Agent Loop

Flashcard: why must every agent loop declare when to stop?

Flashcard: what is the ReAct pattern for agents, in one sentence?

Flashcard: when would you pick Plan-and-Execute over ReAct?

How does function calling enable the observe-plan-act agent loop?

Flashcard: what is an AI agent, in one sentence?

Flashcard: in the agent loop, what counts as an 'action' and how is it different from a thought?

Flashcard: what is an 'agent runtime' and what does it do?

Flashcard: what is the ReAct prompting pattern?

Predict what the model emits next in this ReAct trace, given the observation just returned.

Order the four phases of a single iteration of a ReAct (Reason + Act) loop in the correct sequence.

How should a production MCP host handle a tool call that exceeds the latency budget?

Explain precisely why a chatbot with persistent memory is not an agent

Describe each step of the agent loop and explain which component, LLM or runtime, is responsible for it

Order the five steps of the canonical agent loop from first to last

Explain the LLM vs runtime split in an agent and why the distinction matters for debugging

Which component is 'the agent' in an LLM-based agent system?