Unit of work

Continuous improvement

Make the unit of work bigger, and measure it.

Test: Is what you hand the agent bigger than last month? Show the trend, not a feeling.

Human domain

Hand over goals, not tasks, as big as you can assess.

Test: Could you demo the result to a stakeholder? Leave it building overnight? Review it in one sitting?

Agentic domain

The agent sees and acts wherever a human can.

Test: List what engineers look at and touch, such as CI, logs, staging and production telemetry. Which of those does the agent have access to, with nobody copying and pasting?

Machinery

Continuous improvement

Said it twice? Make it a check.

Test: What did you tell the agent more than once this week? Is it an automated check yet?

Human domain

Define and enforce the qualities you care about, or don’t expect them.

Test: Where is each quality you care about written down? What fails when one breaks?

Agentic domain

The agent isn’t done until the checks pass.

Test: When the agent says it’s done, which checks did it run? How often does a human find something the checks missed?

Consequence

Continuous improvement

Span and batch keep growing, or you’ve stalled.

Test: Are span and batch bigger this quarter than last?

Human domain

Humans spend their time on problems and experiments, not on reviewing output.

Test: What share of last week went on problem analysis and experiment design, and what share on reading what the agent produced?

Agentic domain

No human reads or writes code.

Test: When did someone last open the code? Treat each time as a bug in the machinery, and fix the cause.