Build
Systems, models and platforms
Built small enough to ship and checked well enough to trust.
The common thread is a constraint taken seriously. A classifier that has to fit inside a browser tab. An agent that is not allowed to report what it cannot cite. A reporting engine with no model in it at all, so it cannot invent a number. A marketplace where a payment event can arrive twice and must not be counted twice.
Each case study shows the architecture, the decisions and what I would change, with every number marked by whether it can be checked.
Case studies
- 1.7 MBclassifier and runtime
- 0server calls
Corporate Signal Translator
A 1.7 MB machine learning stack that runs entirely in your browser.
- 483signals
- 65scored
- 60companies
- 48leads
Morpheus
483 public signals in, 48 ranked buyers out.
- tool calls store sources
- only cited findings pass
Raven
An SEO and AI-search agent that can only report what it can cite.
- parents book classes
- 66vendor listings imported
BabyBrain
A two-sided marketplace with bookings, payments and payouts, built from the first commit.
- any wide export
- period, entity, metric, value
Universal Financial Reporting Engine
Built deliberately without AI, so every number is computed and none is generated.
Where I did it
- Chief AI Officer, QuinyJul 2026 to present
I lead AI at Quiny, an AI app builder based in New York. The work is proprietary, so it isn't written up on this site.
- Lead engineer, BabyBrainJun 2026 to present
I built BabyBrain's marketplace platform from its first commit and was its only engineer for the first ten weeks.
- Technical partner, Axis Venture Partners2025 to present
Technical partner on an FP&A automation product built with the firm's partners, for CFOs, finance directors and scale-up founders who still report out of spreadsheets. I'm responsible for the technical architecture and delivery.
- Founder, Morpheus2025 to present
I'm building a system that identifies companies preparing to buy, from public signals such as hiring, leadership changes and transformation announcements, instead of static job-title filters.
Topics
- Web data pipelines and LLM classification
Collecting structured data from the open web at scale, then classifying and extracting from it with LLMs, so that a team can work from a clean table instead of a browser.
- Reliable AI systems
Making model output dependable enough to act on, with deterministic checks around the model, numbers computed in code, and a record of why each decision was made.
- Signal-based lead intelligence
Finding the companies that are about to buy from what they are doing in public, such as hiring, restructuring and leadership changes, rather than from static firmographic filters.