An AI agent, also called an LLM agent or autonomous agent, is a system that can pursue a goal by deciding what to do next, taking actions, and using the results to keep going.
Most AI systems just answer a prompt once. An agent is useful when one answer is not enough and the system needs to act over multiple steps: search, call tools, inspect results, retry, and stop when the goal is met.
You’d reach for an agent when the task is:
In practice, many teams start with plain prompting or retrieval before moving to agents, because agents are more complex and easier to get wrong.
At a high level, an agent combines three things:
A goal or task
A decision loop
Tools or actions
A common pattern is: think → act → observe → repeat.
In LLM-based agents, the language model often serves as the controller that chooses the next step. The exact architecture varies across products and papers, and “autonomous agent” is not a single formal standard term.
User: “Find the latest docs for our payment API and draft a support reply about refund timing.”
Agent loop:
A simple pseudo-flow:
goal: answer refund timing question
observe: user request
action: search_docs("refund timing")
observe: policy says refunds post in 3-5 business days
action: draft_reply(...)
result: support response ready