AI adoption · evaluation · strategy
I build AI systems, then prove they work.
15 of them so far — extraction pipelines, adoption decision tooling, production reporting, generated content with real validation. Twelve years of quality leadership behind it, which is why the interesting part is usually the evidence, not the demo.
- 12+ years
- in quality and delivery leadership, from sole in-house QA to QA Manager
- 70+ testers
- in the largest organisation I governed, across concurrent workstreams
- 4 platforms
- owned end to end — mobile, web, TV and console, including payments and certification
- 15 AI systems
- designed, built and run since 2025, in production and in my own practice
Selected work
What I have actually built
Vision-to-catalogue extraction pipeline
Photograph a physical item, get back the verified catalogue record.
One case left deliberately failing: the record does not exist in the source catalogue
- n8n
- Vision LLM
- Cloudflare D1
Enterprise AI adoption decision platform
Decision-support software for choosing which AI use cases an organisation should fund and ship.
Around ten design decisions documented with the alternative rejected
- React
- TypeScript
- Zustand
Offline certification framework with LLM-generated content
Desktop exam software, plus several hundred bilingual assessment items generated and validated by language models.
Zero lines hand-edited
- Electron
- Node.js
- Python
Daily LLM reporting pipeline, in production
Test metrics, stakeholder summaries and risk reports generated every morning from live delivery data.
Built inside a confidential client engagement — client and product are not named
- LLM API
- Delivery tooling integrations
A personal AI operating system
The infrastructure I run my own work on: memory, tickets, sync, budget rules, generated views.
Enforced cost discipline: exploratory fan-out requires stated scale and approval
- Node.js (zero-dependency)
- Git
- Claude Code skills
Image classification for a small retail business
A phone-first tool that sorts incoming second-hand stock into categories from photographs.
At their volume the subscription won — cheaper, simpler, and it degrades gracefully when the shop is busy
- Next.js
- Vercel
- Vision model
The reasoning behind it
Five questions, in this order
Most wasted AI spend happens because an organisation starts at question three. Stage four is the one that is usually missing entirely — and it is where I come from.
- 1 Find the bottleneck Business diagnosis
- 2 Choose the instrument Judgement
- 3 Redesign the process Process thinking
- 4 Prove it works Engineering rigour — the part most frameworks skip
- 5 Make it stick Enterprise scaling
Contact
Where I am useful
Deciding which AI use cases are worth funding. Setting the acceptance bar before a pilot starts. Getting something out of pilot purgatory — or killing it honestly.