> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wisepim.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Clean and structure what you imported
> Duplicate SKUs, MiXeD case, stray spaces and no categories at all. Clean the mess in the order that stops each fix from undoing the last one.
Part 2 got the products in; this part makes them usable. A freshly imported supplier catalog is typically the same five problems repeated a few thousand times: duplicate SKUs, trailing spaces nobody can see, `WIRELESS HEADPHONES` next to `wireless headphones`, prices with six decimals, and no category on anything. Each is a one-click fix. The order is what matters, because a cleanup run in the wrong sequence quietly undoes the one before it. Budget about 90 minutes for 5,000 products.
**Before you start:** you need products in the project, so run [part 2](/en/guides/first-catalog/import) first. Everything here happens on the Products page with [filtering](/en/products/filtering-products) and [bulk editing](/en/essentials/bulk-editing). Data already tidy? Skip to [part 4](/en/guides/first-catalog/enrich).
**What you'll get:** no accidental duplicate SKUs, consistent text and numbers across the catalog, products sitting in your own category tree, and flat variant rows collapsed into proper configurable products.
## Find the duplicates before you change anything
Every step below acts on a selection, so start by making the selection honest. Fixing text first and duplicates second means paying for the same fix twice, once on each copy of the product.
On the Products page, click **Filters** next to the search bar and open the **Presets** tab. Each preset card shows how many products have that issue right now. Read the counts before touching anything, they are your to-do list for the rest of this guide.
Switch to **Advanced filters**, pick the SKU field with the **is duplicate** operator. This is the fastest way to surface repeated identifiers before they reach a channel.
The same operator works on EAN, which catches the duplicates that slipped through under different SKUs.
Look at the matches before acting; a repeated SKU is sometimes two genuinely different products from two suppliers. Save the filter as a set so you can re-run this check after every future import.
## Normalize the text, in this order
Run these three in sequence. Whitespace first because trimming spaces never changes meaning, and case before replacements because a Title Case pass run afterwards would re-capitalize the exact brand strings you just corrected. All four live in the bulk editing modal: click **Bulk Edit** with products selected, then search the action by name.
[Trim Whitespace](/en/essentials/bulk-editing/trim-whitespace), under **Text & Content**, strips the leading, trailing, and duplicated spaces that break sorting, search, and feeds while staying invisible on screen. It is the safe first move.
[Standardize Text Case](/en/essentials/bulk-editing/standardize-case), also under **Text & Content**, puts names and other text fields into one consistent style. Check the live before-and-after preview before applying.
[Find and Replace](/en/essentials/bulk-editing/find-replace) handles the leftovers: misspelled brand names, an old supplier's wording, stray HTML. Use whole-word matching so you do not hit substrings inside other words.
[Convert Numbers](/en/essentials/bulk-editing/convert-numbers), under **Attributes & Custom Fields**, rounds long decimals and rescales values, for example dividing weights by 1000 to go from grams to kilograms. A live preview shows the result on a sample value first.
Every one of these acts on your current selection. Filter first, read the match count in the filter summary, then select, so a stray condition cannot take your whole catalog with it.
## Give the catalog a structure
Structure comes last because it feeds on the work above: [AI Categorization](/en/ai/categorization) reads each product's content, so the tidier that content is, the better it places the product. Running it before the text cleanup means categorizing on the mess.
Select your products, click **Enrich with AI** in the toolbar, pick **AI Categorization**, and click **Start Enrichment**. It assigns products to your **existing** category tree and never invents categories, and the default 75% threshold gives you the confident assignments first.
Filter to whatever is still uncategorized and run again at 60 to 65%. You keep the safe assignments from pass one and only review the genuinely ambiguous products.
Auto-assign lets the AI decide how many categories fit each product. Turn it off and set a maximum when your rules limit where a product may appear.
If sizes and colours came in as separate products, select the ones that belong together and pick the [Group as Variants](/en/essentials/bulk-editing/group-as-variants) card under **Categories & Organization** in the bulk editing modal. It works on a page selection only, up to 500 products per run, and a toast reports how many were grouped and how many were skipped.
[Product families](/en/products/product-families) are templates per product type: assign one and the product inherits the attributes that type should have. Do it now, because that is what turns the missing-field reporting in part 4 into something meaningful rather than a list of fields nobody expected anyway.
## How to tell it worked
| Signal | Where to look | When it moves |
| ----------------------------- | --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| Duplicate SKU and EAN matches | Advanced filters with the **is duplicate** operator | Re-run the saved filter set after each cleanup |
| Preset issue counts | The **Presets** tab of the filter modal | Each card shows a live count |
| Uncategorized product count | Filter for products with no category | Drops sharply after the first pass at 75% |
| Quality score and grade | [Data Quality](/en/analytics/data-quality) overview | As data changes; force it with [Recalculate Data Quality](/en/essentials/bulk-editing/recalculate-quality) |
## When it doesn't work
The threshold is too high for this catalog, or your category names are ambiguous. Lower it to 60 to 65% and re-run on the remainder, and consider clarifying vague category names.
A misplacement usually traces back to thin product content, so the AI had little to work with. Enrich titles, descriptions, and attributes in [part 4](/en/guides/first-catalog/enrich), then categorize again.
The action is deliberately blocked when you select all products across all pages, because grouping every filtered product under one parent is almost never intended. Select on a single page, in batches of up to 500.
Turn on **Match whole words only**, and narrow the target fields rather than replacing across everything. Filtering to a small selection and checking the result before scaling up is the cheap version of an undo.
Check the match count in the filter summary before applying a bulk action. A broken filter now shows an error rather than quietly matching everything, but the count is still your safety check.
Clean, structured, and still half empty. [Part 4](/en/guides/first-catalog/enrich) fills the holes, and part 1's Knowledge Library is what decides how they sound.
## Related
Next in the series: fill the gaps without overwriting the data you just cleaned.
The same cleanup with a measured baseline in front and a Quality Guard floor behind it.
Presets, the is-duplicate operator, and saved filter sets.
Every bulk action available, and what each one changes.