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
- 0
- 1
- 2
- 3
- 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 One question becomes several searches — Nobody ever sees these intermediate queries, including the person who asked.
- 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 The context window is the real filter — A long, meandering passage spends budget it may not be worth. Density wins the packing.
- 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 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.
Explorable Explanations
- How a search engine decides who gets found Ten blue links look like a list. They are the last frame of a pipeline that starts with a crawler and ends with a click curve. One slider walks the whole thing.
- One page, two front doors SEO and GEO are not two projects. They are one document that has to satisfy two different readers: a ranking function and a retrieval step. One slider shows what they share, what they don't, and what it costs to add the second door a year late.
- How a drug is smuggled past the blood–brain barrier The brain refuses almost every drug molecule, and it is right to. One slider follows the trick the labs are trying instead: wrap the molecule in a bubble the wall already knows how to carry.
- How a robot draws the map of a room it has never seen A lidar returns a few hundred dots per sweep and no idea where it is. One slider walks from that cloud to a floor plan with the robot standing in the right spot.
- How two people type in one line without losing a letter Two cursors, one line, nobody holding the pen in the middle. One slider takes an index-based merge apart and rebuilds it out of addresses that sit between the letters.
- Why a quantum computer stops at a lattice Shor’s algorithm eats RSA in one move. The same machine gets almost nothing on a grid of points with a little noise added. One slider shows the difference.
- Cooling a building by pointing it at space A coating that stays colder than the air around it, in full sun, drawing no power at all. One slider follows the heat from the sun to the far side of the atmosphere.
- How a robot predicts the next second A text model guesses the next word. A world model guesses the next frame — mass, speed and gravity included. One slider walks the whole loop, from the camera to the catch.
- Proving a secret without revealing it One slider walks through the stages, the other adds rounds. Watch certainty climb to almost total while the secret stays a secret.
- Getting lithium out of brine: ponds versus direct extraction Move the slider through five stages and compare two ways of taking the same metal out of the same salt water.
- How a personalised mRNA cancer vaccine works Move the slider through five stages and watch how a tumour’s own mutations become the instructions that teach the immune system to find it.
- The edge of the app Everything arriving from outside is untrusted. Break one link at a time and watch where the chain stops and what the screen shows.
- How search over your documents works Move the sliders and watch a search pipeline decide what the model is allowed to see — and what happens when it is fed the wrong passage.
- Retries and slow responses The network drops in the middle of an operation. Press the button twice and see what ends up in the database — with an idempotency key and without one.
- How a language model writes The weights are frozen and nothing is remembered. Pull the sliders and watch the model pick the next piece of text, over and over.
- How a language model learns Pull one slider and watch a pile of random numbers turn into a prediction over a thousand training steps.
- Where electricity comes from Pull one slider and follow the energy from a river all the way to a pump that lifts water back up.