repository context
Repository context is the relevant source, configuration, history, documentation, dependencies, and worktree state needed to understand a software task.
AI Terminology
Search clear AI terminology definitions, acronyms, related concepts and the reviewed videos that explain them.
Showing 41–60 of 1136 terms
Clear filtersinference
AI inference is the process of running a trained model on new input to produce a prediction, classification, generated response or action.
multimodal model
A multimodal model can process or generate more than one kind of data, such as text, images and audio.
stateful agent
A stateful agent preserves task information across multiple events and model calls so its AI behavior can continue coherently over time.
token pricing
Token pricing is the rate an AI provider charges for processing input tokens, generating output tokens, or reading cached tokens.
compute infrastructure
AI compute infrastructure is the hardware, facilities, networks, power, cooling, storage, and software used to train and run AI models.
prompt engineering
Prompt engineering is the practice of designing and refining instructions, context, examples, and constraints to obtain useful AI outputs.
reward hacking
Reward hacking happens when an AI system exploits a scoring rule or proxy to earn a high reward without achieving the intended outcome.
alignment
Alignment is the effort to make an AI system pursue intended goals and follow relevant human values, instructions, and constraints.
deterministic software verification
Deterministic software verification checks an output with a repeatable procedure that produces the same result for the same inputs and state.
agent-to-agent communication
Agent-to-agent communication lets AI agents exchange messages, task state or other information with one another.
fine-tuning
Fine-tuning continues training a model on selected data so its behavior becomes better suited to a task, domain or operating environment.
guardrail
A guardrail is a technical or procedural control that limits unsafe, disallowed, deceptive, or otherwise unwanted AI behavior.
inference speed
AI inference speed measures how quickly a trained model begins and continues producing outputs for a request.
model quantization
Model quantization represents AI model values with fewer bits to reduce storage, memory use and often inference cost.
long-running AI agent
A long-running AI agent maintains task state and continues observing, deciding, and acting across an extended period.
video generation model
A video generation model creates or transforms moving images from text, images, video, audio, or structured controls.
AI-assisted software development
AI-assisted software development uses AI systems to help plan, write, test, review or maintain software while people retain responsibility for the result.
AI-generated content
AI-generated content is text, imagery, audio, video, code, or other material produced substantially by a generative AI system.
automatic speech recognition
ASRAutomatic speech recognition converts spoken language into text or structured linguistic output using signal processing and machine learning.