AI agent
Also known as: agent, agents
An AI agent is an AI system that plans and takes multiple steps — often using tools or external systems — to accomplish a goal, rather than answering a single prompt.
In more detail
Where a chatbot responds to one message at a time, an agent works toward a goal: it can break a task into steps, call tools (search, code execution, APIs), read the results, and decide what to do next. Coding assistants that edit files and run tests, or research assistants that browse and compile findings, are examples. Agents are more capable and also riskier, because they act — so human review and clear boundaries matter more.
Example
"Research our top three competitors and put the findings in a table" given to an agent might trigger several web searches, reading pages, and assembling a comparison — multiple steps from one instruction.
Why it matters
Knowing the difference between a prompt, a workflow, and an agent helps you pick the right tool and understand why agents need more oversight.
Try a prompt for yourself
Open any prompt and run it in the IterPrompt playground.