Seven AI agents run the full content pipeline — from deep research to publishing — so buyers find the brand on Google, ChatGPT, and Perplexity.

A real-time voice agent that turns a two-minute conversation into a complete, bookable itinerary — coaches, flights, hotels and attractions in one pass.

A modular constellation of action-oriented AI agents that integrate with existing software, share context across workflows, and ship measurable business outcomes — with full transparency via dashboards.

An AI copilot for wealth advisors, built on the Claude Agent SDK. Advisors chat naturally to research SEC filings, query client portfolios, run quant analysis (RSI, MACD, risk metrics), and execute paper trades — powered by domain-specific MCP tool servers and specialized subagents (research, data analyst, quant, audit) over an AWS S3/Athena data lake. Battle-tested in production, then extracted into a reusable agent framework with memory, skills, scheduled agents, and deck generation out of the box.

An extensible RAG chatbot framework with multi-LLM support, built with Pixeltable for vector search and Chainlit for the chat interface. Build intelligent chatbots that answer questions from product catalogs, documents, and FAQs — all through natural conversation. Demo: Built a fully functional customer support agent for Bombay Shaving Company in under 10 minutes — no code, no fine-tuning.

Built an agentic platform that helps VCs discover high-potential open source projects before they become startups. Used by a16z, Sequoia, Elevation, and Accel. The system runs a fully autonomous pipeline: ingests raw GitHub data, filters for signal, then deploys AI agents to research and score each project.