Planning is two separate moves, not one. The AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → decomposes a large task into manageable subgoals up front, and separately reflects on finished actions, criticizing its own mistakes and refining the next steps.
Agent memory maps onto the model itself. Short-term memory is just in-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → learning, whatever you fit in the prompt. Long-term memory is an external vector store the agent writes to and retrieves from, so it can hold effectively unlimited history.
tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition → exists because the weights are frozen after pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition → and hard to change. Calling external APIs is how an agent reaches anything the weights lack: current information, code execution, and proprietary data sources.
Terms in this piece · Glossary
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
Why it matters
A clear, canonical breakdown of the core components of LLM agents — planning with subgoal decomposition and reflection, short/long-term memory via vector stores, and tool use — giving builders a mental model for designing autonomous agent systems rather than copying a single framework.
Key quotes
“The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.”
“In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:”
