Summary & Key Terms - Introduction to AI Agents

What We Learned

An agent chooses its next action; a workflow follows developer-defined control flow.
Build the model-tool-observation loop with validated arguments and correctly linked results; tools, memory and planning are covered in Agent Building Blocks.
Use human review where it improves task outcomes.
Bound steps, time and cost; evaluate outcomes, trajectories and repeated-run reliability.

Term	Short meaning
Agent / workflow	Model-directed action selection / predefined execution path.
Tool / function calling	A model requests a structured operation; application code executes it.
Observation / trajectory	Result returned from an action / sequence of steps in a run.
Tool-call ID	Connects a tool result to the model request that produced it.
HITL	Human In The Loop: a person reviews, corrects or approves selected steps.
Guardrail / stop condition	Checks around behavior / rule that terminates execution.
pass@k / pass^k	At least one success in k attempts / success across all k repeated trials.
Outcome / trajectory evaluation	Checks final task success / checks the actions used to reach it.