In depth
Tool use is what turns an LLM into an agent. The runtime presents a list of tools to the model with their schemas, the model emits a structured call (tool name plus arguments), the runtime executes it, the result is added to context. Reliable tool use is the most important capability of a modern model for agent work. Different providers format tool calls slightly differently, the runtime normalises across families.
Related concepts
Function callingOpenAI's term for tool use. Same concept, slightly different format.AI agentAn autonomous program that uses an LLM to plan and execute multi-step tasks via tools, in a loop, until a goal is reached.System promptThe instruction text the LLM sees before any user message. Sets the agent's role, constraints, and behaviour.
Newsletter
Get the next post in your inbox.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.