Reference
AI Glossary
Plain-language definitions of the terms you need to know when building with AI. No jargon walls. Each term links to a full explanation with examples and related guides.
AI Agents
Autonomous AI systems that can plan, use tools, and take multi-step actions to accomplish goals without constant human direction.
Read full definition →AI Fluency
The ability to communicate effectively with AI systems, understand their capabilities and limitations, and integrate them into everyday work.
Read full definition →AI Knowledge Base
A structured collection of documents that an AI can read, reference, and build upon to produce consistent, accurate outputs.
Read full definition →AI Workflow
A repeatable sequence of AI-assisted steps that transforms an input into a finished output, often combining prompts, tools, and human review.
Read full definition →Chain-of-Thought Prompting
A prompting technique that instructs the AI to reason through a problem step by step before giving a final answer.
Read full definition →AI Change Management
The practice of planning, communicating, and supporting the adoption of AI tools across a team or organization.
Read full definition →CLAUDE.md
A schema file that gives an AI persistent instructions about how to interact with a project or knowledge base.
Read full definition →Context Window
The maximum amount of text an AI model can process in a single conversation, measured in tokens.
Read full definition →Fine-Tuning
The process of training a pre-trained AI model on a specialized dataset to improve its performance on specific tasks.
Read full definition →AI Hallucination
When an AI model generates information that sounds plausible but is factually incorrect, fabricated, or unsupported by its training data.
Read full definition →Prompt Engineering
The practice of writing clear, structured instructions that guide AI models to produce accurate, useful outputs.
Read full definition →Prompt Library
A curated collection of reusable prompts organized by task, role, or department that teams can share and refine over time.
Read full definition →RAG (Retrieval-Augmented Generation)
A technique that retrieves relevant documents from a knowledge base and feeds them to an AI model so it can generate answers grounded in real data.
Read full definition →System Prompt
A hidden instruction given to an AI model at the start of a conversation that defines its role, behavior, and constraints.
Read full definition →Tokens
The basic units of text that AI models process. A token is roughly 3-4 characters or about three-quarters of an English word.
Read full definition →