Projects using Claude in Los AngelesProjects using Claude in Los AngelesLed delivery of a cloud-native K-12 student wellness platform that helps counselors monitor wellbeing, surface at-risk students, and act early—balancing product velocity with FERPA/COPPA-aware design and multi-tenant isolation (API RBAC, PostgreSQL RLS, district-scoped analytics).
→ Owned technical direction and delivery rhythm across a TypeScript monorepo (pnpm/Turbo):
backend API, web app, shared packages, DB migrations, CI/CD gates, and staged deploys to GCP (e.g. Cloud Run), aligning engineering work with roadmap and release risk.
→ Orchestrated an AI assistant for counselors on Google Vertex AI (Gemini):
system prompts, safety settings for K-12, function-calling tool design, multi-round tool loops, and strict separation so UI widgets render from verified tool results—not model hallucinations—with tracing/feedback hooks (e.g. Langfuse) for quality and auditability.
→ Drove access-control and compliance posture for sensitive student data:
role/permission middleware, tenant-scoped queries, and defense-in-depth database policies—documentation and evidence suitable for enterprise security reviews (e.g. SOC 2–style narratives).
→ Partnered on product and program management:
phased feature rollout, PR/branch discipline, and clear ownership of scope vs. risk so pilot schools could onboard without compromising data boundaries.
→ Shaped integrations and platform boundaries:
Firebase auth, Neon PostgreSQL + Drizzle ORM, real-time patterns, BigQuery analytics isolation, and operational practices (testing, lint, type-check) that keep the stack maintainable at scale.
→ Established a disciplined, AI-accelerated delivery model—not ad-hoc prompting:
Cursor rules and Claude skills/agents for repeatable workflows; Husky + lint/type-check/test gates; GitHub Actions CI/CD; Cursor Cloud Agents for automated PR review; and daily monitoring of E2E, coverage, and critical issues—owning AI-orchestrated implementation while enforcing accuracy, consistency, and observability There are 100,000+ museums worldwide. Exploring culture, history and art has become more about ticket sales and less about learning.
Introducing Museum Envy. A website & mobile app that uses AI-powered data enrichment to help people discover museums and cultural sites using important, typically hard-to-find information like time to visit, kid-friendliness, free days, accessibility and more.
There will also be Journeys and Passports. Offering playlists of museums enriched by history and art. Users can check-in, document and earn badges to share.
It will be free to use with a $30/yr premium subscription offering enriched journeys, offline features, create-your-own journeys, smart planning & more! Revenue will also come from ads and museum partnerships.
Early prototype (much to do!):
https://museumenvy.com/version-test/
A full-stack personal productivity app built for daily use ,not as a demo, but because I actually needed it.
The app has a three-part daily journal (morning planning, midday check-in, evening reflection), a meal planner, a habit tracker with streaks, a recipe journal, and a weekly summary view. Every tab has a built-in AI assistant powered by Claude that knows your context ,what you planned, what you ate, what habits you're tracking — and gives grounded, specific help instead of generic responses.
Built with Next.js, TypeScript, Drizzle ORM, Neon (serverless Postgres), and the Anthropic Claude API with streaming responses. Designed mobile-first as a PWA so it installs on your phone like a native app.
The kind of project that only gets built when you're solving a real problem for yourself. Client Website - Bloom Boutique
Built a complete website for a curated floral boutique using BizStack AI's automated delivery engine - designed, animated, and deployed SAME DAY.
Delivered: scroll-animated site with fade-in reveals and stat counters, custom Playfair Display + DM Sans typography, AI-generated images via Kie.ai (http://Kie.ai) (no stock photos), lead capture popup, working AI chatbot with 20 industry FAQs, contact form, blog template, full mobile responsiveness, Schema.org (http://Schema.org) structured data, and SEO setup.
No templates. No stock assets. Every element custom to the client's brand.
Live: bizstack-bloom-boutique.vercel.app (http://bizstack-bloom-boutique.vercel.app) A working demonstration of how AI integration replaces hours of finance work with minutes. Three real workflows shown end-to-end with before/after data:
Transaction categorization. Messy bank/card transactions (wires, AMEX charges, vendor descriptions) auto-categorized, vendor-cleaned, and pivoted into a category summary. Manual: 2–3 hours for 200 transactions. AI-assisted: 5 minutes.
Investor commentary drafting. Raw quarterly performance data (NAV, returns, watchlist movement, pipeline) turned into polished investor letter copy. Manual: 1–2 hours of writing per quarter. AI-assisted: 10 minutes of editing.
Portfolio company summarization. Unstructured sponsor letters and press releases parsed into a structured tracking table with revenue, margins, leverage, and status flags. Manual: 30–45 min per company. AI-assisted: instant. The integrations are built INTO existing Excel workflows — no new tools for the team to learn. Two common patterns: copy/paste with Claude, or direct API integration via VBA / Office Scripts. The "after" sheets look like normal Excel because they are; AI just did the manual work. Illustrative samples built for portfolio purposes. Happy to scope an automation for your specific finance workflow.
