Case study
AI product descriptions from photos
Turned Stupel's product photos into SEO-optimized listings automatically, cutting per-listing writing from 30-60 minutes to seconds.
Industry
E-Commerce / SaaS
Key result
Auto
Product descriptions generated
Services
E-Commerce
The Challenge
The Challenge
Stupel sells products online and, like most e-commerce businesses, needed good product descriptions. Writing them by hand was slow. For every new product someone had to look at the photos, figure out what to say, and write the copy. Then someone else had to check it. Then someone had to optimize it for search. It could take 30 to 60 minutes per listing, and across hundreds of products that added up fast.
The quality was also inconsistent. Different writers described the same types of products in different ways, so some listings came out detailed and compelling while others were thin. Customers could not tell what they were buying, and that hurt conversions. Listings also went out missing SEO keywords. What Stupel needed was a way to generate high-quality, consistent product descriptions automatically, from the product images they already had.
The Solution
The Solution
NetAesthetics built an AI workflow that takes a product image as input and outputs a complete, SEO-optimized product description, with no human writing step. Amazon Rekognition analyzes the image and extracts what it sees — materials, colors, features, dimensions — then passes that data to an AI language model that writes the description. The system was built around what good product copy looks like: short sentences, feature-benefit pairs, and keywords woven in naturally, so the output reads as an experienced copywriter would write it rather than a robot.
Each listing takes seconds. A product photo goes in and a full description comes back ready to publish, so a catalog that used to take weeks to write can be processed in a day. That changes the math on launching new products. Coverage is not limited by category: Amazon Rekognition is trained on millions of images and works across apparel, home goods, electronics, food, and tools, and the language model adapts its output based on what it sees in the image.
Results
Results
Auto
Product descriptions generated
100%
Image analysis coverage
SEO
Optimized output
Scalable
Workflow for any catalog size
30-60 min
Writing time per listing, before
Seconds
Writing time per listing, after
Before & after
Before and after
Before
Product descriptions written by hand
AI writes descriptions from photos
Hours per listing
Seconds per listing
Inconsistent copy quality
Consistent optimized output
Listings missing SEO keywords
Built-in SEO from day one
Common questions
Common questions
More case studies
Get started
Ready to see what AI
can do for your business?
Book a free 60-minute consultation. No sales pitch — just honest answers about where AI fits.