I'm a PM who owns the parts that decide whether a product works — the problem reframe, the strategy, the hard trade-offs — and builds the engineering when it's the fastest path to proof. I co-founded Vendaxo, acquired by Moglix, and have since shipped six products solo across very different problem spaces.
A body of work across AI, consumer, and tooling — one explored in depth below, the rest showing range and a steady shipping cadence.
CareerAssistant, Viscollab, MarkDownCopy, and InventorySim aren't the headline acts — they're the evidence of range and cadence. I don't just plan products; I ship them, repeatedly, across different problem spaces.
How the flagship was reasoned about and built — the decisions and trade-offs, not the code.
Vendor selection isn't a search problem. It's a trust problem. Practices weren't short on options — they were drowning in 480+ of them with no one credible to match them. That single reframe set the product, the data strategy, and the safeguards.
Dental practices were drowning in 480+ vendor options with no trusted matcher. Every "directory" was a list; none answered the real question — which vendor is right for a practice like mine, and can I trust the answer?
A live AI assistant in production with a zero-hallucination eval baseline — credible enough that the founder raised capital on the platform.
In a trust product, your safeguards are your feature. Accuracy isn't a backend concern you bolt on — it's the thing the user is actually buying. So the eval suite and safeguards got first-class roadmap status, not "later."
A deliberate sequence: build the data moat first, choose an LLM-conductor architecture, make safeguards a feature, then engineer latency and cost to production-grade — kept current by a refresh pipeline.
Curate 484 vendors as structured, editorial-grade data. In a trust product the corpus is the product — no clever model rescues a thin dataset.
The first design was a hand-built state machine — brittle, every new path meant new branches. I rearchitected to an LLM conductor that orchestrates retrieval and tools dynamically.
Pair semantic search (Chroma) with keyword search (BM25) and fuse rankings with RRF. Semantic alone misses exact product names; keyword alone misses intent.
A 7-module safeguards pipeline backed by 79 tests and an eval suite. "It didn't make something up" is the headline feature — so it gets tested like one.
Drove TTFC from 38s → 15s → 2–3s (streaming + retrieval/orchestration tuning) while holding $0.03–0.05 per turn.
A repeatable refresh pipeline (on AWS Elastic Beanstalk + RDS) keeps the 484-vendor corpus current. A stale data moat stops being a moat.
Essays on product, communication, money, and building — here and on my Substack, Pages to Practice.
Always happy to talk product, AI, or building things that ship.