Frank Ray

Software built with AI assistance reaches a dispute the same way any other software does: defects emerge, a system proves unmaintainable, or a security failure surfaces.

When I wrote about preparing a legal case with AI without a lawyer, I described the discipline but not the machinery.

This article is about how I used AI agents to prepare a legal case without a lawyer, and how you can too, without getting burned.

If a harness doesn’t deliver reliable, high-quality, largely autonomous output from an AI agent, we may as well go back to hand-coding and save on tokens and data-centre cooling.

Last week I gave Claude an issue from one of my side projects and walked away.

A follow-up to How to Build an AI Emotional Regulation Coach for Autism.

Don’t laugh, but I’m currently obsessed with those tacky car renovation programs on Netflix.

Damien asked for help resolving some delivery issues with their fledgling SAAS product.

I’ve seen nearly every flavour of dysfunction after 20 years of working with software teams.

The distinct roles we’ve organised software development around—Product Owner, Business Analyst, Developer, QA, DevOps—are collapsing into each other.

Update: I’ve since written a follow-up covering the clinical safety considerations and design lessons from a year of testing: Lessons from Building a Safe AI Mental Health Coach.

Last Tuesday I was standing in line at the pharmacy waiting for a prescription, phone in hand, tagging Claude into a pull request on GitHub.

Most organisations approach business analysis backwards.

A nine-month embedded Solutions Architect engagement, building an AI-powered incident analysis platform for over 2,000+ ServiceNow incidents, helping a global business services firm move from reactive firefighting to systematic quality improvement, cutting

Client calls.

Client calls.

Organisations need business analysis capability.

Something feels off with your development team.

It’s 6:47 AM, and I’m already at my desk with a cup of coffee, staring at three monitors displaying evidence logs, source code repositories, and deployment histories from a failed integration project.

Three months ago, I was writing about hand-carving wooden surfboards, planting an orchard, and recreational coding for fun.