A draft becomes a send.
The agent was asked to prepare a message. Access to the send button is treated as permission to use it.
How we know enough to act.
An agent can prepare a change. What establishes that it may carry it out?
Books, knowledge, and practical instruments for making scope, evidence, limits, and authority explicit before a system sends, spends, deploys, or changes the world.
Try to send a message with permission only to draft. Change the authority, inspect the review, and watch what reaches the simulated outbox.
Run the draft-to-send experimentThe agent was asked to prepare a message. Access to the send button is treated as permission to use it.
A missing acknowledgment leaves the outcome uncertain. Repeating an action can repeat its consequences.
The same system proposes the action and declares it ready. The checks that matter need an accountable source.
These are illustrative failure patterns. The work is to design controls at the actual action boundary and test whether they hold.

Work through an agent example, then map the boundary in a workflow of your own.
Use the instrumentsIllustrative engraving · Not a historical specimen

Study the boundary, evidence, and authority in aviation, medicine, trade, and software.
Examine the casesIllustrative engraving · Not a historical specimen
The same questions connect a plumb line, a court, a compiler, and an autonomous system.
Reality. What exists independently of the system’s account?
ANATOMY, NOT A LINEAR LAWWhat must be established before commitment?
Publication details pendingII / REPRESENTATIONWhat can the model actually tell us about the world?
Planned volumeIII / AUTHORITYWho gets to make a determination binding?
Planned volume