Category

Agent Tool Orchestration

These ideas describe how agent systems choose tools, structure actions, and add safeguards around execution.

How to recognize this theme

AI agent terms for routing tools, checking actions, and keeping execution constrained.

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.

Tool Router

A tool router is logic that chooses which external tool or function an AI agent should call for a given task.

Action Schema

An action schema defines the fields and constraints an agent must follow when preparing a tool call or external action.

Human Approval Step

A human approval step requires a person to review or approve an agent action before it is carried out.

Execution Sandbox

An execution sandbox limits what code, tools, files, or network destinations an agent can access while running a task.