AI product engineering

A production AI product is mostly not the model. It is the voice and chat around it, the retrieval that decides what the model even sees, and the controls a team needs to run the thing after launch. That is the part I build.

Most of the work sits on the line between what the model gets to decide and what stays ordinary application logic.

AI product engineering

LegalAgent: voice, chat, and retrieval

For LegalAgent, I built a React Native and Expo assistant with voice, chat, bilingual realtime transcription and synthesis, and RAG for case context and document summaries. I sat with attorneys at the firm to see how they used the assistant. That feedback drove persona changes and tighter tool calling in the React Native client.

I also built the TanStack Start administration system for Microsoft SSO, document management, prompt controls, and retrieval categories so the team could change access, sources, and instructions after launch.

Specialized assistants inside larger products

For Masterbots, I built separate interfaces for domain-specific assistants and integrated AI SDK tooling so each assistant stayed scoped to its domain.

For Bitlauncher, I built a RAG chatbot with tools for current news and video content and added AI-assisted internationalization. The assistant could retrieve and explain information while balances, bids, contracts, and transactions remained grounded in deterministic application data.

Further back, Wizard World was a 2022 Flow Hackathon PWA that wired DALL-E generation into a Next.js flow and minted the results through Niftory.

Writing about AI products

AI employment record

The employment record behind this work is the AI CV.

Open to direct hire, international hire, or contracting through Blockmatic Labs LLC. Cannot work under W-2. Based in Costa Rica, working US Mountain Time.

Tell me what you're building and where it's stuck. Start a conversation.