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 1136 terms
Clear filtersbenchmark
A benchmark is a standardized task or collection of tests used to compare AI systems under defined conditions.
agent skill
An AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work.
agent permission boundary
An agent permission boundary limits the information, tools and actions an AI agent can use during a task.
evaluation
Evaluation measures how well an AI system performs against defined tasks, criteria and failure conditions using repeatable evidence.
agent harness
An AI agent harness is the software framework that packages a model with tools, instructions, context management, execution controls, and user interaction.
code generation
Code generation uses AI or another automated system to create source code from instructions, examples, schemas, or higher-level specifications.
multi-agent system
MASA multi-agent system contains multiple AI agents that interact, coordinate, divide work, or influence one another while pursuing tasks.
agent orchestration
Agent orchestration coordinates AI agents, tools, people, tasks, state, and control flow so a larger workflow reaches a verified outcome.
context engineering
Context engineering designs the information, instructions, memory, and tool state an AI receives so it can perform a task reliably.
model routing
AI model routing sends each request to a model chosen for that request's complexity, cost, speed, privacy, or other requirements.
agent memory
AI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts.
human-in-the-loop AI
HITLHuman-in-the-loop AI keeps a person involved in reviewing, correcting, approving, or guiding an AI system's work.
frontier model
A frontier AI model is among the most capable general-purpose models available at a given time.
feedback loop
An AI feedback loop occurs when AI outputs or their consequences become inputs that influence later model or agent behavior.
safety
AI safety is the field and practice of reducing harmful failures, misuse, loss of control, and unintended consequences from AI systems.
open-weight model
An open-weight model makes its learned numerical settings available so people can run or adapt the AI under the release's license.
AI-assisted scientific discovery
AI-assisted scientific discovery uses AI to support hypothesis generation, experiment design, analysis, simulation, literature work, and interpretation while researchers retain responsibility.
data privacy
Data privacy governs how personal, confidential, or sensitive information is collected, used, shared, retained, and protected in AI systems.
reasoning effort
Reasoning effort is the amount of internal computational work an AI model applies before producing an answer or action.