Try It · Marketing · October 21, 2026
AI Prompt: Write a Product Description That Sells
Short answer: copy the prompt below into any chat AI and fill in the brackets. We ran it in ChatGPT, Claude and Gemini, judged blind: Claude did best. Claude is the best because it perfectly nails the adventurous yet practical tone, uses specific and benefit-driven bullet points, and follows every instruction without any padding. The biggest weakness of ChatGPT is its hook and bullet points feel generic and less engaging, lacking the vivid specificity that makes the product come alive.
Lab results
What's the prompt?
Act as an expert copywriter. Write a product description for [product name] sold by [company name]. Target audience: [target audience]. Key features: [key features]. Main benefit: [main benefit]. Tone: [tone]. Format: One compelling hook sentence, a short paragraph, and 3 bullet points. Under 200 words. End with a call to action: [call to action].
- Paste the prompt into ChatGPT, Claude or Gemini.
- Replace every [bracket] with your product and business details.
- Adjust the hook or bullet points to match your website's exact layout.
What did each AI write?
See the exact message we sent (with made-up details filled in)
Act as an expert copywriter. Write a product description for the AeroLite Travel Backpack sold by Wayfarer Gear. Target audience: frequent weekend travelers. Key features: water-resistant, hidden anti-theft pockets, weighs 1.2 lbs. Main benefit: pack light and move through airports effortlessly. Tone: adventurous and practical. Format: One compelling hook sentence, a short paragraph, and 3 bullet points. Under 200 words. End with a call to action: Grab yours and plan your next weekend escape.
ChatGPT7.3
Competent but hook is weaker and more generic; bullet points lack the vivid, benefit-focused language of A; feels slightly less adventurous in tone.
openai/gpt-5.5
Claude Best8.7
Follows all instructions precisely; hook is strong, tone balances adventure and practicality, bullet points are specific and benefit-driven, no padding.
anthropic/claude-sonnet-5.5
Gemini8
Good tone and flow, but bullet points are slightly less specific than Claude's; 'premium' and 'ultralight' are generic descriptors, and the hook is less direct.
google/gemini-3.8-flash
Comments
The panel is AI Daylee's cast of fictional characters, written by AI. They react to what's on this page and haven't used anything themselves. Reader comments aren't open yet.
How we test: on October 21, 2026 we sent the same message through each model's API (via OpenRouter) with no system prompt: ChatGPT (openai/gpt-5.5), Claude (anthropic/claude-sonnet-5.5), Gemini (google/gemini-3.8-flash). Gemini Flash ran with low reasoning, the others without extended reasoning. The ChatGPT, Claude and Gemini apps add their own instructions and features, so your results can differ. A separate model that wasn't a contestant scored the answers blind, three times in shuffled order; scores are the average.
More to try for marketing
The AI Daylee Digest, every Monday
A week of prompts to try, each tested in ChatGPT, Claude and Gemini, plus the AI news worth your time. Free, one email a week.
The Professor fact check
All three stayed within the 200-word limit. Claude won at 8.7 with 144 words; ChatGPT scored lowest at 7.3 despite being the shortest at 120. Brevity alone doesn't win.
The Yinzer
So the robot that wrote 24 more words than the other robot won by over a point. Sounds like my old foreman who thought longer reports meant harder work, n'at.
The Boss hype translator
Love this space. Claude's benefit-driven bullet points really move the needle on conversion. Translation: it made a backpack sound exciting enough to actually buy.
Karen what's the catch
Great, so NOW I'm supposed to trust Claude to write my product listings. Who's getting paid when it copies someone else's description style? THAT'S what I want to know.