How a generated answer picks the sources it will name

An answer engine does not rank pages. It writes a paragraph and then decides which pages to credit for it. One slider follows a single question from fan-out to citation.

Stage The question
  1. 0
  2. 1
  3. 2
  4. 3
  5. 4

Tap a part of the diagram to open that stage.

What GEO actually optimizes

Generative Engine Optimization is not a new set of tricks bolted onto a page. It is the same visibility problem moved one level down: from the page to the passage. A source gets named when it is retrievable, self-contained enough to survive being cut into a chunk, cheap enough in tokens to fit the budget, and quotable enough that a sentence can lean on it. None of those four is a keyword.

What's inside

  1. 1 One question becomes several searches — Nobody ever sees these intermediate queries, including the person who asked.
  2. 2 Every sub-query drags back its own passages — The unit that gets retrieved is a passage. So the unit worth writing is a passage.
  3. 3 The context window is the real filter — A long, meandering passage spends budget it may not be worth. Density wins the packing.
  4. 4 Sentences are written against passages, not pages — Grounded is not the same as correct. It only means a source can be pointed at.
  5. 5 Only a few of the retrieved sources are ever named — Retrieval, inclusion and citation are three separate competitions. A source has to win all three.
Read more What GEO Is: Generative Engine Optimization GEO is not a new bag of tricks. It is the same visibility problem moved from the page down to the passage. What answer engines actually select for, and how to measure something that has no position.

Explorable Explanations

Stage The question
  1. 0
  2. 1
  3. 2
  4. 3
  5. 4
1 / 5