Tool Calling
Tool calling lets an AI agent request a function, API call, or other external action to complete a task.
Category
Agent Guardrails
These terms cover calling tools, isolation, human review, 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.
Tool Calling
Tool calling is the act of invoking a function, API, or service from an AI workflow.
Sandbox
A sandbox is a controlled environment that limits what code or an agent can affect.
Memory
Memory is stored context that can help an agent reuse facts or preferences later.
Evals
Evals are repeatable tests used to measure whether a model or agent behaves as expected.