# Knowledge chunkability & content depth

> Chunkability is how well a page splits into self-contained blocks, each answering one question under its own heading, which AI search can retrieve one by one.

- **Check ID:** A13
- **Area:** [AI Readiness](https://be1st.ai/glossary/ai-readiness)
- **Tool:** [AI Readiness](https://be1st.ai/tools/ai-readiness)
- **Page:** https://be1st.ai/glossary/ai-readiness/knowledge-chunkability

## Why it matters

RAG (Retrieval-Augmented Generation) systems split web content into chunks before storing them in a vector database. If content is poorly segmented, chunks lose context and AI generates inaccurate or incomplete responses.

## In practice

Stripe API documentation has each endpoint in a separate section with a heading, description, parameters, and examples. This allows AI systems to accurately extract information about a specific endpoint without contamination from other sections.

## How be1st checks it

Evaluates how well the page content can be divided into standalone knowledge blocks (chunks). Each chunk should contain one complete idea with a clear heading and context. The check scores the average paragraph length (ideally up to 60 words), the density of H2 and H3 headings, headings with an id attribute, the word count (at least 500, 200 on the homepage) and the average sentence length (up to 20 words).

[AI Readiness](https://be1st.ai/tools/ai-readiness), Content tab.

Every check ends as: Pass, Warning, Fail.

## Sources

- [Creating Helpful Content](https://developers.google.com/search/docs/fundamentals/creating-helpful-content) (Google)
- [Google Search Essentials](https://developers.google.com/search/docs/essentials) (Google)

## Related terms

- [Word count](https://be1st.ai/glossary/fingerprint/word-count): Word count is the number of words in the visible text of a page, after the code and hidden elements are removed.
- [Reference / evidence signals](https://be1st.ai/glossary/ai-readiness/reference-evidence-signals): Evidence signals are the references in a text that back up its claims: links to studies, statistics, named sources and citations.
- [Freshness signals](https://be1st.ai/glossary/ai-readiness/freshness-signals): Freshness signals show when content was published or last updated: a visible date, a `<time>` element or dateModified in structured data.
- [Entity & author completeness](https://be1st.ai/glossary/ai-readiness/entity-author-completeness): Entity and author completeness is how clearly a website says who is behind it: the author, the company, contact details and profiles elsewhere.
- [AI-friendly content formats & feeds](https://be1st.ai/glossary/ai-readiness/ai-friendly-content-formats): AI-friendly formats and feeds are versions of your content made for machines, such as RSS feeds, llms.txt, Markdown pages or a JSON API.
- [Linkability of key facts](https://be1st.ai/glossary/ai-readiness/linkability-of-key-facts): Linkability of key facts means the important parts of a page have their own anchors (#section), so anyone, an AI answer included, can link straight to them.