Expertise
Ten years in product, the last stretch spent putting AI into products people use every day. These are the three shapes of problem I keep being handed, and what I actually did about each one.
01 / AI in production
Most AI features die between the demo and the release. The hard part is not the prototype, it is a system that survives latency, hallucination and unpredictable input while still feeling like one product.
↳ 54% of support enquiries resolved without a human · 23 versions of a production prompt, each restorable
02 / Delivery
Turning intent into a rigorous specification should not be the bottleneck. I run spec-driven delivery where AI does work at every step and a human decides at every step.
↳ full PRD produced in 2 sessions · about half the time from design to specification
03 / Discovery at scale
Research that costs a week gets skipped. With thousands of touchpoints, manual synthesis is impossible, so I build pipelines that turn raw conversations into structured decisions.
↳ 1,182 conversations synthesised in one pass · monthly analysis from 1 week to 4 hours
The work is where this gets specific. See the seven cases.