The internet is littered with examples of Agents getting things wrong. I've had some of those same experiences, mostly variants of ignoring instructions. Occasionally I get a fun one like this. …
Read MoreIt's been a fast few. Lots of things have filled the past months, from trips to toiling in the yard. Here we are at the end of another summer. Thankfully I've learned a few things, relearned really - …
Read MoreSix months ago I would have told you there's a lot of value in crafting a custom harness to drive a reliable development flow. Claude Code was good, but it lacked guardrail loops. If you wanted …
Read MoreWith the right language, everything is a toy. […] Two conversations I've had in the past week dovetailed perfectly. One focused on the perils of one-shot development, the other on the challenge …
Read MoreIf I Knew, What Good Can I Do?
Jul 14, 2026 · 5 min read · observability logging o11y software engineering discernment marketing pixel agentic ai ·Oh what I would do, if only I knew... […] Logging has been a continuously evolving practice for me. When I started writing code, I leaned heavily into debug/log/assert hack based strategies. I …
Read MoreWhere's My Cheese?
Jul 1, 2026 · 2 min read · product strategy feature fatigue digital product less is more agentic ai ·I recently came across this rethinking of the Amazon way and this interview where we hear that Spotify is pushing ~4500 production releases a day. Both are worth a dive, but they dance around the …
Read MoreWith one of my side web projects I noticed that it had been months since I'd taken a hard look at the level of accessibility. I'd run a pass using axe-core, and addressed the issues, and then set it …
Read More