A model capability for invoking external functions: web search, database queries, code execution, API calls. Required ingredient for any non-trivial agent.
Definition: A model capability for invoking external functions: web search, database queries, code execution, API calls. Required ingredient for any non-trivial agent.
The capability that lets a model invoke external functions: search the web, query a database, run code, call an API. Without tool use, a model is locked inside its training data and the prompt. With tool use, it becomes the orchestrator of a small system. Required ingredient for any non-trivial agent.
The structured way one piece of software talks to another. API access to a foundational model gives you control over prompts, parameters, version pinning, and data flow that no chat interface offers.
A system that uses a language model to drive multi-step work in a loop: reason, call a tool, observe the result, decide the next step. Distinct from single prompt-and-response interactions.
The scaffolding around a model that runs the agent loop: orchestration, tool dispatch, error handling, memory between steps, stop conditions. Most agent failures are harness failures.
Open standard for connecting AI models to external tools and data sources through a shared interface. Supported by multiple AI vendors, replacing one-off integrations with a portable contract.