Twenty-six against forty
I let the fleet run an estate-wide migration overnight with one instruction: don't merge. In the morning a single count told me something was missing, before I'd opened a diff.

I let the fleet run an estate-wide migration overnight with one instruction: don't merge. In the morning a single count told me something was missing, before I'd opened a diff.

keryx has no users but me, and it still got seven bug reports in two days, all filed by one of my own agent sessions. Checking one meant reading exactly what the reporter had typed, which you don't normally get to do.

Two weeks tuning a retrieval system, every day productive and the numbers still not good enough... so I finally went and read what other people had already built.

A plugin marketplace has no registry, so whatever's on main is what people install. I tried twice to get CI to keep the version honest before settling for a check that makes me type a command.

I sent a research agent off to back up something I'd been saying out loud for weeks. It handed me the evidence against it instead, and it wasn't the first time that model had done it to me.

The tool had comments on under ten per cent of its lines and ninety pages of documentation built into the binary, and I'd argue that was one decision made for two very different readers.

Forty-two comments telling a checker to stand down. I went through them one at a time to see what each was actually asserting, and some of them were wrong.

Blameless was meant to make it safe to tell the truth. Somewhere along the way it started to mean nobody did anything, and I'd quite like the first one back.

Reviewers in a group agree more than they should, and I don't think it's anybody's fault. So I've started building review panels out of things that have never been in a room.

A commit landed a month before I noticed it. By the time somebody told me, two of my own tools had already written workarounds for it without mentioning it.
