CatalogFix AI — Product Catalog Cleaning & Data Quality Audit

Clean messy product catalogs before they reach your store, marketplace, or feed. CatalogFix normalizes product fields, flags missing data, invalid prices and duplicates, and separates Ready rows from records needing manual review.

Designed to reduce manual catalog QA before import or publication. Upload a supplier PDF, Excel, or CSV file; download structured products and an issue report.

See the result before you run

Supplier CSV → normalized products → Ready / Needs Review → Issues Found

Preview from two successful synthetic demo runs on 14 October 2026. These are fictional products, not customer results.

Supplier data	Product output	Status	Issue / next action
cfx-201, uneven title spacing	CFX-201 · Linen Cushion Cover · 24.90	READY	Review the normalized record
CFX-302, price -5.00	Travel Lunch Box · source price retained	NEEDS REVIEW	Negative price; confirm the supplier price
Two rows with SKU CFX-304	Both conflicting products retained for review	NEEDS REVIEW	Duplicate SKU; resolve the conflicting records

Download: RESULT.xlsx with Issues Found, separate Ready / Needs Review views, and SHOPIFY_READY.csv for rows passing the current gates. Ready is a quality-gate result; review relevant issues before import.

Run the 3-product demo · Try a catalog audit

From $4.90 per completed catalog up to 50 PDF pages: get normalized product data, a Ready / Needs Review split and an issue workbook. Larger PDF tiers and non-catalog screening prices are listed below. A completed tiny demo is subject to the same catalog event pricing; Apify credits or plan eligibility determine what you actually pay.

40-second illustrated walkthrough

This is an illustrated workflow guide, not a screen recording. All demo products are fictional.

Quick start

1. Run the linked three-product example (one row has a missing price), or use the Actor's prefilled two-product smoke test. Replace Supplier catalog with your PDF, CSV, XLSX or XLS file.
2. Open Catalog quality at a glance to review product status and normalized values.
3. Download RESULT.xlsx and check Issues Found for issue type, severity, affected field and current value.
4. Review flagged rows before import. SHOPIFY_READY.csv contains rows passing the current quality gates; it is not a guarantee of acceptance by every marketplace.

Before / After

Before: supplier data	After: CatalogFix output
cfx-101, uneven title spacing	Normalized SKU CFX-101 and title Ceramic Mug
Missing or invalid price	Needs Review; missing price is not invented
Duplicate or conflicting SKU	Issue recorded for manual resolution
Uncertain extracted row	Explicit Ready / Needs Review status and source context
Manual inspection across a file	RESULT.xlsx with Issues Found and separate export views

These are synthetic demonstration examples. Ready means the row passed current quality gates; inspect relevant issues before import.

Example results

These results come from the bundled synthetic demonstration catalogs, processed by CatalogFix:

Record	Issue in Issues Found	Severity	Result / next action
CFX-101	Extra spaces and lowercase SKU in source	—	Normalized SKU CFX-101, title Ceramic Mug, price 19.90; READY
CFX-102	Missing or invalid price	Critical	NEEDS REVIEW; obtain the correct supplier price
CFX-302	Negative price	Critical	NEEDS REVIEW; confirm the price in the source
CFX-304	Duplicate SKU	Critical	NEEDS REVIEW; resolve the conflicting records

The next actions above are guidance for interpreting the report. CatalogFix does not fabricate missing values or generate a suggested repair for every issue. Possible duplicate products can be flagged for review even when their rows pass the basic Ready gates.

Popular use cases

Clean supplier Excel catalog

Normalize supplier spreadsheet product data, flag missing commercial fields, and separate Ready records from rows that need review.

Convert supplier PDF catalog to product data

Extract structured product data from text-based or image-only supplier catalogs while keeping uncertain records review-only.

Find duplicate products in a catalog

Surface duplicate or conflicting records before they reach Shopify, a marketplace, PIM, or product feed.

Check missing SKU and prices

Flag records where supplier SKU, price, or other required commercial data is missing or uncertain.

Clean ecommerce CSV before import

Use CatalogFix as a QA gate before uploading product data to your storefront or downstream feed.

Audit product feed before Shopify import

Review catalog quality and separate import-ready products from records requiring manual attention.

Prepare supplier catalog for marketplace upload

Clean and audit supplier product data before marketplace publication.

Best for

• supplier catalogs that need to become e-commerce product data;
• image-only PDF catalogs that require OCR;
• mixed catalogs with printed and unprinted supplier codes;
• price lists and order forms;
• teams that need an audit trail instead of a black-box extraction.

