Home
NowUpdated July 2026

Following the boundary between autonomy and accountability.

A living page about the questions, systems, and practices receiving my attention right now.

FocusJuly 2026

Autonomous workflows are getting easier to assemble. The more interesting product problem is deciding what they should be allowed to do, how we know they are doing it well, and where human judgment creates more value than another model call.

01Question

Agentic product patterns

Where autonomy creates leverage, where it creates hidden risk, and how an interface should expose the difference.

02Building

Evaluation as infrastructure

Turning product judgment into living test sets, production signals, and feedback loops that a whole team can use.

03Testing

Human–agent handoffs

Designing context, confidence, and accountability across the point where an automated workflow returns control to a person.

04Practice

Technical range for PMs

Staying close enough to code, models, and architecture to make better product decisions without confusing depth with ownership theatre.

Operating loop

Frame the decision. Build the smallest real system. Watch where reality disagrees.

  1. 01 Frame
  2. 02 Build
  3. 03 Observe
  4. 04 Revise

If one of these questions overlaps with yours, that is probably worth a conversation.

Send a note