on-toggle.

Tech: React, Tailwind, Anthropic Claude API, i18n

Browser-based RAG chat for a B2B documentation knowledge base

A retrieval-augmented chat interface running entirely in the browser, indexing a client's full product documentation and answering questions with cited sources.

Designed and built a browser-based RAG (retrieval-augmented generation) chat for a B2B SaaS client's customer-facing documentation. Used Google's text-embedding-004 for embeddings and Claude Sonnet for response generation. The interesting parts were the operational ones: most "RAG demos" assume direct API access from the browser — production environments rarely allow that. I designed a CORS proxy fallback strategy plus a manual paste workflow so the system degrades gracefully when corporate networks block direct API calls.

Built so the client could ship it without standing up a Python backend or vector DB infrastructure they'd then have to maintain.

Tech: JavaScript, Google text-embedding-004, Claude Sonnet, CORS proxy fallback

Architecture walkthrough → (anonymized — happy to walk through architecture on a call)

Real-time inventory search for real estate agents

A Rails + React platform serving live pricing and availability across millions of property listings, with sub-second filtering on 15+ dimensions.

Built for a real estate SaaS company whose agents needed to generate up-to-the-minute, client-ready property lists in seconds, not minutes. The platform indexes millions of inventory units across multiple cities, with 15+ filter dimensions (price, layout, amenities, proximity, availability windows, builder, possession date, and more) returning filtered results in milliseconds.

The hard parts: keeping the inventory data fresh as feeds arrived from dozens of sources with conflicting schemas, and making complex multi-filter queries feel instant. Used PostgreSQL with carefully tuned indexes and Redis for hot-path caching, plus a write-side normalization layer that absorbed the source-data chaos so the read side stayed clean.

Tech: Rails, PostgreSQL, React, Redis

Architecture walkthrough → (anonymized — full architecture available on call)