Writing
Notes on human-in-the-loop AI
Approval design, policy gates, and what it takes to let an agent move real money.
-
· 2 min read
Why we're writing this
A blog about the unglamorous half of AI engineering: what happens when an agent proposes an action that a person has to stand behind.
-
· 4 min read
What belongs in an approval context payload
A reviewer who clicks approve without understanding the decision is a liability, not a control. Five things every approval request should carry — and three it should never.
-
· 4 min read
Why
waitForEventis not human-in-the-loopEvery workflow engine can pause. Pausing is the easy half. The hard half is everything between the pause and the resume — and that is the half you end up building yourself.