Go further · Advanced pathway

Delegating an action to AI.

For users who already understand dialogue, verification and taking back control.

This is not an introductory pathway.

Delegation begins when AI does more than answer and starts using tools or modifying an environment. The user must already know how to:

In training: begin with a simulation, then a simple, reversible and supervised action.

What is not authorised is forbidden by default.

The contract does not give the machine general freedom. It defines a limited mandate, expected evidence and the moments when the human must take back the decision.

Before Define the permission
  1. Mandate: define what is entrusted

    The user writes what the machine may do alone, what is forbidden and what requires approval. The authorised tools, files, data, recipients and budgets are also specified.

    A task or permission absent from the contract is forbidden by default.

    Question
    What are you willing to let the machine do without asking you?
  2. Deliverable: describe the result before seeing it

    Format, length, recipient, required content and quality criteria are written before execution. The machine cannot move the target afterwards.

    Question
    How will you recognise that the work is good before you have seen it?
  3. Stop points: name the decisions the machine cannot make

    The machine stops before deleting, sending, publishing, spending, transmitting data, exceeding a budget or choosing between two important directions. Whenever possible, it first presents a simulation or reversible draft.

    Question
    At what point must it stop and ask you?
During Keep your own reference
  1. Forecast: write what you expect

    During execution, the user records the plan they would have followed and the result they expect. This personal version prevents the machine’s output from becoming the only reference.

    Question
    What would you have done first?
On return Audit and take back control
  1. Trace: audit actions, not only the result

    The user checks a verifiable trace: tools called, files touched, sources used, messages sent, costs, errors and the order of actions. The user does not request the machine’s private chain of thought.

    Question
    Can you describe what the machine actually did, step by step?
  2. Gap: compare mandate, result and forecast

    Any unauthorised action is a contract violation, even if it appears useful. An additional suggestion is acceptable only when clearly separated and not executed.

    Question
    What did it do that you had not authorised?
  3. Takeover: decide what the human resumes

    The user observes, verifies, appropriates and decides. They also choose what to redo personally, what to undo and what the next contract must correct.

    Question
    What will you redo yourself, and what will you change in the next contract?

A written contract is not a technical permission.

Real access must remain minimal. A backup, an undo option and human approval are required for any sensitive or difficult-to-reverse action.

Intention, limits and the final decision.

The machine may help format the contract or perform a preliminary check. It must neither define the mandate for the user nor validate its own execution.

Return to the main method