coding agent
An AI coding agent is a tool-using AI system that can inspect, modify, and validate software within a repository.
AI Terminology
Search clear AI terminology definitions, acronyms, related concepts and the reviewed videos that explain them.
Showing 1–20 of 705 terms
Clear filtershuman-in-the-loop artificial intelligence
HITLHuman-in-the-loop AI keeps accountable people involved in guiding, reviewing or approving selected AI actions.
multi-agent system
MASA multi-agent system contains several autonomous or semi-autonomous agents that interact within a shared environment to pursue individual or collective objectives.
agent skill
An AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work.
open-weight artificial intelligence model
An open-weight AI model makes trained model parameters available for users to download and run under a specified license.
agent
AI agentAn AI agent is a system that observes context, decides what to do, and takes actions through tools to pursue a goal.
agent observability
AI agent observability makes an agent's state, actions, tool use, failures, resource use, and outcomes visible enough to understand and operate it.
agent permission boundary
An AI agent permission boundary defines the data, tools and actions an agent is allowed to access or execute.
frontier artificial intelligence model
frontier AI modelA frontier AI model is among the most capable general-purpose models available at a given time.
agent evaluation
AI agent evalAI agent evaluation measures whether an agent completes tasks correctly, safely, efficiently, and consistently under defined conditions.
agent orchestration
AI agent orchestration coordinates agents, models, tools and workflow stages so they can complete a shared task.
benchmark
An AI benchmark is a standardized set of tasks, data, procedures, and metrics used to compare model performance.
context engineering
AI context engineeringContext engineering designs how an AI system receives the instructions, data, tools, and history it needs for a task.
human-artificial intelligence collaboration
Human-AI collaboration combines human judgment and accountability with AI speed, generation, analysis, and tool use in a shared workflow.
artificial intelligence-assisted code review
AI-assisted code review uses a model to inspect source changes for defects, security risks, design issues, and maintainability problems while leaving final judgment to a reviewer.
evaluation
AI evaluation measures how well an AI system behaves for its intended users, tasks, risks and operating conditions.
execution trace
An AI execution trace is a structured record of the steps, tool calls, state changes, and outputs produced during an AI workflow.
model routing
AI model routing sends each request to a model chosen for that request's complexity, cost, speed, privacy, or other requirements.
artificial intelligence-assisted scientific discovery
AI for scientific discoveryAI-assisted scienceAI-assisted scientific discovery uses AI to help generate, test or prioritize scientific hypotheses and candidates.
feedback loop
An AI feedback loop occurs when AI outputs or their consequences become inputs that influence later model or agent behavior.
Knowledge graph
Explore AI concepts
Follow general terms into specialised sub-terms. Select any node to open its definition.