Topic
Engineering practice
The standard a team holds itself to when an AI tool is doing much of the writing: a coding standard the tool actually reads rather than one assumed to be common sense, and what a company keeps — the reasoning, not just the code — when the person who built something leaves. Continuity as an engineering discipline, not a handover email written in a hurry.
-
Sep 11, 2026 Note For companies
AI writes instant legacy code
Code written with AI is being thrown away or rewritten within weeks at twice the old rate, and the share of code being refactored is falling. The draft is faster. Owning it is not.
-
Sep 11, 2026 Note For companies
Fast food architecture
AI is a very good drafter and a poor architect. Treating its output as finished engineering is like living on fast food: it works today and costs you later. The fix is a place the reasoning lives that the model can read back.
-
Sep 11, 2026 Note For companies
The tool nobody in IT knows about
Shadow IT used to be a spreadsheet. Now it is a working app that runs part of the business, built by one person with an AI tool, and that person is the only one who can change it.
-
Sep 5, 2026 Note For companies
The coding standard is a file the tool reads
Three people building with AI produce three different codebases unless the standard lives somewhere the tool reads it every time. Not a wiki page. A file in the repo.
-
Sep 5, 2026 Note For companies
What a company keeps when the coder leaves
Git keeps the code. It does not keep the reasoning, the gotcha that cost a day, or why the last approach was abandoned. That is a different kind of backup, and most companies do not have it.
-
Sep 5, 2026 Playbook For both
Standards and continuity for a small AI-coding team
The repo files that make AI-written code consistent, how a shared vault survives more than one author, the automated handoff that catches unfinished work, and the drill that proves any of it actually works.