Structured Outputs enforce a specific response shape, often with schemas, so AI output can be parsed and consumed reliably by software.

Reasoning Effort is a controllable depth setting for model thinking, balancing answer quality, latency, and cost.

A Context Window is the maximum amount of tokens a model can process at once, including instructions, conversation history, and retrieved data.

Tool Calling is the capability for a model to decide when to call connected tools, then use tool results to complete a task.

Retrieval-Augmented Generation (RAG) enriches model outputs by fetching external knowledge at runtime and conditioning generation on it.

Grounding is the practice of constraining generation with verifiable sources so outputs are accurate, attributable, and context-specific.

Hallucination refers to model outputs that sound plausible but are unsupported or false, often due to missing or weak source context.

Guardrails are technical and procedural constraints, such as filters and validators, that enforce safe and reliable AI behavior.

Related AI terms: Model Card and Content Credentials.

Evaluations (Evals) are benchmarked test suites used to track model behavior, regressions, and improvements against defined criteria.

Model Routing is the strategy of directing requests to the most suitable model dynamically using policy and workload rules.

Related AI terms: Partner Models and Model Card.

Text-to-Image Generation creates visuals directly from prompt instructions. Most modern systems rely on a Diffusion Model and can be steered using a Reference Image.

Partner Models are external foundation models exposed through a single product interface. Product teams often combine them with Model Routing and governance artifacts like a Model Card.

A Model Card summarizes model behavior, scope, limitations, and known risks for operators and users. It supports safety controls such as Guardrails and helps teams reason about Hallucination risk.

Classifier-Free Guidance (CFG) is a sampling technique that adjusts prompt adherence versus diversity in generated outputs. It is a common control in Diffusion Model pipelines and complements Prompt Enhancement.

ControlNet augments diffusion generation with explicit structural conditions such as edges, depth, or pose. It improves control in Diffusion Model systems and often uses cues from Image Segmentation.

An MCP host is the application that runs one or more MCP clients, manages connections, and makes responses from connected MCP servers available to the user or model.