Product descriptions have at all times been an important ecommerce promoting software. However crafting distinctive and persuasive copy is difficult.
So virtually a decade in the past, I wrote what has develop into considered one of my favourite articles, “The way to ‘Manufacture’ Product Descriptions for Ecommerce.” The piece describes a composition course of and, finally, produces this description for a soup spoon:
Hungry for some hearty hen noodle or creamy clam chowder? This soup spoon has a big bowl meant to haul bisques and broths to your mouth. In actual fact, this soup spoon can maintain about 3 times as a lot soupy goodness as your customary desk spoon. You can take 3 times as many bites, or you would purchase this soup spoon and slurp massive.
Descriptions at Scale
I had been battling product descriptions on the web site of my employer, a regional brick-and-click farm-and-ranch retailer. We had hundreds of things needing descriptions for our ecommerce web site. I attempted three choices: Amazon’s Mechanical Turk, a Romanian product description company, and a template-based software.
Synthetic intelligence has made it straightforward to supply product descriptions in a mechanical or algorithmic approach, virtually like manufacturing.
Writers employed through the Turk or in Romania tended to strategy every description like a novel with a plot. Some descriptions had been wonderful, however not all. The unhealthy ones missed the purpose.
I then devised the product description “manufacturing” course of.
- Give attention to a single factor. The merchandise’s prime characteristic or aggressive benefit.
- Connect with a profit. Clarify how the characteristic helps the patron.
- Make clear and specify. Make the feature-and-benefit bridge exact and comprehensible.
- Take a look at your phrases. Take away redundancy, add motion verbs, and spark curiosity.
- Spell and grammar verify. Sloppy textual content erodes belief and harms conversions.
- Add an introduction. Polish, humanize, and insert a hook.
- Add a name to motion. Encourage the sale.
The method was a framework for writers and advertising and marketing groups.
Mad Libs
Sadly, the method took a number of time. So we doubled down on a tactic that I likened to enjoying “Mad Libs” — a template-based phrase sport — and wrote one other article, “Generate Product Descriptions with Pure Language Software program.”
Pure language templates had been forerunners to at the moment’s generative synthetic intelligence platforms. The templates used product-category variables to mass-produce copy.
A template for LED televisions would possibly appear like this:
{} {{ display dimension >= 55 ? {} “viewing”: “the reveals and flicks you like: }} from the consolation of your {} with this {{ display dimension }} {{ model }} {{ display kind }} tv.
That instance got here from Greatest Purchase:
Expertise cinema-like viewing from the consolation of your lounge with this 55-inch Insignia LED tv. It shows Blu-ray and high-definition motion pictures in full 1080p decision with gorgeous HD element. Use the three HDMI inputs to create a house theater expertise with this Insignia LED TV and your different audio and video gadgets.
Generative AI
I’ve used the “manufacturing” and natural-language processes on dozens of ecommerce websites.
However generative AI makes the duty simpler with higher outcomes — morphing from templates and pure language into immediate engineering.
Begin with Google’s five-step immediate engineering framework: Activity, Context, References, Consider, and Iterate.
Activity
Instruct the AI on what to do. Right here the goal is to supply a product description specializing in a single characteristic.
First, produce a template-like immediate:
Compose a compelling product description for [Product Name], specializing in the [Detailed Key Feature]. Describe how the [Short Key Feature] advantages clients, offering particular examples and comparisons.
The variables may very well be:
- [Product Name] – “a soup spoon.”
- [Detailed Key Feature] – “massive spoon bowl that holds soup.”
- [Short Key Feature] – “massive bowl.”
The immediate addresses two parts of my unique manufacturing course of: “deal with a single factor” and “hook up with a profit.”
Context
Generative AI is best with context. So to engineer our immediate, we as soon as once more “hook up with a profit” whereas including the “make clear and specify” step to incorporate our goal buyer.
Think about you’re an skilled copywriter engaged on product descriptions. Compose a compelling product description for [Product Name], specializing in the [Detailed Key Feature]. Describe how the [Short Key Feature] advantages clients, for instance, [Benefit Bridge], offering particular examples and comparisons.
Embrace a direct deal with name to motion, too. Be aware [Product Name] is for [Target Audience]. Use a [Brand Voice] tone. Guarantee the outline is partaking, grammatically right, and avoids repetition. Use a diversified, related, and significant vocabulary.
Our variables may very well be:
- [Benefit Bridge] – “so clients get extra soup with every chunk.”
- [Target Audience] – “anybody who likes soups and doesn’t wish to take tiny bites.”
- [Brand Voice] – “informal and enjoyable.”
I’ve built-in three steps from the unique course of: “take a look at your phrases,” “spell and grammar verify,” and “add a call-to-action.”
References
Subsequent, we are able to present the AI with examples of profitable, category-specific product descriptions.
The product description could also be comparable in model to those examples:
“[First Example]”
“[Optional Second Example]”
Craft three wonderful product descriptions.
Filling within the instance variables, we have now a accomplished immediate.
Think about you’re an skilled copywriter engaged on product descriptions.
Compose a compelling product description for a soup spoon, specializing in the massive bowl or head that enables it to carry soup. Describe how the massive bowl advantages clients — akin to “get extra soup with every chunk” — whereas offering examples and comparisons.
Embrace a direct name to motion.
Be aware {that a} soup spoon is for anybody who likes soups and doesn’t wish to take tiny bites. Once you write, use an informal and enjoyable tone. Guarantee the outline is partaking, grammatically right, and avoids repetition. Use a diversified, related, and significant vocabulary.
The product description could also be comparable in model to this instance:
Hungry for some hearty hen noodle or creamy clam chowder? This soup spoon has a big bowl meant to haul bisques and broths to your mouth. In actual fact, this soup spoon can maintain about 3 times as a lot soupy goodness as your customary desk spoon. You can take 3 times as many bites, or you would purchase this soup spoon and slurp massive.
Craft three wonderful product descriptions.
Consider
Even the very best AI prompts won’t at all times produce the specified outcomes, so consider the output. The instance immediate generated this response from ChatGPT 4o.
Uninterested in chasing soup round your bowl with a tiny spoon? Meet the soup spoon designed for actual soup lovers. Its beneficiant, deep bowl permits you to scoop up wealthy, velvety bisques, hearty stews, and soul-warming broths in satisfying mouthfuls — no extra dainty sips. In comparison with your common tablespoon, this unhealthy boy holds almost 3 times as a lot, so you may take pleasure in extra taste with each chunk. Whether or not you’re slurping ramen or savoring selfmade hen noodles, this spoon will get the job carried out. Go massive or go hungry — seize yours at the moment.
Iterate
The ultimate step in Google’s immediate engineering framework is to iterate or repeat the method with minor adjustments till you get the suitable response.
Product descriptions have by no means been extra essential for ecommerce success. How we produce and take a look at them displays their significance.
