multimodal artificial intelligence model
A multimodal AI model can process or generate more than one data type, such as text, images, audio or video.
AI Terminology
Search clear AI terminology definitions, acronyms, related concepts and the reviewed videos that explain them.
Showing 21–40 of 705 terms
Clear filtersartificial intelligence-generated content
AI-generated contentAI-generated mediaAI-generated content is text, imagery, audio, video, code, or other material produced substantially by a generative AI system.
computer use
AI computer use lets an AI agent operate graphical applications through screen perception and input controls.
enterprise artificial intelligence
Enterprise AI is AI deployed within an organization under business, security, integration and governance requirements.
human judgment in artificial intelligence
Human judgment in AI is the accountable interpretation and decision-making people contribute when setting goals, evaluating evidence, and managing consequences.
Model Context Protocol
MCPThe Model Context Protocol is an open protocol for connecting AI applications to tools, data sources, and reusable capabilities through a common interface.
repository context
Repository context is the relevant source, configuration, history, documentation, dependencies, and worktree state needed to understand a software task.
research agent
AI research agentAn AI research agent searches, gathers, organizes, analyzes, and reports information through a multi-step tool-using workflow.
stateful artificial intelligence agent
A stateful AI agent preserves relevant information across interactions or workflow runs instead of treating every request as unrelated.
token efficiency
AI token efficiency measures how effectively a model or workflow turns consumed input and output tokens into useful results.
agent harness
An AI agent harness is the software framework that packages a model with tools, instructions, context management, execution controls, and user interaction.
agent memory
AI agent memoryAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts.
context window
An AI context window is the maximum amount of tokenized input and generated output a model can consider in one interaction.
institutional knowledge
Institutional knowledge is the accumulated decisions, practices, context and experience that an organization relies on to work effectively.
mixture-of-experts model
MoEMoE modelA mixture-of-experts model contains multiple specialized subnetworks and activates a selected subset for each input instead of using every parameter every time.
model selection
AI model selection is the process of choosing the model best suited to a task, constraints and desired outcome.
self-hosted artificial intelligence
local AIlocal AI deploymentSelf-hosted AI runs on hardware controlled by the user or organization instead of relying entirely on a third-party hosted model service.
workflow automation
AI workflow automationAI workflow automation uses models or agents to perform and coordinate steps in a repeatable process.
agent delegation
AI agent delegationAI agent delegation assigns a bounded task, context, authority, and expected result from one participant to an agent or another agent.
agent-to-agent communication
AI agent-to-agent communicationAI agent-to-agent communication is the structured exchange of messages, results, requests, or state between autonomous AI agents.
Knowledge graph
Explore AI concepts
Follow general terms into specialised sub-terms. Select any node to open its definition.