Tool-Call Trace
A tool-call trace records which tools an AI agent used, what inputs were sent, and what outputs came back during a task.
Category
Agent Evaluation Ops
These concepts help teams test whether an AI agent uses tools correctly, completes tasks, and stays within expected boundaries.
How to recognize this theme
AI agent terms for measuring tool use, task outcomes, and safety behavior.
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.
Task Success Rate
Task success rate measures how often a model or agent completes a defined task according to evaluation criteria.
Regression Eval
A regression eval checks whether a model or agent has lost expected behavior after a prompt, model, or system change.
Safety Rubric
A safety rubric is a scoring guide used to judge whether an AI system follows expected safety and policy constraints.