7 docs tagged with "llm"

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.

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.

Summary: Temperature controls how randomly an LLM picks each next token from its

Summary: Once the pipeline shape is fixed, the remaining work is operational — structured output at every boundary, versioned prompts, retries, per-step tracing, and evals that gate prompt changes the way tests gate code.

Summary: A workflow is a fixed, developer-defined sequence of steps where an LLM fills in each step. Each pattern below is paired with how it's actually implemented in production.

Summary: Building a workflow LLM app is two separate decisions — what shape the

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.