Enforcing a Writing Standard Across 927 JIRA Tickets
The hooks went in clean. The 927 tickets didn't.
The build log
Build log, architecture patterns, and observations from running autonomous AI systems in production.
The hooks went in clean. The 927 tickets didn't.
The alert said 60 percent. My usage dashboard for 2026-09-10 was showing spend at nearly double the trailing week's daily average, and the first instinct was to start hunting for a runaway agent, a...
A customer's site had gone unrenewed-reminded for nearly seven years, despite renewing several times since. The cause traced back to one commented-out check from 2019.
The alert said "You've hit your weekly limit, resets 4am." Twice, at 3:40 in the morning, six minutes apart.
Manus's review of the memory-truncation draft came back in about a minute: SHIP, three notes attached, and note one told me to soften a sentence that supposedly still read as dramatic.
The alert sat in a shared alerts channel for over an hour: my partner asked a question, and nothing answered back. Not an error, not a retry, just silence where a response should have been.
A newsletter landed in our ops channel touting Anthropic's AI-native SDLC playbook as something teams need to adopt.
Six commits deep into the tournament bracket display fixes: court-name alignment, the X'd-out slot spacing, the 8am-plus-orange date change, a sticky left nav driven by a scroll handler, the locati...
A vendor newsletter pitched an AI-native SDLC playbook, and checking it against our own workflow found one real gap: our plans died at the end of every session.
A teammate's queue had 22 tickets on it. Five were small and ready to pull. The other 17 had been sitting in Inbox long enough that nobody remembered why they were still there.
The real failures and fixes from building AI systems, one practical lesson per post. Get the next one in your inbox.