← Back to directory
E-commerce Involved to set up AI workflow Repurpose/Transform

Shopify Product Description Generator

Source reviewed Updated 2026-07-07

Automatically generates SEO-aware product descriptions from images and updates daily sales analytics in Google Sheets.

What it does

Get SEO-optimized product descriptions for your Shopify store automatically by having the agent analyze images with GPT-4o Vision and write concise marketing copy using Claude 3.5 Sonnet. You will also see daily sales analytics tracked in Google Sheets while the system handles large catalogs and maintains a clear audit trail of all updates.

Step by step

  1. Configure the HTTP Request tool to paginate through Shopify's product API using cursor-based pagination for large catalogs.
  2. Set up a Google Sheet with fixed columns for Product ID, SKU, Generated Description, and Timestamp to serve as the audit trail.
  3. Define the JSON schema for the final output to ensure consistent formatting when writing back to the spreadsheet.

Where the LLM does the work

  • Prompt GPT-4o Vision to extract specific visual attributes like color, material, and fit from product images without hallucinating details.
  • Use Claude 3.5 Sonnet to transform extracted attributes into SEO-optimized marketing copy that matches the brand's tone of voice.
  • Instruct the LLM to incorporate relevant keywords naturally while maintaining a concise length suitable for mobile shoppers.

Watch out for

Vision models may misinterpret dark or low-resolution images so you must add error handling to skip unclear products rather than generating bad copy.
SEO keywords might conflict with brand guidelines if not explicitly defined in the system prompt, so include a negative constraint list for banned terms.
Google Sheets has row limits that can crash the script over time, so archive old entries or split the sheet by month to maintain performance.

Tools that fit

OpenAI LLM Vision analysis of product images to extract visible attributes
OpenRouter Chat Model LLM Generating SEO-aware copy using Claude 3.5 Sonnet
HTTP Request API Fetching product data and sales orders from Shopify API
Google Sheets Service Orchestrating workflow state, staging data, and logging analytics

The agent brief

Everything your agent needs, including the gotchas. Copy it and go.
agent-brief.md
You are helping me build the following AI agent workflow.

## Goal
Shopify Product Description Generator: Automatically generates SEO-aware product descriptions from images and updates daily sales analytics in Google Sheets.

## Specification
- What it does: Get SEO-optimized product descriptions for your Shopify store automatically by having the agent analyze images with GPT-4o Vision and write concise marketing copy using Claude 3.5 Sonnet. You will also see daily sales analytics tracked in Google Sheets while the system handles large catalogs and maintains a clear audit trail of all updates.
- Trigger: On a schedule (Scheduled ยท every 5 minutes and daily at 2:01 PM)
- Autonomy: Fully hands-off
- Expected setup effort: a few focused days
- Tools/services involved:
  - OpenAI: Vision analysis of product images to extract visible attributes
  - OpenRouter Chat Model: Generating SEO-aware copy using Claude 3.5 Sonnet
  - HTTP Request: Fetching product data and sales orders from Shopify API
  - Google Sheets: Orchestrating workflow state, staging data, and logging analytics

## Known pitfalls, handle each one explicitly in your implementation
1. Vision models may misinterpret dark or low-resolution images so you must add error handling to skip unclear products rather than generating bad copy.
2. SEO keywords might conflict with brand guidelines if not explicitly defined in the system prompt, so include a negative constraint list for banned terms.
3. Google Sheets has row limits that can crash the script over time, so archive old entries or split the sheet by month to maintain performance.

## Reference implementation
https://n8n.io/workflows/8562 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/automated-shopify-product-description-generator/ via usecasesforagents.com

Frequently asked questions

Can I use a different LLM than OpenAI?

Yes. OpenAI is only the example LLM in this recipe. The same flow works with Anthropic, Cohere, DeepSeek and Google Gemini. Swap the LLM connection and keep the rest of the setup as written.

Want this running in your business?

This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Get in touch →

Who it's for

Also fits E-commerce Operator.

Seen in the wild

← Back to directory