Agents
Agent (Agentic AI)
An agent is an LLM given a loop, memory, and tools it can call.
It plans multi-step work and takes actions, rather than returning a single answer.
"Agentic" describes a spectrum, from one tool call to a fully autonomous loop, not an on/off feature.
The engineering that matters most is the guardrails, observability, and evals around the loop.
An agent that can act is also an agent that can act wrongly.
← Back to the full glossaryRelated terms
Tool Calling Tool calling lets a model request a structured action instead of only generating text. Guardrails Guardrails are the checks that keep an LLM or agent inside acceptable bounds in production. Observability Observability captures traces of every prompt, retrieval, tool call, and response for debugging. Eval Suite (Evals) An eval suite is a versioned set of test cases that measures whether outputs are good.
More in Agents
Model Context Protocol (MCP) MCP is an open standard for connecting LLM applications to tools and data sources. Context Engineering Context engineering decides what occupies a model's context window at every step, and in what order. Tool Contract A tool contract is the schema a tool exposes to a model. Idempotency An idempotent operation produces the same result no matter how many times it runs.