# Artificial Intelligence

> AI for designers: LLM fundamentals, agents, orchestration, AI UX patterns, vibe coding, tools and career, explained from a product design point of view.

## Pages

- [Agent vs. Assistant vs. Copilot: Three Ways to Delegate to AI](https://www.fernandoux.com/en/wiki/ai/agent-vs-assistant-vs-copilot/)
  An assistant answers, a copilot suggests inside your task and an agent runs steps on its own. How to tell them apart and what design each one needs.
- [AI Product Strategy: How to Decide Where AI Goes](https://www.fernandoux.com/en/wiki/ai/ai-product-strategy/)
  An AI product strategy is a portfolio of bets with measured value, data and risk. Learn how to score initiatives and decide where to invest first.
- [Claude Code: a programming agent that works in your repo](https://www.fernandoux.com/en/wiki/ai/claude-code/)
  Claude Code is Anthropic's programming agent: it reads your code, edits files and runs commands. What it does, what it costs and what to check before accepting.
- [Loading states in AI interfaces: what to show while the model thinks](https://www.fernandoux.com/en/wiki/ai/ai-loading-states/)
  What to show while an AI model responds: spinner, skeleton, real steps or a progress bar, depending on how long the wait lasts and what the NN/g guidelines say.
- [Response streaming: showing AI output while it is being written](https://www.fernandoux.com/en/wiki/ai/response-streaming/)
  Response streaming shows an AI model's text as it is generated, instead of waiting for the end. How it works with SSE and how to design the interface for it.
- [Tokens: The Unit AI Thinks (and Bills) In](https://www.fernandoux.com/en/wiki/ai/tokens/)
  A token is the chunk of text an AI model processes as one unit. What tokens are, how many a word has, how they are counted and how they affect cost and limits.
- [Vibe coding vs. AI-assisted engineering: the difference that decides quality](https://www.fernandoux.com/en/wiki/ai/vibe-coding-vs-ai-assisted-engineering/)
  Vibe coding accepts code without reading it; AI-assisted engineering reviews, tests and starts from a spec. What changes and when to use each.
- [What Is an AI Agent?](https://www.fernandoux.com/en/wiki/ai/what-is-an-ai-agent/)
  An AI agent decides its own steps, uses tools to act and reviews the results until it finishes. How it works and how it differs from a chatbot or a workflow.
- [What Is an LLM? Explained for Designers](https://www.fernandoux.com/en/wiki/ai/what-is-an-llm/)
  An LLM is a language model trained on huge amounts of text to predict the next token. Here is how it works and what it means for the people who design with it.
- [What is vibe coding? Programming by describing what you want](https://www.fernandoux.com/en/wiki/ai/what-is-vibe-coding/)
  Vibe coding means building software by telling an AI what you want, without reviewing the code. Where the term comes from, what it suits and where it stops.


---

Source: https://www.fernandoux.com/en/wiki/ai/