Projects
What I'm building: agentic systems, experiments, and what I learn from shipping them.
Projects / 7 entries
I lead commercial AI transformation at a global payments company. I own the strategy and I ship the systems — an operating model, a portfolio of production agents, and the enablement that makes revenue teams actually use them.
An always-on autonomous agent built on Claude Code that acts as a genuine extension of how I think and work. Persistent context, its own memory, scheduled routines, and a governance layer that earns autonomy one task at a time.
A two-pane review tool that renders Markdown pull requests properly and posts inline comments as real GitHub review comments on the right source lines.
A scheduled agent that decides what to research, runs it without me, and lands deduplicated, cited, freshness-tracked files. It now runs three modes daily across two dozen topics. The hard part was never the researching. It was pulling the trigger on a schedule without generating plausible-but-useless filler.
A measurement spike over twenty real UK salons that priced, timed and stress-tested a Google Business Profile audit before anything was built on top of it. The useful output was the list of claims the data could not support.
An agentic pipeline for a local-business website side project. It found leads, audited their web presence and drafted outreach, then ran into an arithmetic wall and an audit engine whose headline grade moved on its own. Both failures are the interesting part.
An adaptive tutor that teaches people to actually master a subject, not just skim it. One engine, a generic personal tutor and named commercial niches, with new subjects authored as data rather than built as code.