AI-generated product descriptions

​

Setting up product Collections

• Title - Product name
• Description - Main product description (WYSIWYG for AI enhancement)
• Price - Product pricing
• Features - Key product features (Repeater field)
• Short description - Brief summary for listings

​

Using the AI assistant for product descriptions

• Open the AI Assistant dialog and generate a description from the product details you type in
• Select an existing description and run the Optimize product description shortcut, which rewrites it around the features customers value most
• Select a description and run A/B Testing & Variation Creation to get three variations
• Use Change tone or a custom shortcut to rewrite for a different audience

​

Effective prompt strategies

​

RACE framework for product descriptions

• Role: “You are an expert e-commerce copywriter specializing in [industry]”
• Action: “Write a compelling product description”
• Context: Provide product details, target audience, and brand voice
• Expectation: “The description should be 150-200 words, highlight key benefits, and include a call-to-action”

​

Example prompts for different product types

​

Scaling product description generation

​

Catalog workflow

1. Prepare Product Data
   • Export product information (name, category, features, specs)
   • Organize by category for consistent prompts
2. Create Category-Specific Prompts
   • Develop template prompts for each product category
   • Include brand voice guidelines and SEO keywords
   • Save them as shortcuts under Settings > Integrations > AI Assistant so the whole team uses the same wording
3. Generate Initial Descriptions
   • In the editor, open each product and run the category shortcut on the description field
   • Outside the editor, call your AI provider from a script and write the results back with the Write API
4. Human Review & Refinement
   • Review AI-generated content for accuracy
   • Adjust for brand voice consistency
   • Add unique selling points
5. Publish & Monitor
   • Track performance metrics (conversion rates, bounce rates)
   • Iterate on prompts based on results

​

Using the Write API for automation

const axios = require('axios');

// The JS SDK only reads content; writes go through the REST API directly.
// Example: Update product description via Write API
async function updateProductDescription(productSlug, newDescription) {
  try {
    await axios.patch(
      `https://api.buttercms.com/v2/pages/product/${productSlug}/`,
      {
        // 'draft' saves the change for review (also the default when status is
        // omitted); 'published' makes it live immediately
        status: 'draft',
        fields: { description: newDescription }
      },
      {
        headers: {
          'Authorization': `Token <your-write-api-token>`,
          'Content-Type': 'application/json'
        }
      }
    );
    console.log('Product description update accepted');
  } catch (error) {
    console.error('Error updating product:', error);
  }
}

​

Best practices for AI product descriptions

​

Do’s

​

Don’ts

​

Personalizing descriptions for different audiences

• Segment Name - Customer grouping from your CRM or CDP
• Product Recommendations - Reference to relevant products
• Description Variant - Tailored description for this segment