ReAct
A prompting pattern for agents that interleaves Reasoning (thought) and Action (tool call), with each observation feeding the next thought. Foundational technique behind most early LLM agents; largely subsumed by more structured agent frameworks in 2025-2026.
Related terms
- Chain-of-Thought (CoT)
A prompting or training pattern where the model produces intermediate reasoning steps before its final answer, typically improving accuracy on multi-step tasks. Modern reasoning models (o1, o3, Claude with extended thinking) internalize CoT during training.
- AI Agent
An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals. Agents can use tools, interact with APIs, and coordinate with other agents.
Related on this site
Framework dimensions
Free tools
Whitepapers
Comparisons
Next steps
- Take the assessment— See where you stand
Call this framework and its tools from your own agent via the Model Context Protocol (MCP) server. Works with Claude Desktop, Cursor, Zed, Continue, and the OpenAI Agents SDK.
Where this fits
ReAct is part of the Agentic AI vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.