Portfolio project · Catalog operations

Turning a basic ERP export into a catalog ready for review.

I built and tested this Make workflow to turn product-image evidence into catalog drafts that a person can review. I set the ERP fields that remain the source of truth, defined the customer-facing outputs the workflow can prepare, and designed the review handoff before any product could be published.

Ivory lace V-neck sleeveless midi dress with tiered asymmetric hem on a model
01 / Context

The catalog had the business data, but not the customer-facing content

The ERP already contained the data needed to run the business: SKUs, barcodes, prices, inventory, variants, and image filenames. Most of the content that customers would see was still blank.

Writing nine customer-facing fields, including titles, categories, descriptions, tags, SEO fields, and alt text, by hand for 44 products would take time. In this test, the workflow took about two minutes per product to prepare those fields for review, while keeping the catalog more consistent.

Could the product image help complete the catalog without turning a visual guess into a fact?
02 / Solution

Turn visible product details into a reviewable draft

The workflow uses AI to identify visible product characteristics and turn them into product-page content and categorization. Guardrails keep visual observations from becoming unsupported facts, and every product goes through human review before publication. Here is how it works:

SELECTPick the next rowsGoogle Sheets finds up to five products with the status READY.
MATCHFind the correct imageThe image filename is matched to the exact file in Google Drive.
DOWNLOADPrepare the imageMake.com downloads the file so the Make AI Agent can read the image itself.
COMPLETEFill the missing fieldsThe Make AI Agent uses the image and ERP row together to create the catalog content.
REVIEWReturn the row for reviewGoogle Sheets receives the updated row, and the status changes from READY to REVIEW.
03A / Evidence

Preview the customer-facing content after review

I created this view to connect the completed spreadsheet to the customer-facing product page it could support. This is a portfolio example, not a live Shopify integration.

Terracotta one-shoulder embroidered midi dress
Liora Vale · Romantic Details

Asymmetrical One-Shoulder Embroidered Midi Dress

$228.00

Terracotta

What is visible in the image


About this example
This page shows how the completed fields could appear in Shopify. The workflow does not publish directly to Shopify.

See the source record and the draft side by side

03B / Product copy

A useful description starts with what the image can support

The draft turns visible product evidence into language a customer can use. It describes what can be seen, makes room for practical styling context, and keeps unconfirmed facts out of the copy.

01

Visible evidence

Color, silhouette, neckline, length, embroidery, texture, and other details a shopper can see in the image.

02

Product language

Those details become clear product copy, with styling suggestions framed as suggestions, not product facts.

03

What stays out

Fabric composition, measurements, construction, and anything else the image cannot confirm stays blank for review.

03C / Evidence

Inspect the synthetic product set behind the test

44 products created for this study

Select a sketch to view its corresponding product image. I created the fashion sketches first, then turned each look into a realistic product image and used the full set as the synthetic test catalog. This image set was created separately from the Make.com enrichment workflow.

First half of the AI-generated fashion collection
Second half of the AI-generated fashion collection
Selected realistic product image
04 / Production

What the prototype showed, and what production would measure

The first run

Processing all 44 products at once did not work.

The run timed out, so I changed the workflow to process five products at a time. When a row is complete, its status changes to REVIEW. The next run starts with the remaining READY rows and does not repeat finished work.

The practical lesson: the status column became as important as the prompt.

The first descriptions sounded too stiff

The descriptions followed the requested structure, but they did not sound natural. I changed the instructions to separate three things: what the image clearly showed, what could be offered as a styling suggestion, and what the image could not confirm.

The final descriptions sound more like a stylist explaining the piece to a customer. Any detail that still needs confirmation stays in the review fields.

What the workflow completed

All 44 products reached REVIEW. Forty have every enrichment field completed. I kept four products with blank fields in this portfolio so the review case stays visible. In a live catalog, those products would remain offline until a person reviewed and completed the missing fields.

Resources

Project files

These sanitized spreadsheets show the study data. The first contains the original ERP data. The second contains the fields added by the Make.com workflow.