AI product engineering

I build the parts of an AI product that surround the model: the voice and chat people use, the retrieval that decides what the model sees, and the controls a team needs to run the assistant after launch. Most of that 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

LegalAgent's assistant answers from case context, document summaries, and procedural guidance in Spanish and English. I built RAG over those sources for both voice and chat, used OpenAI's Realtime API for bilingual transcription and synthesis, and adjusted the assistant's persona and AI SDK tool calling after attorney sessions showed how they used it.

The team runs the assistant from a TanStack Start admin with Microsoft SSO, where they manage documents, system prompts, and the categories that decide what retrieval can reach.

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 OpenAI image generation into a Next.js flow and minted the results as NFTs on Flow 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.