Urgent.News

What's breaking now, across thousands of outlets.

Tech

Don't write a 2,000-word About page for the model. Write one sentence it can lift.

Models don't read your About page. They lift a sentence from it. So the most important copy on your site might be 25 words long. There's a wave of advice telling founders to write long, "comprehensive" pages so AI assistants understand them. I think that's mostly backwards. Long pages are great for humans who want depth. For an assistant building a two-line answer, length is something to dig…

The most influential copy on your website might be as short as 25 words. Contrary to the popular advice to write lengthy, comprehensive pages for AI assistants, the focus should be on creating a concise sentence that can be directly lifted from your site. When an AI assistant answers a question using web sources, it retrieves a few pages, selects relevant passages, compresses them into an answer, and cites the source.

The winning passage is one that answers the question on its own. A liftable sentence typically follows the template: [Name] is a [category] that [does one concrete thing] for [specific audience]. It starts with the name, uses a category people search for, one verb, one job, names the audience, is 30 words or less, and can be easily pasted into various places like the homepage, title, meta description, About page, FAQ, social bios, and app store listings.

To ensure the sentence works, copy it, paste it into a new document, and ask someone unfamiliar with your project what it is and who it's for. If they can answer, the sentence is effective.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Should a daily puzzle tell you how close you were, or only whether you were right?

Every daily puzzle makes one design decision before anything else: what happens after a wrong guess. "Wrong" is one bit of information. "Warm" is a lesson. "Here's exactly how far" might be a spoiler.

  • Binary feedback simply tells if you're right or wrong
  • Proximity feedback indicates how close you were to the correct answer
  • Explanatory feedback provides reasons for wrong guesses

A right-or-wrong score throws away the most useful part of a wrong answer

Two people answer "Sydney" to "What's the capital of Australia?" One was guessing. One was sure. A right-or-wrong score gives them the same zero, and loses the only thing worth knowing.

  • Binary scoring system loses insight into thought process
  • Different scores for wrong answers can enable targeted feedback
  • Hypercorrection effect suggests confident wrong answers are teaching moments

More from Friday 13 November →