Knowledge shorts twice: Once in the tools. Once in the humans.
I build tools for complex knowledge and test whether they work. From user research through working code — end to end.
The problem is always the same: complex information that people can't use well enough. Sometimes that's a researcher drowning in literature. Sometimes it's a checkout flow losing customers. Sometimes it's an organization sitting on data nobody can find.
Full e-commerce rebuild for Rome's esoteric bookshop.
A computable UX knowledge system — HCI research encoded as a graph with every citation verified against its source, exposed to Claude Code through an MCP server so evidence lands in a developer's context window exactly when they need it.
Barcode to catalog in under 10 seconds. A metadata aggregation platform for independent bookshops — scan, enrich from five sources, publish to WooCommerce.
Multi-agent research engine that takes an impossible hypothesis, stress-tests it against real academic literature, and produces papers that read like hard science.
A researcher navigating a corpus of 10,000 papers and a shopper filtering a product catalog are dealing with the same problem — moving through complex information under uncertainty to find what they need. The interfaces differ. The cognitive architecture doesn't.
I started on the hard version: scientific publishing tools, critical apparatuses, information-seeking and research behavior in academic contexts. Marie Curie fellowship, PhD in HCI, three first-author papers on why knowledge tools fail their users. Then eight years at Baymard Institute applying the same evaluation discipline to e-commerce — 700+ usability heuristics, Fortune 500 scale. The finding was always the same: tools assuming a user who doesn't exist.
The underlying cognitive primitives — recognition over recall, progressive disclosure, feedback loops, spatial memory — are the same whether the interface is a checkout flow, a command line, or a graph database explorer. The skill is seeing that. The advantage is also building it: no handoff, no translation loss, no gap between what the research found and what the code does.
Research infrastructure, e-commerce builds, or something in between — let's talk.
Get in touch