Permission Boundary
A permission boundary defines the actions, tools, data, and spending limits an AI agent is allowed to use.
Category
Agent Risk Controls
These controls define what an agent may do, how actions are logged, when approval is needed, and when humans take over.
How to recognize this theme
Terms for keeping AI agents reviewable and within approved boundaries.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Agent Audit Log
An agent audit log records prompts, tool calls, decisions, and approvals so an AI workflow can be reviewed later.
Approval Policy
An approval policy defines which agent actions require a human, system, or compliance check before execution.
Human Handoff
A human handoff transfers an AI agent workflow to a person when judgment, exception handling, or authorization is needed.