Uploaded September 2026 | Updated November 2026, 1 day ago
Amy and Sean from LangChain explain how memory works for AI agents, meaning how they hold onto information beyond a single run. Short-term memory is the context window, basically everything in scope right now, like remembering what you had for breakfast this morning. Long-term memory is what persists across runs: user preferences, past decisions, and facts the agent needs to carry forward, like remembering a birthday every year.
This is a clip from our full conversation where Amy and Sean answer the most commonly searched questions about AI agents, from the basics like what is an agent, what is RAG, and what is MCP, to harder questions like why agents hallucinate, how to evaluate them, and what LangChain actually does.
Amy and Sean from LangChain explain how memory works for AI agents, meaning how they hold onto information beyond a single run. Short-term memory is the context window, basically everything in scope right now, like remembering what you had for breakfast this morning. Long-term memory is what persists across runs: user preferences, past decisions, and facts the agent needs to carry forward, like remembering a birthday every year.
This is a clip from our full conversation where Amy and Sean answer the most commonly searched questions about AI agents, from the basics like what is an agent, what is RAG, and what is MCP, to harder questions like why agents hallucinate, how to evaluate them, and what LangChain actually does.










