📄️ AI Application Spectrum
Summary: LLM applications sit on a spectrum from a single augmented call to fully autonomous agents, and the tier determines how much control the developer keeps over what happens.
🗃️ LLM Workflows
3 items
📄️ Agents
Summary: An agent is an LLM that dynamically directs its own process and tool usage in a loop, rather than following a fixed sequence of developer-defined steps.
📄️ Structured Output With Tool Use
Summary: Asking an LLM to "return JSON" in the prompt is just a formatting hint the model can ignore; tool use forces the model through a real schema, and a validation library still checks the values afterward.
🗃️ Coding Agent Harnesses
2 items
🗃️ Agent Development Environments
2 items
📄️ LLM Sampling Temperature
Summary: Temperature controls how randomly an LLM picks each next token from its