Essays on building products - and on what AI really changes for the work, from practice rather than hype. Written by a practitioner, for practitioners.
Months of designing and building real products with AI coding agents kept surfacing the same problems - not random bugs, but predictable ones. They’re not defects to fix; they’re characteristics of the tool. On sycophancy, confident hallucination, solution-racing, moved effort and eroded judgment - and the test I use to tell a constraint worth adding from ceremony.
Over the last couple of months I finally had the time - and the mental space - to slow down and look at where I am as a designer after more than 11 years in product and UX roles. A reflection on burnout, fundamentals, AI, and why sometimes the most progressive thing you can do is go back to basics.
I recently encountered a post advocating skipping traditional user research in favour of direct sales calls. While this approach seems efficient for startups pressed for time, it compels us to reconsider what user research actually is - and what happens when you skip it.
Read something worth discussing? Have a question or just want to connect? I read everything and reply within a day.