What is an AI agent?
An AI agent is a computer program powered by artificial intelligence (AI) that can perform tasks autonomously to assist human users, even without definite instructions. Unlike other AI-powered software, such as chatbots, AI agents can operate outside of a specific prompt-based context. They can go outside of their training data and take a look around at the world, so to speak, to find information. Then they can, on their own, take actions based on that information in pursuit of a larger goal.
AI agents can make decisions, learn from past experiences, and adapt their actions accordingly. They can even consult with other AI agents to obtain relevant information. Humans set goals for AI agents, but it is up to the agents to figure out how to carry out those goals. They can operate independently or with very little human input.
AI agents can either power hardware (as in robotics) or operate only in software.
Agentic AI vs. AI agents
AI agents are the software programs described above: They make decisions and handle tasks on their own. Agentic AI is the field of AI development that enables the construction of AI agents. (Think of the difference between generative AI and individual large language models, such as Microsoft Copilot, or the difference between "cooking" and a specific meal.)
Agentic AI vs. generative AI
Generative AI (GenAI) refers to a type of deep learning model that can generate content in response to prompts. It is the category of AI to which LLMs like ChatGPT belong. Agentic AI is built on top of GenAI. But while an LLM can only respond to prompts through a specific user interface or API, an AI agent can go outside of a defined context and perform actions even without prompts.
A sales executive at a large company might prompt a large language model (LLM) by saying, "Write an email that I can send to 10 of our biggest customers, inviting them to a dinner." But with agentic AI, the executive might instead prompt an AI agent by saying, "Invite 10 of our biggest customers to dinner." In other words, the LLM can generate text, but the AI agent should be able to both generate the email text, find the 10 biggest customers in a CRM, and send personalized email invites to the event (provided it has sufficient permissions to do so).
How do AI agents work?
Large language models (LLMs)
AI agents are built on LLMs. An LLM is a type of AI model that has been trained on large sets of sample data, enabling it to comprehend human-created content and generate content of its own. LLMs understand even imprecise human prompts and requests.
Because they are built on LLMs, AI agents can process and interpret a wide range of data and content, from conversational requests from users to web-hosted video content. AI agents can interpret content from multiple types of media: code, text, audio, video, and so on. They can then use what they learn from that content to refine their actions.
External integrations and interactions
Additionally, AI agents have ways to interact with the world. In robotics, this can include physical sensors and cameras. For software-only AI agents, this can take several forms:
Agents can plug directly into external applications via APIs
Some AI agents can interact with web apps just like a human user, filling out forms, reading webpages, and so on (they may use a headless browser for this purpose)
An emerging standard called the Model Context Protocol (MCP) connects AI agents to a variety of tools (email clients, CRMs, billing systems, etc.) with the proper authentication and authorization allowed for the agent
These ways of interacting with the world outside the context of the AI agent's environment enable the AI agent to take actions. Organizations can establish guardrails for AI agents to help ensure the actions they take are correct, just as human users may have limited permissions within an IT environment. In addition to programming policies into the AI agents, organizations can also employ a human-in-the-loop approach, in which humans verify the accuracy of AI agent responses or approve agent actions.
Learning via data flywheel
AI agents can learn as well, using results of past actions and input from human users to refine their actions in the future. They have "memory" — not just in the computational sense of RAM, but in the sense of remembering past interactions and outcomes. This learning takes place through a feedback loop called a data flywheel: Records of an agent's interactions are used by the underlying model to improve future performance.
What are the types of AI agents?
There are two main types of AI agents:
Background agents: They perform tasks, especially routine tasks, in the background, with little user interaction. Background agents are like the janitors or maintenance workers keeping the office clean and the lights on.
Surface agents: They interact more directly with human users. Chatbot, customer service, and assistant AI agents are in this category. Surface agents are like front-desk workers in an office building, interacting with the people who come in and fulfilling certain tasks as needed.
