Shipping agent graphs without burning your margin budget
Autonomous agents are cheap to demo and expensive to keep honest. The moment you wire “just one more tool” without a contract, your margin graph looks like a crypto wallet after a bridge hack.
AI Director · Technical Founder
Agentic AI, shipped.
From computational neuroscience to agentic AI in production. AI Director & systems architect — Madrid / EU-remote.
Selected projects
Projects I've built — from agentic RAG and gamified productivity to transformer-based summarization.
01
startlight-brain-app
A "second brain" app with semantic search, pgvector embeddings, knowledge graph, and Web Clipper — built end-to-end as a solo project.
45 commits · semantic search pipeline with hybrid retrieval (cosine + top-K) Personal project · Agentic RAG 2026 02 time-killing-app
Gamified productivity app — warriors, battles, and quests powered by OpenAI + Google Generative AI, built as a solo full-stack project.
203 commits · full-stack AI-native gamified productivity Personal project · Full-stack 2025 03 Text summarization with transformers
Summarization assistant for long-form Spanish newsroom copy with human-in-the-loop review.
Latency P95 −62% vs. monolithic baseline · human approval 4.3/5 NLP · Editor workflow 2021
A "second brain" app with semantic search, pgvector embeddings, knowledge graph, and Web Clipper — built end-to-end as a solo project.
45 commits · semantic search pipeline with hybrid retrieval (cosine + top-K) Personal project · Agentic RAG 2026 02 time-killing-app
Gamified productivity app — warriors, battles, and quests powered by OpenAI + Google Generative AI, built as a solo full-stack project.
203 commits · full-stack AI-native gamified productivity Personal project · Full-stack 2025 03 Text summarization with transformers
Summarization assistant for long-form Spanish newsroom copy with human-in-the-loop review.
Latency P95 −62% vs. monolithic baseline · human approval 4.3/5 NLP · Editor workflow 2021
Selected press & long-form
Where the work and writing have shown up over the years.
- La Razón2019
- Editorial2016
- Mediumongoing
Engagements
How teams use my time when an essay isn't enough — selectively, with prep.
Advisory
Sparring with CTOs and Heads of AI on architecture, evals, and team shape.
Implementation
Hands-on 0→1 work when a deck won't get the system out the door.
Speaking
Keynotes, panels, and editorial briefings on agentic AI in production.