Skip to content
Last Dictionary
Plane
Agents & HarnessesLanguage Models & TransformersCore Concepts

AI agent

nounAlso: LLM agent, language agent, autonomous agent, AI agents

In plain wordsAn AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done.

  1. 1

    Language-model agents

    A software system that pursues a goal over many steps by letting a large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. decide, turn by turn, which tooltool, n.: Any outside capability an AI model is allowed to use — a web search, a calculator, a code runner, a database or an app — described to the model so it can ask for it by name. to use next — search, code execution, file editing, web browsing, other software — and feeding each tool's output back to it, rather than producing a single response. The model supplies the decisions; a harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car. runs the agent loopagent loop, n.: The repeating cycle at the heart of an AI agent: the model decides what to do next, software carries it out, the result is shown to the model, and the cycle repeats until the task is finished., executes the tool callstool call, n.: A single request from an AI model to use one of its tools — naming the tool and filling in the details — which the surrounding software then carries out and reports back on., manages contextcontext window, n.: How much an AI model can read and keep in view at once: the instructions, the conversation so far and any attached documents. Text that does not fit has to be cut, summarized or left out. and permissions, and stops when the goal is met or a limit is reached. Agents vary in autonomy (how much they do without human approval), horizon (minutes to days of work) and environment (a terminal, a browser, a whole desktop); familiar types include coding agentscoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed., browser agentsbrowser agent, n.: An AI agent that uses a web browser on your behalf — searching, clicking links, filling in forms and reading pages — to complete tasks such as booking, shopping or gathering information., deep researchdeep research, n.: An AI feature that spends minutes rather than seconds on a question — planning, running dozens of web searches, reading many sources — and then writes a long report with citations. agents and computer-usecomputer use, n.: An AI's ability to work a computer through its normal screen and controls: it studies pictures of what is displayed and sends mouse and keyboard actions, so it can use ordinary apps that were built for people. agents. Simon Willison's widely quoted 2025 summary: 'An LLM agent runs tools in a loop to achieve a goal.'

    We replaced the scripted pipeline with an AI agent that decides for itself which records to query.

  2. 2

    Classical AI

    In the classic textbook sense set out by Stuart Russell and Peter Norvig, anything that takes in its surroundings through sensors and affects them through actuators, from a simple reflex agent to a learning, goal-based or utility-maximizing one; see intelligent agentintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals. and the hub entry agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks., which cover this sense and the reinforcement-learning sense.

Origin

'Agent' entered AI through 1980s–1990s research on autonomous and software agents and the agent-centered framing of Stuart Russell and Peter Norvig's textbook (1995). The language-model sense grew from 2022 systems that let models call tools (MRKLMRKL system, n.: An early design, pronounced 'miracle', in which a language model acts as a switchboard, sending each part of a question to the right specialist — a calculator, a database, a search tool — and combining the answers., ReActReAct, prop. n.: A method in which an AI alternates between thinking out loud about what to do next and taking an action, such as a web search, then uses what it observed to plan its next step.), burst into public view with AutoGPTAutoGPT, prop. n.: A 2023 open-source program that gave GPT-4 a goal and let it run on its own — planning, searching the web and writing files in a loop — becoming the first viral 'autonomous AI agent'. and BabyAGIBabyAGI, prop. n.: A tiny 2023 program that kept an AI working through an ever-changing to-do list — doing a task, adding new ones, reprioritizing — and helped start the craze for autonomous AI agents. in spring 2023, and became industry vocabulary in 2024–2025 as laboratories shipped coding, browsing and research agents.

Usage note

Usage is loose: marketing applies 'agent' to chatbots and fixed automations, while researchers stress that agency comes in degrees (see agentic AIagentic AI, n.: AI built to pursue goals on its own — planning, taking actions and adjusting along the way — instead of only responding to one prompt at a time. 'Agentic' describes how much of this independence a system has.). Anthropic's influential distinction separates agents, which choose their own steps, from workflowsagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance. that follow predefined code paths. Willison had earlier crowdsourced 211 definitions on Twitter before settling on his.