There are also single-agent and multi-agent systems. Single-agent AI systems are built on just one model. Multi-agent AI systems combine the capabilities of multiple agents that consult with each other to solve problems.
What is an agentic AI chatbot?
Agentic AI chatbots are, like traditional chatbots, able to interact conversationally with people. Agentic AI chatbots can, however, go outside of their chatbot context — leave the chat — to take actions on behalf of the person they are interacting with. A traditional chatbot might be able to provide instructions on filing a support ticket. An agentic AI chatbot would be able to file the ticket itself.
Agentic AI chatbots vs. non-agentic AI chatbots
Non-agentic AI chatbots are reactive, responding to user prompts in accordance with their training data. They may still be powered by an LLM, but they are better at providing users with helpful content or directions than at performing actions on behalf of users. Agentic AI chatbots are able to take action outside of the context of their interaction with a user. Agentic AI chatbots can also learn from a range of sources beyond their training data.
How does Cloudflare support agentic AI?
The Cloudflare developer platform provides all the tools needed to build and deploy AI-powered agents that can:
Autonomously perform tasks
Communicate with clients in real time
Call AI models
Browse the web
Query a database
Support human-in-the-loop interactions
In addition, Cloudflare's global network allows developers to build AI agents with code running anywhere in the world, as close to end users as possible. Learn how to start building AI agents on Cloudflare.
FAQs
What is an AI agent?
An AI agent is a computer program powered by artificial intelligence that can autonomously perform complex tasks for human users, even without explicit instructions. Unlike other AI software, such as chatbots, AI agents can operate beyond a specific prompt-based context and independently find information and take actions to achieve a broader objective.
How do AI agents function?
AI agents are built upon large language models (LLMs) and are capable of processing and interpreting diverse data types, including conversational requests and web-hosted content. They can interact with external applications through application programming interfaces (APIs), simulate human user interactions with web apps (e.g., filling out forms, reading webpages), and connect to various tools via emerging standards like the Model Context Protocol (MCP). These capabilities enable them to take actions beyond their immediate environment. Furthermore, AI agents learn and refine their future actions through a "data flywheel" feedback loop, which uses records of past interactions and human input.
What is the difference between agentic AI and AI agents?
AI agents are the actual software programs that make autonomous decisions and handle tasks. Agentic AI refers to the field of AI development that focuses on creating these AI agents.
How does agentic AI compare to generative AI?
Generative AI (GenAI), which includes LLMs like ChatGPT, is designed to produce content in response to prompts. Agentic AI is built on top of GenAI, but it goes a step further by allowing AI agents to perform actions outside of a defined context, even without direct prompts. For example, while an LLM might generate an email draft, an AI agent could also find customer information and send personalized emails.
What are the different categories of AI agents?
There are two primary types of AI agents: background agents and surface agents. Background agents handle routine tasks with minimal user interaction, similar to maintenance workers. Surface agents, like front-desk staff, interact more directly with human users, assisting them with various tasks. Additionally, systems can be single-agent (using one model) or multi-agent (combining multiple agents that collaborate to solve problems).
What is an agentic AI chatbot?
An agentic AI chatbot is a conversational AI that can not only interact with users but also take actions outside of the chat context on their behalf. Unlike traditional chatbots that might provide instructions, an agentic AI chatbot could directly perform the action, such as filing a support ticket.
How do agentic AI chatbots differ from non-agentic AI chatbots?
Non-agentic AI chatbots are reactive and primarily provide information or directions based on their training data, even if powered by an LLM. Agentic AI chatbots, however, can initiate and complete actions beyond the user's immediate interaction and can learn from a broader range of real-world data, not just their initial training.
How does Cloudflare support the development of agentic AI?
The Cloudflare developer platform offers tools for building and deploying AI-powered agents that can perform tasks autonomously, communicate in real time, interact with AI models, browse the web, query databases, and support human oversight. Cloudflare's global network also enables the deployment of AI agents with code running close to end users worldwide.