Write Down Manual Decision Criteria Before Delegating to an AI Agent
A note on why you need to audit what operators actually look at before you start agentifying a workflow.
When I ask what tasks people want to hand over to an AI agent, I often hear something like, “I just check and judge things each time, so it seems automatable.”
But when I dig into what that “just checking and judging” actually involves, it turns out to be surprisingly complex. Amounts, deadlines, counterparties, past exchanges, exceptional contracts, how busy the handler is. People are combining information that does not even appear on-screen inside their heads.
Before thinking about agentification, it seems better to first write out the manual decision criteria.
Items always checked
Past information used for decisions
Conditions for putting on hold
Conditions for escalating to a human
Impact of getting it wrongDoing this separates what can be automated from what should remain with humans. You do not have to hand everything over to AI. Even just making hold conditions and escalation conditions explicit has value.
I feel like designing an AI agent by starting with “let’s make it capable of calling tools” is risky. What you need first is making visible what judgments people were making during the actual work.
