Agt Pattern Glossary

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

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

Flashcard: how is self-correction different from self-refine in agents?

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?

Flashcard: why connect agents through MCP?

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

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