0.95, fifty times
"confidence": 0.95on all 50 of themA classifier I was building gave all 50 of its answers the same confidence, 0.95. The answers were fine. The number meant nothing: it was filling in a box.
What I check now: a score the model writes is just more text. Mine now has to write out its reasons first, 100 characters at least, before it's allowed a score. That stops it filling in the box blind. It doesn't make the number right by itself.
A blank deadline, read as fine
"deadline_hint": ""it closed in Aug 2025I emailed 15 businesses about a cleaning tender my pipeline called live. It had closed eleven months earlier. The prompt said to skip anything past its deadline, but the deadline was blank, so the model had nothing to check.
What I check now: rules that matter live in code, not in the prompt. A plain filter now drops any tender with a past or unknown deadline, whatever the model says.
12 of 12, and down for three weeks
tests (12/12)none of them opened the new filesTender Radar is my script that reads UK government tender notices every morning and sorts out which ones are worth a bid. An AI helped me add three trades to it, each with a little file describing a sample firm. Its commit said the tests passed, 12 of 12. The new files were missing two details the script insists on, so the morning run crashed on them every day for three weeks. None of the 12 tests had opened them.
What I check now: a passing test only vouches for what it opens. So I watch the run, not the tests: the last 40 sit on my home page as bars, red when one fails.
POD matching, allegedly
chiropodyfeet, not freightAn AI agent reading job adverts for me wrote up a firm as one that matches proof of delivery paperwork, POD for short. The only POD in the advert it quoted was inside the word chiropody.
What I check now: no sentence, no claim. A lead only counts if the exact sentence behind it is saved next to it, and POD has to be a whole word.
Things AI got confidently wrong
Pinned here so I don't forget them. Each one came back sounding sure of itself, and each one changed what I check.