# AI Agent

> An AI agent is an LLM-driven system that pursues a goal in a loop — calling tools, observing results, iterating — instead of returning one answer.

**An AI agent is a system that uses a language model to pursue a goal autonomously: it decides on an action, executes it through a tool, observes the result, and repeats — a loop, not a single answer.**

The loop is the whole distinction. A plain LLM call maps input to output and stops; an agent closes the feedback cycle — run the test, read the failure, edit the code, run it again. That makes agents capable of multi-step work (and of recovering from their own mistakes), and it makes their quality depend on more than the model: [tool design](/guides/concepts/production-tool-calling), [memory](/glossary/agent-memory), and termination conditions matter as much as raw intelligence.

In practice "agent" spans a spectrum of autonomy — from a function-calling loop with three tools, through coding agents like [Claude Code](/guides/getting-started/what-is-claude-code), to multi-agent systems with planners and workers. Frameworks like LangGraph and CrewAI ([compared here](/guides/concepts/agent-frameworks-2026)) supply the orchestration scaffolding; the [Model Context Protocol](/glossary/model-context-protocol) standardizes how agents reach tools.

---

_Source: https://agentscamp.com/glossary/ai-agent — Term on AgentsCamp._