Permission Envelope
A permission envelope defines the tools, data, limits, and actions an AI agent is allowed to use for a task.
Category
AI Agent Governance
These concepts describe how AI agents can be constrained and audited before acting.
How to recognize this theme
Terms for limiting, reviewing, and recording agent actions.
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.
Approval Gate
An approval gate pauses an agent workflow until a person or policy check approves a sensitive step.
Action Log
An action log records tool calls, decisions, and outputs so an agent workflow can be reviewed later.
Policy Evaluator
A policy evaluator checks a planned response or action against defined rules before the system proceeds.