Search

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

Flashcard: why break a complex goal into subtasks before acting?

Flashcard: what is an agent 'trajectory' and why does it matter for evaluation?

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

Flashcard: what is a tool in an LLM agent?

Flashcard: is a 0.85 cosine similarity score from your retriever 'high confidence'?

Flashcard: what is a token in LLM prompting and why does it matter for cost and context?

Flashcard: what is an AI agent?

Flashcard: name the three augmentation sub-decisions in a production RAG pipeline.

Flashcard: what does 'grounding' mean in the context of RAG, and why is it the whole point?

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

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

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

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

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

Flashcard: what is similarity search in RAG, and how does it differ from keyword search?

Flashcard: why use Tree of Thoughts search on hard agent planning problems?

Flashcard: what is an embedding in a RAG pipeline, and what role does it play?

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

Flashcard: what is chain-of-thought (CoT) prompting?

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

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

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

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

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

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

Flashcard: what is the ReAct pattern for agents?

Flashcard: what is the ReAct prompting pattern?

Flashcard: what role does the LLM's context window play in a RAG pipeline?

Flashcard: what is a vector database, and why does RAG need one?