Answers

What does approving an agent action look like?

A message in your chat: what the agent wants to do, why, on what evidence, with approve or decline a tap away. Your decision is logged, and declines teach, the agent learns what you rejected and why.

Approvals arrive where you already are, so the loop is seconds, not a dashboard pilgrimage. The request shows its reasoning and sources, because asking for trust without evidence is not how this house works.
Treat declines as feedback with a sentence attached: 'no, this customer is mid-escalation' becomes memory, and the next request is smarter for it.

Related

Which actions does Heidi run automatically versus ask first?

How do Heidi's agents earn trust and autonomy?

Ask AI about Heidi:
Share this: