# OTIS Guard: Runtime Mandate Check

A working OTIS Labs demonstration showing how consequential AI-agent actions can be checked against a live human mandate. Presented as part of MIT Project NANDA, 2026.

An AI agent receives bounded authority to spend. Each proposed action is checked against a live human mandate at the moment of action and returns approve, confirm, escalate or block.

Video: https://www.youtube.com/embed/P7KnlR8xMfQ

## What the demonstration shows

- Bounded authority: the agent can act independently within limits defined by a human principal.
- Action-time checking: authority is checked when intent becomes action, not only when access is initially granted.
- Human confirmation thresholds: some actions may be permitted only after explicit confirmation.
- Cumulative limits: authority may depend on prior actions and changing totals, not only the current request.
- Revocability: the source of authority remains capable of changing or withdrawing the mandate.

## The elements

- Principal: the human or organization from which authority originates.
- Agent: the delegated actor proposing an action.
- Mandate: the live boundaries governing permitted action.
- Check: evaluation of the proposed action against the mandate.
- Outcome: approve, confirm, escalate or block.
- Evidence: a record of the decision and its stated basis.