Unit 2 AI Web Design WordPress
Across
- 3. Three measurements Google uses to judge whether a website loads quickly and feels responsive: LCP, INP, and CLS. You can check them at pagespeed.web.dev.
- 4. The type of software behind most AI tools; it is trained on huge amounts of text and predicts what words are most likely to come next based on patterns it learned.
- 5. A short written description of an image, read aloud by screen readers and used by search engines to understand what the image shows.
- 7. Compressing image files so they take up less space and load faster, without making the image look noticeably worse.
- 9. A private copy of a website used to test changes before they go live.
- 10. Telling readers when AI was used to help create the content they are reading.
- 11. A reference to the source of a fact, quote, or idea. AI tools sometimes invent citations that do not actually exist.
- 13. The title of a page as it appears in search engine results. Should be unique for every page and under 60 characters.
- 15. The rules that determine whether you have the legal right to use a piece of content, an image, or code that an AI tool produced or referenced.
- 17. To remove or replace real names, numbers, and other identifying information before putting content into an AI tool.
- 18. What you type into an AI tool to ask it to do something.
Down
- 1. Extra HTML code, unnecessary div tags, or redundant scripts that some AI plugins generate, which slow a site down.
- 2. When an AI tool produces a confident-sounding statement that is factually wrong. One of the most common AI mistakes.
- 6. A short description of a page that appears under the title in search results. Should be unique and specific for every page.
- 8. The skill of writing prompts that are clear, specific, and structured so the AI produces something usable.
- 12. Software like ChatGPT, Claude, Gemini, or Copilot that you give a written request to and it produces written or visual content in response.
- 14. Patterns of unfairness or stereotyping that exist in AI training data and can show up in AI output.
- 16. A multi-step review process for AI-assisted content: request an outline, draft, refine, verify, and only then publish. Each step can loop back to improve the result.