AI Agent

An AI system that autonomously plans, uses tools, and takes multi-step actions to accomplish a goal.

Example: a coding agent like Claude Code reads your repo, plans changes, edits files, runs tests, and fixes failures in a loop — instead of just answering a single question. Agents rely on function calling and often the Model Context Protocol (MCP).

Related resources

Claude Code is Anthropic's agentic coding tool that works in your terminal and editor, understanding your entire codebase to plan, write, and refactor code autonomously. It handles multi-file changes, runs tests, and integrates with Git workflows — designed for developers who want an AI collaborator, not just autocomplete.

LangGraph is a low-level orchestration framework from the LangChain team for building stateful, multi-step agent workflows. It provides fine-grained control over execution flow with persistent state, human-in-the-loop checkpoints, and cycle support — ideal for complex agents that need more than simple chain sequencing.

CrewAI is an open-source framework for orchestrating role-playing, autonomous AI agents that collaborate to complete complex tasks. You define agents with specific roles, goals, and tools, then combine them into crews that work together — ideal for building multi-agent systems for research, analysis, and automation.