> This page is for Developer.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.bigcommerce.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.bigcommerce.com/_mcp/server.

# What is Catalog Enrichment?

> What Catalog Enrichment generates, why product content affects search and answer engine visibility, and how this guide relates to the support documentation.

Catalog Enrichment is a paid AI tool in the BigCommerce control panel. It reads your existing product data and generates content for seven product fields, optimized for search engines and answer engines.

> **Beta**
>
> Catalog Enrichment is in beta and enabled for a subset of stores. If it is available on your store, you will see a banner on the control panel Home page.

## What this guide covers

The [support article](https://support.bigcommerce.com/s/article/BigCommerce-Catalog-Enrichment) documents the procedure: where to click, what each screen does, how to purchase entitlements, and how to apply results. Follow it for mechanics.

This guide covers the decisions the procedure doesn't make for you — what to put in your brand guidelines, which products to enrich together, how to review at scale, and how to tell whether it worked. Output quality depends far more on these choices than on the click path.

## How you guide the voice

Enrichment writes from your product data, but two inputs decide how it sounds: **brand guidelines** and **additional context**. Without them the output is accurate and generic. With them it reads like your store.

Brand guidelines describe how you speak — personality, tone, the words you use and avoid, and the claims you cannot make. Additional context adds instructions specific to the products in one enrichment, such as how a particular line is positioned. You enter both when you create an enrichment, and both are applied to every field it generates, so specificity pays across the whole run. Brand adherence is also scored only when you supply guidelines.

These are the inputs most worth your time. See [Writing brand guidelines](/developer/docs/ai-tools/catalog-enrichment/inputs/brand-guidelines) and [Purpose, keywords, and context](/developer/docs/ai-tools/catalog-enrichment/inputs/purpose-keywords-context).

## Why product content matters more than it did

Two things changed.

**Shoppers ask questions instead of typing keywords.** Answer engines assemble responses from product content they can read and cite. A page with two lines of description gives them nothing to work with.

**The volume of usable text required has grown.** Search engines still expect text that is human-readable, unique, and specific to the product. Answer engines need enough substance to quote. Product detail pages carry most of that load, and writing it by hand does not scale past a few hundred products.

Enrichment closes the gap by generating that content from the product data you already hold.

## What it generates

Seven fields. Four write to built-in product attributes, three are added as custom fields for answer engines. See [Fields in an enrichment](/developer/docs/ai-tools/catalog-enrichment/overview/fields).

![The Enrichments list showing three enrichment runs, each with a product count, the seven fields generated — product name, description, SEO meta description, SEO page title, AI snippet, intent Q and A, and conversational Q and A — and a status of generated or completed.](/_fern-img/c3625841ce6623ee12767590bdcdce7eab4bb158e7362c2dcf51bb0ac29e024f.webp)

## Where to start

#### [Check your source data](/developer/docs/ai-tools/catalog-enrichment/before-you-enrich/source-data)

Output quality is capped by input quality. Start here.

#### [Plan your batches](/developer/docs/ai-tools/catalog-enrichment/before-you-enrich/planning-batches)

Which products to enrich together, given the 250-product limit.

#### [Write your brand guidelines](/developer/docs/ai-tools/catalog-enrichment/inputs/brand-guidelines)

The input that most affects how the output reads.