Flashcard

Flashcard: how does Reflexion let an agent learn from failed runs?

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

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

What does observability mean for production LLM agents, and how is it different from app monitoring?

Flashcard: why connect agents through MCP?

How is long-term memory typically implemented in an agent?

When should a production agent pause for human approval?

Why cap each agent run with a cost-per-task budget?

What causes context pollution in a long-running agent?

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: how is agentic RAG different from single-shot RAG?

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

Flashcard: what is a tool in an LLM agent?

Flashcard: what does it mean when an LLM 'makes a tool call'?

Flashcard: what does zero-shot prompting mean and what makes it work at all?

Flashcard: what is Tree of Thoughts (ToT) prompting and what problem does it solve?

Flashcard: what does the temperature parameter do during LLM generation and how should you set it?

Flashcard: what is a stop sequence in an LLM API call and what is it used for?

Flashcard: what is the self-refine prompting pattern and what loop does it set up?

Flashcard: what is self-consistency prompting and what does it produce as a final answer?

Flashcard: what is the ReAct prompting pattern?

Flashcard: what is a prompt template and how does it differ from a prompt?

Flashcard: what is JSON mode (response_format) in LLM APIs and what does it guarantee?

Flashcard: what is few shot prompting and what does the 'few' actually refer to?