What you get

Every successful catalog run can produce:

• RESULT.xlsx — full workbook with Clean Master, Issues Found, Shopify Ready, Needs Review, and Import Report;
• SHOPIFY_READY.csv — only rows that passed the current release gates;
• SUMMARY.json — counts, document type, and quality statistics;
• IMPORT_REPORT.json — page/sheet routing and parsing audit;
• Dataset — normalized product rows with source and quality context.

Ready vs Review

CatalogFix does not treat every extracted row as equally trustworthy.

Ready

A row is placed in Ready only when it passes the current release gates, including required product fields and quality checks.

Needs Review

A row is placed in Needs Review when something important is uncertain, for example:

• supplier SKU is missing or not confidently verified;
• OCR confidence is low;
• title or product-card boundaries are uncertain;
• required commercial data such as price is missing.

This means a run can legitimately return zero Ready rows while still extracting useful product candidates. That is intentional behavior, not a failure.

Safety behavior

CatalogFix prefers an explicit review state over false certainty.

• Missing supplier SKUs are not invented.
• Internal candidate IDs stay review-only.
• Technical datasheets can be rejected with zero product rows.
• Visual OCR keeps source location and confidence metadata.
• Structured price sources preserve price provenance where available.
• Quality gates keep uncertain records out of Shopify Ready.

Knowing when not to extract is part of the product.

Input

Upload one supplier catalog per run.

Supported formats:

• PDF
• CSV
• XLSX
• XLS

You can also provide a direct HTTP(S) URL.

For URLs that do not preserve a recognizable file extension, use Filename override.

Verified release behavior

CatalogFix AI v1.9.0 was regression-tested across:

• image-only visual catalogs;
• structured dual-price order forms;
• technical datasheet refusal.

In the image-only Appliances test, the Actor successfully ran RapidOCR on Apify, extracted structured product rows, preserved verified supplier codes such as DW-01, MWO-1, FSCR01, BIO-01, CW-165, and CW-46, and kept uncertain rows in Review.

In the TL972 technical-datasheet test, CatalogFix intentionally returned zero products with a technical-datasheet skip status.

How it works

1. Upload a catalog.
2. CatalogFix classifies the document and routes pages by content type.
3. Structured parsers handle commercial tables and order forms where possible.
4. Visual pages use adaptive OCR.
5. Quality gates separate Ready rows from review-only rows.
6. Download the structured dataset and audit files.

Pricing

CatalogFix uses pay per event with one charge per completed run:

• Up to 50 pages: $4.90
• 51–200 pages: $12.90
• 201–500 pages: $24.90
• Technical/statistical non-catalog screening: $1.00

The catalog event includes OCR/parsing, QA and the listed output files; there is no separate OCR event. CSV and Excel files use the $4.90 small-catalog event. A completed demo uses the same event pricing. A completed run with no detected products can still incur the catalog event; only files classified as technical/statistical non-catalog documents use the $1 screening event. Inspect the source and select an appropriate maximum cost before starting. Apify credits and applicable discounts determine the amount charged to your account.

The current self-service Store version accepts PDFs up to 500 pages. Larger catalogs should be split or handled as a managed/custom run.

API, automations, and AI agents

CatalogFix can be run from the Apify Console, API, scheduled Tasks, integrations, and Apify MCP workflows. Public Example Tasks are named around concrete catalog-cleaning jobs so users and AI agents can start from a specific workflow instead of building an input from scratch.

Common automation pattern: supplier file → catalog QA → Ready / Needs Review → structured export or downstream ecommerce workflow.

60-second demo flow

Upload supplier CSV/PDF → normalize product fields → flag missing, invalid, or duplicate data → split Ready from Needs Review → download structured output and audit files.

Use the public Example Tasks in the Store to launch common catalog-cleaning scenarios with prefilled demonstration data.

Notes and limitations

• OCR-heavy PDFs take longer than text-based catalogs.
• A second OCR pass may be triggered when the first pass is not reliable enough.
• A real supplier SKU can still remain in Needs Review if other required fields are missing.
• CatalogFix does not promise perfect extraction. It makes uncertainty explicit and auditable.

Current release

Sellable v1

Try your own small catalog / support

Send us one small supplier catalog and we'll show you the Ready / Needs Review output. Start with the Actor's Issues tab to arrange a sample; do not attach a confidential supplier file to a public issue. Only share a catalog you are authorized to share, through an agreed private channel.

For support, include the run ID, input format and expected outcome in the Issues tab. If CatalogFix helped with a real import or catalog QA job, an honest Store review describing that workflow is welcome. No review is required for support or a sample. We do not promise an unverified response-time SLA.

Documentation and public example pages checked: 14 October 2026. Apify reported reliable prefilled-input execution at this check.