AI Policy

I use AI openly in the making of this site. This page sets out how it is used, and where a human stays in charge.

What is made with AI

The code behind this site and the writing on the blog are produced with Claude and Claude Code, an agentic coding tool I direct through a series of role-based prompts. AI does the bulk of the work - drafting posts, building pages, and shaping the code - while I set the direction and make the decisions.

Human oversight

Every post and every change is reviewed, edited, and approved by me before it goes live. That reflects how I see AI in delivery: it does the bulk of the work, while a human stays accountable for the design, the security, and the outcome. Nothing reaches the live site without passing through that review.

Watermarking

Anthropic has announced that it will begin watermarking content generated by Claude. The AI involvement here has always been stated plainly, so a watermark just confirms what this page already tells you - nothing to catch out, because nothing is hidden.

Read more

For the fuller story of how the site is built and shipped, I wrote it up in Building and Hosting This Website. For anything else, reach out via LinkedIn.