# [LLM visibility: help AI assistants read your business information](https://rebilder.com/solutions/llm-visibility)

- **Updated:** 2026-09-10
- **Description:** Improve LLM visibility with accessible business facts, useful content and response checks across the retrieval paths your customers use.

Give assistants useful, current business information. Inspect both direct responses and browser views, then improve missing answers and source connections.



## What you get

- Measure response bytes and estimated tokens
- Cut a page to its facts without changing what browsers get
- Source integration through the SDK
- Choose self-hosted serving and optional connected reporting

## Visibility is a budget problem first

Some agents read the initial HTTP response; others use a browser or a search index. Compact, well-structured business facts support direct retrieval while clear rendered pages support browser-based use.

Improve structure and content together. The reference captures demonstrate compact representations of the same facts; use a scan to identify the opportunities on your own pages.

> **Check yours in one command** Compare the content type and facts as well as response size. Similar sizes do not establish that a request failed or that the page is unreadable.

## Where the first fact sits matters as much as the total

Clear structure helps readers find the important facts. The demo page captures demonstrate compact responses; test completeness and source consistency on your own pages.

- **Find your own offset.** For each template, search the raw HTML for the first fact a person would actually ask about: a price, opening hours, a fee, an eligibility rule.
- **Count what is above it.** Everything before that offset is what a model pays to reach you.
- **Improve the useful answer.** Remove irrelevant markup from the agent response and clarify source content where the customer needs more information.

## Connect the serving layer

Content negotiation provides a compact representation for clients requesting it. The gateway renders configured business sources; Answers generation is a separate source-backed workflow.

middleware.ts

```ts
import { NextResponse } from 'next/server'
import { createGatewayProxy } from '@rebilder/gateway/next'
import { gatewayConfig } from '@/lib/gateway-config'

// Configure storeId and source resolvers in gatewayConfig.
export default createGatewayProxy(gatewayConfig, () => NextResponse.next())
```

The SDK serves independently of the Console plan. Choose self-hosted or managed operation according to the maintenance and reporting your team needs.

## What is LLM visibility?

Whether a language model can retrieve your pages and afford to read them. It has two measurable parts: is the fetch answered with parseable text, and how many tokens does the useful content cost once it arrives.

## How many tokens does my page cost an LLM?

Roughly bytes divided by four for English prose, but the ratio is worse for markup-heavy HTML because tags tokenize badly. The reliable way is to fetch the page as the agent does and measure what comes back rather than estimating from the rendered view.

## Does serving markdown to models affect my site for humans?

The gateway serves your normal pages to browsers and markdown to supported requesting clients. Test the integration with your theme, analytics and checkout when you install it.

## Can I do this without a third-party service?

Yes. The gateway SDK is free and self-hostable. Run the CLI locally to inspect your site; it keeps scan results on your machine.

## Related

- [AI visibility: improve your business information](https://rebilder.com/solutions/ai-visibility)
- [LLM SEO: what transfers from SEO](https://rebilder.com/learn/llm-seo)
- [LLM optimization](https://rebilder.com/solutions/llm-optimization)
- [LLM brand visibility](https://rebilder.com/solutions/llm-brand-visibility)
- [Gateway quickstart](https://rebilder.com/docs/quickstart)