Back to glossary
Concepts

AI Agents

Systems where an LLM plans, calls tools, observes results, and iterates toward a goal.

Definition

An AI agent is a system where a language model is given a goal and the freedom to plan, call tools, observe results, and iterate until the goal is achieved or a budget is exhausted. Agents combine LLM reasoning with tool use and memory. By 2026, agentic frameworks (OpenAI Assistants, Claude Agent SDK, LangGraph) make this pattern accessible without bespoke infrastructure.

Example

An agent given 'Book me a dinner reservation in Brooklyn for Saturday at 7pm' might: search restaurants → check availability via a tool → confirm with user → call a booking API.

When to use

Multi-step tasks with uncertainty, browsing, code execution, customer-facing assistants.

Also known as

llm agents, ai agent

Related terms

Free Chrome Extension

Stop rewriting prompts. Start shipping.

Works with ChatGPT, Claude, Gemini, Grok, Midjourney, Ideogram, Veo3 & Kling. 5.0★ on the Chrome Web Store.

Add to Chrome — Free