What is an AI agent?
An AI agent is an AI system that takes actions to accomplish a goal - using tools, browsing the web, and completing multi-step tasks autonomously, not just generating text.
Where a chatbot responds to a prompt, an agent decides what steps to take and executes them. Given a goal, it plans, calls tools such as web browsers, code, and APIs, checks the results, and iterates until the task is done.
Modern AI agents combine a large language model for reasoning with a set of tools and a memory of past steps. This loop - reason, act, observe, repeat - is what lets them book a table, research a topic across many sites, or run a workflow end to end.
how this works in folk
Folk is a personal AI agent you reach by text. Each user gets a cloud computer the agent uses to browse, run code, and act - so it doesn't just talk about doing things, it does them.
frequently asked
What's the difference between an AI agent and a chatbot?
A chatbot generates responses; an agent takes actions. An agent can use tools, browse the web, and complete multi-step tasks autonomously to reach a goal.
Are AI agents safe to give access to my accounts?
It depends on the design. Well-built agents run in isolated environments, use scoped permissions, and ask for approval on sensitive actions. Folk runs each user in a private sandbox and never trains on your data.