Dependency Managers, LLMs, and Agentic IDEs

Learning Objectives:

1. Differentiate between a large language model (LLM) and runtime / inference engine.
2. Understand that today's large language models guess likely next tokens given an input context in an inference loop until a stop token, or other condition, is encountered.
3. Explain how a chat-like system is layered on top of a large language model.
4. Understand how a context window impacts the quality of output tokens emitted.
5. Explain what tool calling means to today's AI agents.
6. Explain, at a high level, what context engineering means in a developer agent workflow.