risk

After the hackathon I spent a couple of weeks working with Claude on the merchant-risk model. What we built across the sessions, what I learned about variable engineering, and the parts that work well now versus the parts that are still a work in progress.

A vague ask ("give me a list of prospects that look like X") turned into a working pipeline in under sixty minutes: Companies House metadata, the filed accounts as scanned PDFs, Claude reading them for the signals I needed, and a final ranking with commentary. Small build, but the speed is the point.

An internal hackathon in February 2026, the merchant-risk problem the team had been chewing on for a year, and the day I stopped thinking of AI as a useful tool for tasks and started thinking of it as something you build a system around.