> ## Documentation Index
> Fetch the complete documentation index at: https://docs.merchantops.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Reviewing enriched products

> How to check enrichment status and completeness, re-run enrichment, and why your own values are protected.

After [enrichment](/enrichment/how-it-works) runs, each product carries signals
that tell you how far it got and how complete its data is. This page covers what
to look for, when to re-run enrichment, and why the values you entered yourself
are safe. For the shared vocabulary, see
[Core concepts](/getting-started/concepts).

## Enrichment status

Every product tracks an **enrichment status** that tells you where it is in the
process — for example, whether it's still queued, in progress, finished, or ran
into a problem. Use it to spot products that haven't been enriched yet or need
attention.

## Completeness score

Alongside the status, each product carries a **completeness score** — a single
number that reflects how much of the product's data is filled in. A higher score
means a more complete record; a low score points to a product still missing
descriptions, attributes, or other fields. Use it to prioritize which products to
review or re-enrich first.

<Note>
  The score reflects completeness, not correctness. A high score means the fields
  are populated — always spot-check the values themselves.
</Note>

## What "enriched" looks like

A well-enriched product has its descriptive content written, its attributes
standardized to your catalog's values, and identifiers or brand data filled in
from the sources enrichment consulted. Because enrichment adds a **new version**
rather than overwriting, the enriched result sits alongside the version you
started with — the latest or production-labeled version usually holds the richest
data. See [Versioning](/catalog/versioning) for which version to read.

## Re-running enrichment

You can run enrichment again on a product — for example after the brand updates
its site, or after new data lands in the lakehouse. Each run adds another version
with the freshest merged result, so re-running is safe and never destroys earlier
versions.

## Your values are protected

Enrichment merges sources by priority — **brand site > lakehouse > your
input > AI-generated** — and the values *you* entered outrank AI-generated
content. That means re-running enrichment won't quietly overwrite your input with
a machine-generated guess: your data is preserved, and enrichment fills the gaps
around it.

<Note>
  Because enrichment adds a new version rather than editing in place, the version
  you started with — including the values you entered — always remains available.
  See [Versioning](/catalog/versioning).
</Note>

<CardGroup cols={2}>
  <Card title="How enrichment works" icon="wand-magic-sparkles" href="/enrichment/how-it-works">
    The steps enrichment runs and how sources merge by priority.
  </Card>

  <Card title="Versioning" icon="code-branch" href="/catalog/versioning">
    Why enrichment adds versions and which one holds the richest data.
  </Card>
</CardGroup>