Tool Calling
Tool calling lets an AI agent request a function, API call, or other external action to complete a task.
Category
Agent Control Plane
These terms cover calling tools, isolation, human approval, and logging.
How to recognize this theme
Terms that keep an AI agent safe while it reaches for external 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.
Sandbox
A sandbox is a restricted environment that limits what an agent or program can access or change.
Approval
Approval is a checkpoint where a human reviews and authorizes a risky or important action.
Audit Trail
An audit trail is a log that records what happened, when it happened, and who or what triggered it.
Fallback Path
A fallback path is a backup route used when the primary AI flow fails or times out.
Memory Store
A memory store keeps prior context or state that an app can reuse later.
Tool Schema
A tool schema defines the fields and shape expected by a callable tool.
Response Filter
A response filter checks model output before it is shown or sent onward.