51 terms
Agents & Tools
AI that takes action: agents, tool use, protocols, and the systems that coordinate them.
- A2AnounAgent2Agent: an open protocol that lets AI agents built by different companies discover each other, communicate, and hand off…
- agent fleetnountrendinga group of AI agents deployed and managed as one operational system, often to carry out separate or parallel tasks under shared…
- agent gatewaynountrendingan infrastructure layer placed between AI agents and the models, tools, APIs, data, or other agents they use, providing a central…
- agent handoffnountrendingthe transfer of responsibility for an active task, conversation, or workflow stage from one AI agent to another, usually together…
- agent loopnounthe repeating cycle at the heart of an agent: the model decides on an action, a tool carries it out, the result or evaluation is…
- agent org chartnountrendinga visual or machine-readable representation of the roles, reporting lines, delegation paths, approval relationships, and…
- agent skillnouna packaged set of instructions, scripts, and resources that an AI agent can load when needed to perform a specific kind of task…
- agent swarmnouna large group of AI agents working on parts of a task at the same time, coordinated by a lead agent or by simple shared rules…
- agenticadjectivetrendingable to act independently toward a goal, taking multiple steps and making decisions with limited human direction
- agentic advertisingnountrendingan advertising model in which AI agents plan, negotiate, buy, sell, optimize, or measure media on behalf of advertisers and…
- agentic browsernouna web browser with a built-in AI agent that can read pages and act for you, such as filling forms, comparing products, or booking…
- agentic commercenountrendingshopping in which AI agents search, compare, and buy products or services on a person's behalf, often paying through new…
- agentic financenountrendingthe use of autonomous or semi-autonomous AI agents to analyze financial situations, make delegated decisions, and initiate or…
- agentic operating systemnountrendinga software or infrastructure layer that manages the execution, memory, tools, permissions, coordination, and lifecycle of AI…
- agentic paymentsnountrendingpayments that an AI agent initiates or completes on behalf of a person, organization, or another agent under delegated rules…
- agentic workflownouna process in which one or more AI agents carry out a series of steps, such as research, drafting, checking, and revising, with…
- agenticnessnounthe degree to which an AI system behaves like an agent by pursuing goals, acting through tools or an environment, adapting its…
- AI agentnountrendingan AI system that can pursue a goal over many steps on its own, deciding what to do next, using tools such as search, code, or…
- AI research agentnountrendingan AI agent that pursues a research goal by planning and carrying out an iterative sequence of activities such as reviewing…
- always-on agentnountrendingan AI agent that remains continuously available in a persistent cloud environment, retains project context, and can monitor…
- artificial symbiotic intelligencenountrendinga proposed form of advanced intelligence that emerges from continuing cooperation among AI agents, human participants, tools, and…
- background agentnounan AI agent that works on a task by itself in the cloud while you do something else, then reports back with the result, such as a…
- code modenountrendinga tool-use pattern in which an AI model writes a program that discovers, combines, and calls available tools inside a controlled…
- computer usenountrendingthe ability of an AI agent to operate a computer or web browser like a person, by looking at the screen, moving the cursor…
- copilotnounan AI assistant built into a piece of software that suggests, drafts, or completes work alongside the user, who stays in control
- deep researchnounan AI feature or agent that spends several minutes searching many sources, reading them, and writing a long cited report on a…
- function callingnounan API feature in which a model, instead of replying in plain text, outputs a structured request to run a specific function with…
- general agentnountrendingan AI agent designed to complete many different kinds of tasks across unfamiliar tools, applications, or domains without being…
- GUI agentnounan AI agent that understands and operates a graphical user interface by actions such as clicking, typing, scrolling, dragging…
- harness engineeringnountrendingthe work of building everything around an AI model that lets it act as a reliable agent, including its tools, verification…
- human-in-the-loopadjectivedescribing a system in which a person reviews, approves, or corrects an AI's work at key points instead of letting it act fully…
- human-on-the-loopadjectivetrendingdescribing an AI oversight arrangement in which a system operates autonomously while a person monitors its behavior and can…
- MCPnountrendingModel Context Protocol: an open standard for connecting AI applications to outside tools and data sources, so one connector can…
- multi-agent systemnouna setup in which several AI agents, often with different roles, work together or check each other to complete a larger task
- multi-agent taxnountrendingthe extra tokens, computation, time, complexity, or loss of performance caused by coordinating multiple AI agents instead of…
- orchestrationnounthe software layer that coordinates models, tools, agents, and data so a multi-step AI task runs in the right order
- orchestrator agentnountrendingan AI agent that coordinates a multi-agent workflow by breaking a goal into subtasks, assigning them to specialized agents or…
- personal agentnountrendingan AI agent that works for one person over the long term: it remembers their preferences, connects to their accounts such as…
- Personal Agent Consent & Trust Protocolnountrendingan open protocol for interactions between a customer's personal AI agent and a business, allowing the business to verify the…
- Personal Agent Protocolnountrendinga proposed open standard for identifying a personal AI agent to a business, authenticating the user it represents, and allowing…
- proactive agentnountrendingan AI agent that uses context, events, or inferred user needs to decide when to offer help or initiate authorized work without…
- procedural memorynounan AI agent's stored knowledge of how to perform tasks, such as reusable instructions, rules, action sequences, or executable…
- prospective memorynounan AI agent's ability to retain an intention to do something later and bring it back into use when the relevant time, event, or…
- scaffoldingnounthe software surrounding an AI model that supplies instructions, tools, memory, context management, execution loops, permissions…
- self-evolving AI agentnountrendingan AI agent that uses experience, feedback, or environmental interaction to revise parts of its own behavior after deployment…
- subagentnounan agent that a main agent creates or calls to handle one part of a task, usually with its own fresh context, and that reports…
- tool usenountrendinga model's ability to call external tools, such as a search engine, calculator, code runner, or app, and use the results in its…
- tool-schema biasnountrendingsystematic variation in an AI agent's performance caused by how functionally equivalent tools are named, grouped, structured, or…
- voice agentnountrendingan AI agent that listens and responds through spoken language, carries on a conversation, and may reason, use tools, or take…
- WebMCPnountrendinga proposed browser API that lets a website expose structured tools directly from its page so browser-based AI agents can discover…
- x402nountrendingan open payment protocol that uses the HTTP 402 Payment Required status code to let software clients, especially AI agents…
Advertisement