Portfolio
The work, with the numbers behind it.
Each case study states the problem, what was built, and what was measured afterwards — including what has not moved yet. Every figure comes from the code, the build, or the live site on the date shown.
12 skills are demonstrated below. See the full skill map, including the 7 in progress.
3,850
commits since 29 April 2026
A content operation run by AI agent loops
One person, a set of Claude agents working in supervised loops, and a review gate on every change.
114
checks run on every build
Evals for AI-generated output, and testing the tests
114 checks hold the bar on generated pages. Then an audit asked which of them would pass if there were nothing to check.
1,103 → 45
median title length, characters
Why a 995-page site drew zero search traffic
Four mechanical causes, each measured, three fixed in code, and one documented as a dead end.
4
capture surfaces walked end to end in a browser
A health endpoint that told the truth about the funnel
Every form rendered and every page converted, and nothing was being kept. Nobody could see that until the system reported on itself.
5
evidence-graded research briefs
Context engineering: a doctrine every writing agent loads
Five competing schools of copywriting, graded on their evidence and resolved into one set of rules an agent can follow.
319
nodes
An offering graph to choose one thing to sell
A 319-node graph built from the live product registries, used to pick a single wedge and then to kill two channels that could not carry it.
Hiring for this kind of work?
Tell me the role and the company. Four fields, no call booked until we have both decided it is worth one.