A growing reference for the AI a designer actually needs to know.

The base layer: what AI, machine learning and neural networks actually are, and how models learn.

How large language models work — tokens, transformers, training, prompting and their limits.

How meaning becomes numbers: embeddings, vector databases, semantic search and RAG.

Where AI's data lives and flows: warehouses, lakehouses, embedding models and the pipelines that feed models.

Putting models to work: tool use, agents, chaining, MCP, guardrails and evaluation.

Repeatable patterns for applying AI to product and design problems.

Bias, hallucination, privacy and the responsible-AI considerations product teams must own.