AI agent

agentic able to act independently toward a goal, taking multiple steps and making decisions with… tool use a model's ability to call external tools, such as a search engine, calculator, code runner, or… agent loop the repeating cycle at the heart of an agent: the model decides on an action, a tool carries… multi-agent system a setup in which several AI agents, often with different roles, work together or check each… human-in-the-loop describing a system in which a person reviews, approves, or corrects an AI's work at key… chatbot a computer program that holds a conversation with people through text or voice vibe working office work done by describing the result you want to an AI agent inside a document… harness engineering the work of building everything around an AI model that lets it act as a reliable agent… background agent an AI agent that works on a task by itself in the cloud while you do something else, then… agentic browser a web browser with a built-in AI agent that can read pages and act for you, such as filling… agentic commerce shopping in which AI agents search, compare, and buy products or services on a person's… GTM engineer a job that uses AI agents, data tools, and automation to build repeatable systems for finding… agent swarm a large group of AI agents working on parts of a task at the same time, coordinated by a lead… personal agent an AI agent that works for one person over the long term: it remembers their preferences… AI kill switch a control outside an AI model that can immediately stop an agent or cut off the computing… rogue AI agent an AI agent that acts outside its intended permissions, policies, environment, or assigned… long-horizon model an AI model designed to work autonomously on a goal through many steps and repeated attempts… agent containment the use of enforced technical boundaries to limit what an AI agent can read, change, execute… automated alignment researcher an AI agent that conducts alignment research by finding relevant work, proposing safety… voice agent an AI agent that listens and responds through spoken language, carries on a conversation, and… AI worm a prompt-injection attack that causes an AI application or agent to reproduce malicious… sandbox escape an event in which code or an AI agent gets beyond the technical restrictions of its isolated… scaffolding the software surrounding an AI model that supplies instructions, tools, memory, context… instrumental convergence the proposed tendency of sufficiently capable, goal-directed agents with very different final… state-based evaluation a method for evaluating an AI agent by comparing the final state and side effects of the… shadow AI the use or deployment of AI tools, models, or agents inside an organization without the… semantic privilege escalation a security failure in which an AI agent stays within its formally granted technical… agent washing the practice of marketing or relabeling a chatbot, assistant, scripted workflow, or… closed-loop discovery a scientific research process in which an AI or automated system uses the results of one… agent identity the identifiers, credentials, provenance, permissions, and delegated authority used to… AI interviewer an AI system that conducts a job interview, asks or adapts questions, observes a candidate's… code mode a tool-use pattern in which an AI model writes a program that discovers, combines, and calls… compound AI system an AI application whose behavior comes from several interacting components, such as models… Web Bot Auth an emerging web authentication protocol and IETF working-group effort that lets automated HTTP… WebMCP a proposed browser API that lets a website expose structured tools directly from its page so… Agent Control Standard an open protocol for placing portable policy checks at points in an AI agent's runtime… AI agent insurance commercial insurance designed to cover specified losses or liabilities caused by autonomous or… agent bill of materials a structured inventory of the components and capabilities that make up an AI agent, such as… lethal trifecta the dangerous combination in an AI-agent system of access to private data, exposure to… vibe hacking the use of a generative or agentic AI system to plan, automate, or scale cyberattacks through… always-on agent an AI agent that remains continuously available in a persistent cloud environment, retains… agentic SOC a security-operations-center model in which AI agents coordinate multi-step threat detection… decision network a graphical model that extends a Bayesian network with decision nodes and utility or value… normative competence the ability of an AI system to recognize, interpret, and respond appropriately to the social… Model Hardware Standard an open specification for connecting AI agents to programmable physical equipment so that they… agentic finance the use of autonomous or semi-autonomous AI agents to analyze financial situations, make… self-evolving AI agent an AI agent that uses experience, feedback, or environmental interaction to revise parts of… agentic advertising an advertising model in which AI agents plan, negotiate, buy, sell, optimize, or measure media… agent sprawl the uncontrolled proliferation of AI agents across an organization faster than the… agent sandbox an isolated, policy-controlled computing environment in which an AI agent can run commands… action space the complete set of actions an AI system is able or permitted to choose in an environment… YOLO mode a setting or operating style in which an AI coding agent or other tool-using agent… context layer the part of an AI system that assembles and governs the current knowledge an agent or model… fiduciary AI an AI system, especially an agent that advises or acts for a person, designed or proposed to… AI research agent an AI agent that pursues a research goal by planning and carrying out an iterative sequence of… orchestrator agent an AI agent that coordinates a multi-agent workflow by breaking a goal into subtasks… agentic workload the pattern of computing work produced when an AI agent pursues a goal through many dependent… agentic threat actor a cyberthreat operator or operation in which an AI agent autonomously plans, selects tools… agentic ransomware a ransomware operation in which an AI agent autonomously carries out multiple attack stages… AI accountability gap the difficulty of identifying, tracing, and enforcing who is responsible when an AI system or… agenticness the degree to which an AI system behaves like an agent by pursuing goals, acting through tools… model autonomy the capability of an AI model or model-based agent to carry out extended sequences of… agentic reinforcement learning the use of reinforcement learning to train an AI agent through multi-step interaction with… GUI agent an AI agent that understands and operates a graphical user interface by actions such as… self-driving company a company in which people set goals, exercise judgment, and remain accountable while AI agents… agent development lifecycle a repeatable process for designing, building, testing, deploying, monitoring, and improving AI… general agent an AI agent designed to complete many different kinds of tasks across unfamiliar tools… self-driving lab a laboratory system that combines AI, automated instruments, and robotics to choose, run… agentic in-context learning a form of in-context learning in which an AI agent actively chooses actions, retrieves or… proof of personhood a verification method or digital credential that allows an online service to establish that a… proactive agent an AI agent that uses context, events, or inferred user needs to decide when to offer help or… credential delegation the controlled granting of limited credentials or access tokens to an AI agent so it can act… memory injection an attack that causes an AI agent or assistant to store attacker-controlled information or…