Messy data into products people trust
Product manager for data and AI products, from energy to consulting. Open to full-time PM roles.
SentinelAI: a governance gateway for enterprise LLMs
AI securityKey highlights
- Tripled attack detection, from 21% to 62% across 100 attacks.
- Catches 100% of direct injections, 80% of hidden ones and 75% of jailbreaks.
- Every decision is logged; risk teams change policies without a deploy.

Sector: a weekly planning app organized by time
A phone-first task app where time is the only way to organize: five buckets, a weekly limit and a short weekly review. Built from discovery and a PRD to a live app.
Tierwise: EU AI Act risk tiers inside Jira
A Jira app that gives each AI system an EU AI Act risk tier from 6 questions, and blocks high-risk work until evals pass and a reviewer signs off.
CaseCraft: a practice room for PM interviews
Pick a case, face an interviewer, beat the clock, get scored. 87 cases across 9 PM interview types, live as a front-end demo.
Aura: from crowded to calm
A PM audit and redesign of Aura, an AI study tutor with spaced-repetition flashcards: honest due counts, a recall-first study flow and a proposed Today screen.
I start with the user, not the dashboard.
I work best where enterprise users, messy data and AI meet. I cut what doesn't matter so teams ship what does.
Every metric earns its place.
A team can only act on a few numbers. I pick the ones that drive decisions and retire the rest, so everyone looks at the same truth.
Say no more than yes.
Every feature added is one more thing to maintain and explain. I protect the roadmap by cutting what doesn’t move the goal.
Ship the smallest thing that proves it.
I start with the smallest version that tests the idea, put it in front of real users and measure. Only what works gets scaled.
From interview to rollout.
I work closely with business teams, engineers and leadership, turning interviews and usage data into specs a dev team can build. On my own projects I run the same path end to end, from discovery and PRD to a shipped app.
Listen before building
I talk to the people who use and fund the product, from engineers to executives, before deciding what to build and what to cut.
Let usage data decide
I prioritize by how people actually use the product, so the roadmap rests on evidence, not opinions.
Prototype early, learn fast
I get a rough working version in front of real people quickly. Their reactions settle debates faster than meetings do, so we iterate or move on before over-investing.
Build the AI myself
I stay hands-on with AI agents, RAG, LLM evals and guardrails, from personal projects to enterprise solutions.