Related

See also
  • agentic AIagentic AI, n.: AI built to pursue goals on its own — planning, taking actions and adjusting along the way — instead of only responding to one prompt at a time. 'Agentic' describes how much of this independence a system has.
  • agent loopagent loop, n.: The repeating cycle at the heart of an AI agent: the model decides what to do next, software carries it out, the result is shown to the model, and the cycle repeats until the task is finished.
  • harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car.
  • tool usetool use, n.: An AI model's ability to reach beyond its own knowledge by operating outside tools — searching the web, running code, using a calculator or an app — and folding the results into its work.
  • multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves.
  • levels of autonomylevels of autonomy, n.: Ladders that grade how independently an AI system acts — from a tool a person fully controls, through suggesting and asking for approval, up to acting on its own while people merely watch.
  • coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed.
  • intelligent agentintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals.
Contrast with
  • chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going.
  • agentic workflowagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance.

Sources

  1. Willison, S. (2025). I think 'agent' may finally have a widely enough agreed upon definition to be useful jargon now. Simon Willison's Weblog, 18 September 2025. simonwillison.net/2025/Sep/18/agents
  2. Kapoor, S., Stroebl, B., Siegel, Z. S., Nadgir, N. & Narayanan, A. (2024). AI Agents That Matter. arXiv:2407.01502. arxiv.org/abs/2407.01502
  3. Schluntz, E. & Zhang, B. (2024). Building effective agents. Anthropic, 19 December 2024. anthropic.com/research/building-effective-agents

Mentioned in

agent memoryagent memory, n.: The ways an AI assistant or agent keeps information — your preferences, past conversations, lessons from earlier tasks — and brings it back later, beyond what fits in a single conversation., agentic AIagentic AI, n.: AI built to pursue goals on its own — planning, taking actions and adjusting along the way — instead of only responding to one prompt at a time. 'Agentic' describes how much of this independence a system has., AI securityAI security, n.: Protecting AI systems — their data, models and surrounding software — from being attacked, stolen or tricked, and dealing with the ways AI itself can be used to attack others., AnthropicAnthropic, prop. n.: An American AI company that makes the Claude chatbot and models. It was founded in 2021 by former OpenAI staff and puts particular emphasis on AI safety research., automationautomation, n.: Using machines or software to do work that people would otherwise do, from factory robots to programs that sort email or write reports., chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going., coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed., computer usecomputer use, n.: An AI's ability to work a computer through its normal screen and controls: it studies pictures of what is displayed and sends mouse and keyboard actions, so it can use ordinary apps that were built for people., copilotcopilot, n.: An AI assistant built into software that works alongside a person — suggesting code, drafting text or answering questions — while the person stays in charge, like a co-pilot beside the captain., deep researchdeep research, n.: An AI feature that spends minutes rather than seconds on a question — planning, running dozens of web searches, reading many sources — and then writes a long report with citations., guardrailsguardrails, n.: Safety checks built around an AI system — filters on what goes in and comes out, and limits on what it may do — to keep it from producing harmful or off-topic content or leaking data., inference costinference cost, n.: What it costs to use an AI model after it has been built: the computing power, electricity and hardware needed every time it answers, usually billed per chunk of text., large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., METR time horizonMETR time horizon, n.: A way of measuring AI progress by asking how long a task — timed by how long it takes a skilled human — an AI agent can complete with even odds of success., prompt injectionprompt injection, n.: Tricking an AI system by slipping in text that it mistakes for instructions — for example, a hidden line in an email telling an AI assistant to forward the user's messages to a stranger., robotrobot, n.: A machine that senses its surroundings, decides what to do and physically acts, moving itself or handling objects, with some independence from a human operator. Factory arms, robot vacuums and self-driving cars are all robots., actionaction, n.: A choice an AI agent makes at one moment — move left, place a stone, type a command — which changes its situation and may earn it a reward., agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks., agent frameworkagent framework, n.: A software library that gives developers ready-made parts for building AI agents — model connections, tool handling, memory, multi-agent coordination and logging — so they need not write everything from scratch., agent instruction fileagent instruction file, n.: A plain-text file kept in a software project that tells AI coding agents how the project works — how to build and test it, which conventions to follow, what to avoid — read at the start of every session., agent loopagent loop, n.: The repeating cycle at the heart of an AI agent: the model decides what to do next, software carries it out, the result is shown to the model, and the cycle repeats until the task is finished., agent skillagent skill, n.: A packaged how-to guide for an AI agent — written steps, sometimes with small programs and examples attached — that sits unread until a job of that kind comes up, when the agent opens it., Agent2Agent protocolAgent2Agent protocol, prop. n.: An open standard that lets AI agents built by different companies find each other, say what they can do and work together on tasks, much as email lets different mail systems exchange messages., agentic browseragentic browser, n.: A web browser with an AI assistant built in that can do things for you online — reading pages, clicking, filling in forms, shopping or booking — instead of just showing you websites.