This website uses cookies
Read our Privacy policy and Terms of use for more information.
Nov 9, 2026
•
8 min read
Generated code looks finished before it is safe, so I look in the same five places every time, and a person decides what ships.
Nov 2, 2026
9 min read
An agent can retrieve every record correctly and still get the meaning wrong, which makes it a data problem before it is an AI problem.
Artificial Intelligence
+2
Oct 26, 2026
10 min read
Trust in an agentic workflow lives in the handoffs: who receives the work, what they confirm, and what counts as done.
+1
Oct 19, 2026
An agent that hands work back to a person owes them the reason, the evidence and what it could not check.
Oct 12, 2026
An agent can cite its source perfectly and still be wrong about what the word meant.
Oct 5, 2026
Last week was about fences. This week is about whether you can say why an agent went where it went.
Sep 28, 2026
7 min read
One lab's agent went through a locked door this month. Another kept a person at every bench and found something nobody had found before.
Sep 21, 2026
The week I found out my pinned plugin was never pinned, and that I had quietly stopped looking.
Sep 14, 2026
The week I told a room to write down where an agent may go, twelve hundred of OpenAI's went somewhere nobody wrote down.
Sep 7, 2026
Aug 31, 2026
Aug 24, 2026
6 min read
Aug 17, 2026
Issue No. 10: The Decision Table
Aug 10, 2026
Issue No. 9: The Withdrawal
Aug 3, 2026
Issue No. 8: Will it survive you?
Jul 6, 2026
Issue No. 7: Most ideas should not get built
Mar 30, 2026
11 min read
Issue No. 6: You Built Something. Now What?
Mar 2, 2026
Issue No. 6: The Dilemma of Choice
Feb 2, 2026
Issue No. 5: Learning Without Breaking
Jan 5, 2026
Issue No. 4: AI Reflections & Future Vision
Dec 1, 2025
Issue No. 3: Automation with Intention
Prompt Engineering
Oct 29, 2025
Issue No. 2: Hands Off, Mind On
Oct 15, 2025
Issue No. 1: Between Automation and Vision
