Senior fintech product leader building practical AI systems for product teams, signal curation, and human-in-the-loop agent workflows.
I lead product teams in fintech and build hands-on AI/product systems that turn messy inputs — market signals, discovery notes, screenshots, specs, agent work — into reviewable decisions.
My current thesis: AI is most useful when it is connected to a real workflow, grounded in source evidence, and constrained by clear human approval boundaries.
| System | What it proves | Status |
|---|---|---|
AI Signal Desk |
Converts AI news, repos, papers, and concepts into practical calls: learn, try, watch, or ignore. | Live at aisignaldesk.ai |
skval |
Scores Claude Code skills with deterministic checks, safety gates, eval fixtures, and ship/revise/reject scorecards. | CLI + docs |
firehose |
Keeps AI coding agents aligned with product intent through specs, tasks, verification, and completion artifacts. | Workflow toolkit |
vyno |
Local-first AI digest pipeline with source curation, scoring, Telegram delivery, Obsidian archiving, and an operator console. | Personal automation |
hermes-product-teams |
Product memory agent for discovery notes, insight extraction, decision logs, PRD proposals, and weekly briefs. | Product-team prototype |
shotback |
Screenshot capture, annotation, timeline feedback, and LLM-ready visual review context for product/design QA. | Chrome workflow |
Most AI products fail in the gap between impressive output and trusted operation. I’m interested in the operating layer in between:
- Product memory — preserving discovery, decisions, tradeoffs, and source context.
- Signal curation — reducing information overload into useful next actions.
- Human approval loops — AI drafts, ranks, and proposes; people decide.
- Agent operating manuals — specs, guardrails, checks, and artifacts that make AI-assisted work reviewable.
- Local-first automation — useful systems that remain inspectable, portable, and permission-aware.
- AI/product intelligence:
AI Signal Desk,vyno - Agent workflow quality:
skval,firehose - Product team systems:
hermes-product-teams,shotback - Prototyping and interface systems:
sandy,loopy
I’m a Group Product Manager / Sr. Manager at Neon in São Paulo, with previous product and fintech experience at Mercado Libre, Leve, PagSeguro PagBank, and ConectCar.
I use GitHub as a public workshop for practical AI/product systems: small enough to inspect, real enough to validate, and opinionated enough to show how I think.
- Start with the user workflow, not the model.
- Keep evidence attached to generated claims.
- Prefer reversible, inspectable systems over opaque automation.
- Use deterministic checks and fixtures wherever possible.
- Treat agents as collaborators that need context, constraints, and review.
If you’re building at the intersection of product leadership, fintech, and practical AI systems, I’m happy to compare notes.