Glossary
Chunking
Chunking is splitting a document into smaller passages so a retrieval system can fetch and quote the part that answers a question rather than the whole page. Engines retrieve chunks, not sites, which means the unit that competes for a citation is a section of your page.
In plain terms
Your page gets cut into pieces. Each piece has to stand on its own, because that is what gets shown.
Why it matters
It changes how you write. A section that depends on three paragraphs of earlier context will be retrieved without them and will read as incoherent — so it will not be chosen.
How to apply it
- Start every section with a self-contained statement of what it covers.
- Repeat the subject noun instead of relying on "it" or "this".
- Keep sections tight, with one claim and its evidence.
Example
A 3,000-word guide to SOC 2 compliance gets split into passage-sized chunks by a retrieval system; only the 200-word section defining "Type I vs Type II reports" is fetched and quoted when a user asks that specific question, while the rest of the guide is never shown to the model.
Related terms
Back to the full glossary (75 terms).
Ranking is no longer enough
You need to be cited, mentioned, and recommended.
Being cited, mentioned, and recommended are three different outcomes, and most brands only ever achieve the first one. Ranking is no longer enough because AI engines answer buyers directly and name only a short list of vendors as the recommendation — everyone else is cited in passing, if at all. Get a free AI Visibility Report to see exactly where your brand appears today across ChatGPT, Google AI Overviews, Gemini, Perplexity, and Copilot, where competitors are winning the recommendation instead, and what's keeping you from moving up the shortlist.