Newsletter
The AI PM Playbook
Chapters from an AI product management playbook, checked against the agent system I run at home.
Issue 01
What the Model Sees
Two chapters into an AI product management playbook, checked against the agent system running in my house: context engineering and system design.
Read the issueIssue 02
Own the Definition of Good
What an eval actually is, why agents need harder ones, and the loop that turns every failure into a permanent test.
Read the issueIssue 03
The 300 Second Write
What a wedged GPU taught me about picking models, measuring launches, and keeping an AI product alive once real work depends on it.
Read the issueIssue 04
Three Scouts in 47 Milliseconds
When to fan a task out across cheap parallel agents, when to keep it on one thread, and what a 181,083 character failure loop taught me about the seams in between.
Read the issue