Skip to content

Topic

Human-in-the-loop AI agents

AI agent systems that pause for human review or approval before carrying out proposed actions.

Current clusters

build1 publisher

Lambda durable function replay turned a human-approved refund into an escalation

One developer's Lambda durable function executed 'escalate' after a human approved 'refund', because replay ran the uncheckpointed agent call a second time. Whatever a human signs off on has to be checkpointed with context.step so every replay returns the same value.

Publishers:dev.to

Reality

Evidence55
Adoption
Insufficient
Hype gap+10
Incentives
Insufficient
Confidence60