I ship what normally takes a team.
AI-Powered Tech, Growth & Business Operator
Most people split growth and building. I do both.
I'm an AI implementation operator. I use modern web engineering and AI tools to ship the systems that move a business, not just advise on them.
I'm not an ML engineer who trains models. I'm the operator who turns AI into production output, fast, and knows why every decision was made. I run AI systems the way a director runs a set: the value isn't typing every line, it's knowing what to build, directing the tool to build it right, catching what's wrong, and shipping it. See the method →
The work, at a glance.
Every build here is real, with an honest role and a live link where the work is public. Open any one for the full case: problem, what I did, the result, and what I caught the AI getting wrong.
Rebranded live, zero downtime
Full brand change and a deeper marketing site for Paralegent.ai, shipped continuously on live main without ever taking it down.
A content engine that runs itself
cognilium.ai, live: 76 routes and a 22-post clustered blog on a CMS where you publish once and the page is structured, optimized, and indexed automatically.
A self-maintaining SEO/GEO stack
Found 19 of 46 pages silently un-indexed, recovered them, and left behind a self-maintaining SEO/GEO system plus a citation moat for AI answer engines.
A newsroom built for Google News
Stood up cognilium.ai/tech-news as a real newsroom that qualifies for Google News and Discover: NewsArticle schema, news-spec sitemaps, RSS/Atom/JSON feeds, and Publisher Center registration.
One publish, six platforms
One publish in the CMS now auto-syndicates a post across six channels off a single webhook, idempotent per slug so the same article never double-posts.
Brand rules the AI can't break
Six agent-skills auto-enforce the locked palette, voice, page rhythm, FAQ rules, and conversion psychology on every change, across Cursor, Codex, Gemini, and other AI coding agents.
Scraped a rival's full catalog, with receipts
Reverse-engineered a competitor's API to lift its entire 651-product catalog into a clean, audited dataset, every record carrying a SHA256 receipt of where it came from. The full dataset is downloadable below.
A directory where money can't buy rank
Designed the 16-table database and built the directory that serves it: 575 products scored by a transparent model where sponsorship never touches ranking, on a ~2,000-page Next.js site.
My own MCP platform, live on npm
A SaaS plus stdio MCP server that keeps my private AI-context library out of every client repo, pulled in over MCP and removed clean when the engagement ends.
AI marketing video, fully paid
Cinematic AI marketing video with voice-cloned narration and AI visuals, scripted and edited end to end for a paying UK client.
The reason I move fast is a method, not a trick.
This is the part most people hide. I lead with it, because it's the thing that's hard to copy.
Scope & judgment
I decide what to build and what 'good' looks like, the call AI can't make. Brand direction, which approach wins, what to cut. The taste is mine.
Orchestration
I drive AI across a real server and codebase: context management, breaking work into what the tool can actually execute. Most people get toys out of these tools. I get production.
Guardrails as code
I author agent skills and rule files that enforce brand, vocabulary, page rhythm, and quality on every change, so the output stays correct at speed and across tools.
Verify & ship
I review, test, catch the mistakes, and ship on live main. The output is only as good as the operator's ability to judge it. That judgment is what I bring.
Don't take my word for it.
Hiring, or building something serious? Let's talk.
I'm open to roles and serious collaborations where one operator with AI does the work of a team. The honest way to judge me is the work itself, every case study shows the call I made and what I caught the AI getting wrong.