20 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 loopnounthe repeating cycle at the heart of an agent: the model decides on an action, a tool carries it out, the result is fed back, 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…
- agenticadjectivetrendingable to act independently toward a goal, taking multiple steps and making decisions with limited human direction
- 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 workflownouna process in which one or more AI agents carry out a series of steps, such as research, drafting, checking, and revising, with…
- 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…
- 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…
- 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…
- 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…
- 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
- orchestrationnounthe software layer that coordinates models, tools, agents, and data so a multi-step AI task runs in the right order
- 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…
Advertisement