Product Lead · AI systems, zero to one
Founding PM at Proxity. In 2026 I shipped two AI products to production, a due-diligence engine and an editor-gated AI pipeline for the deal market, both built spec-driven with parallel AI coding agents. Before that: scaled a legal-media platform to 150K MAU and $500K ARR. Background in insolvency and banking law.
An internal due-diligence engine for the group's investment team: 13 stages, cited facts, human review. Agentic loops only in 2 of 13 stages - per-stage LLM cost ~3x lower. Alongside it, I run the Proxity platform itself with an external dev team.
A self-enriching market-intelligence graph for asset deals: an AI pipeline drafts, a human editor decides, and every decision feeds back into the graph. Public launch planned for Q4 2026.
Built the product organization from scratch, monetized the B2B side with a custom CRM, then returned as a consultant to ship AI automation across the operation.
Designed the methodology, personally ran the interviews, and turned raw market data into a top-30 ranking and a public B2B analytics platform for international investors.
Analyzed how lawyers actually worked, then shipped document automation, analytics API integrations, and a knowledge portal for 200+ employees.
I'm a product lead who takes AI products from zero to production. Right now I own the product at Proxity, an invite-only deal platform, and build two AI products for the group: a due-diligence engine the investment team runs every day, and an editor-gated AI pipeline that grows a knowledge graph of the deal market.
How I build: spec-driven, with parallel AI coding agents (Claude Code, opencode). A versioned PRD, a domain glossary and architecture decision records are the agents' source of truth; the scope, the architecture and the review stay mine. I've worked hands-on with generative AI since 2022.
My path here wasn't typical. I started as a corporate and banking lawyer in Russia and spent five years on insolvency cases. I kept running into legal work that could be structured, automated and turned into software, so I moved into product: legal automation first, then a legal-media platform I helped scale from concept to 150K MAU and $500K ARR.
My approach: dig into the "why" behind a problem before jumping to solutions, measure what I can, and name the trade-offs out loud. I'm based in Valencia, Spain, with full work authorization.
Three merged pull requests to the AI reading-assistant plugin for KOReader: dictionary with sentence context and translation, an AI dictionary gesture on text selection, and a model picker for OpenRouter. Started as reading sci-fi in English, ended as shipped features.
A Firebase app that turns a rough research question into a precise Deep Research prompt through AI-generated clarifying questions - a pre-research step that saves 10-15 minutes of prompt tweaking per report.
One of four talks I gave at QA Breakfast Valencia in 2025-2026, three of them on AI. This one closed the June 2026 season at RingCentral: what AI-speed building does to product judgment - argued through a feature I shipped in an evening with zero review changes, and a feature engineers built where I found 9 product and UX issues.
The system behind 70-80% agent-written code with 100% human-owned architecture and review: blocked git push, ADRs as context, and honest numbers on what changes.
Hands-on notes on prototyping and applied AI: prototyping with Firebase, what got cheap and what got expensive in AI-speed building.