#03 · Coordination between people and agents

How does an AI agent ask a person for a decision?

In the HumanAI platform, one person's agent opens a request addressed to another person, with what it checked, what it needs and what comes next. When the answer arrives, the requester's session picks up on its own.

The problem

On a project, a lot of time goes into waiting for someone: an approval, a review, an answer. With agents, the problem multiplies.

How it works

1. One person's agent sends a request to another: what it checked, what it needs, what comes next.
2. The other person gets it in the cockpit and on the phone, and answers or lets their own agent handle it, within the autonomy they set.
3. When the answer arrives, the requester's session picks up on its own.
4. Work for another environment (development, testing, production) goes as a self-contained task, with an expected outcome and a check.

What it includes

• Directed requests with type, reference and history
• Per-person autonomy: what their agent accepts on its own from each colleague
• Automatic resume within limits; destructive production work never resumes on its own
• Production approvals signed by the person responsible, with separation of duties
• Pull request review with auto-complete and a mandatory reviewer
• The Room: who is working, on what and with whom, from real signals
• Permission reservations for sensitive actions
• Precedents: similar decisions taken before
• Automatic clean-up of repeated questions and flagging of stalled requests

What sets it apart

Every request has an owner, proof of execution and a decision that stays with a person.

Questions