Guardrails
Guardrails are the policies, filters, and validation checks applied around a large language model — on its inputs, outputs, or both — to keep its behavior within safe, intended, and application-appropriate boundaries.
6 resources across 1 library
Glossary Terms(6)
Structured Outputs
Structured outputs is a large language model feature that constrains a model's response to strictly conform to a predefined schema, such as JSON with specific…
Guardrails
Guardrails are the policies, filters, and validation checks applied around a large language model — on its inputs, outputs, or both — to keep its behavior with…
Constitutional AI
Constitutional AI (CAI) is a training method developed by Anthropic in which a model is guided by a written set of principles ('a constitution') and trained to…
Model Card
A model card is a structured, standardized document accompanying a machine learning model that discloses its intended use, training data, performance metrics,…
Dataset Bias
Dataset bias refers to systematic imbalances, gaps, or skewed representations within a training dataset that cause a machine learning model to learn and reprod…
Multi-Agent System
A multi-agent system, in the context of modern AI, is an architecture in which multiple distinct AI agents — often each built on an LLM with its own role, inst…