Resources subsection
Glossary
Simple definitions for common terminology across AI models, agents, workflows, and protocols within the Resources section.
AI Model
A trained computational system capable of generating outputs based on input data.
Agent
Software capable of performing tasks autonomously by interacting with tools or systems.
Agentic System
A system where AI performs multi-step workflows toward a defined objective.
Model Context Protocol (MCP)
A protocol allowing AI models to interact with tools, data sources, and services.
Human in the Loop
A workflow in which a person reviews, approves, corrects, or escalates an AI system's work.
Retrieval-Augmented Generation (RAG)
A pattern that supplies a model with retrieved information before it generates a response.
AI Governance
The roles, rules, controls, and review processes used to direct and oversee AI systems.
Model Evaluation
A structured test of whether an AI model or system meets defined quality, safety, cost, and operating requirements.
Prompt Injection
An attempt to make an AI system follow untrusted instructions that conflict with its intended rules.
Workflow Automation
The use of software to execute or coordinate repeatable steps in a business process.