You are helping me build the following AI agent workflow.

## Goal
Shopify Product Image Generation: New product in Shopify? The agent writes an optimized image prompt via deAPI and uploads styled hero and transparent PNGs to your catalog.

## Specification
- What it does: Get professional product images for your new Shopify items without manual design work. This agent automatically creates optimized prompts via deAPI to generate styled hero images and transparent PNGs, then uploads them directly to your catalog.
- Trigger: Triggered by an event (Event · on new product creation in Shopify)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Shopify: Trigger and update product images
  - Anthropic Chat Model: Generate optimized image prompts
  - deAPI: Image generation and background removal

## Known pitfalls, handle each one explicitly in your implementation
1. Product titles may contain special characters that break API payloads, so sanitize input strings before passing them to the image generator.
2. AI-generated images often fail to maintain brand consistency, implement a human-in-the-loop approval step for new product categories.

## Reference implementation
https://n8n.io/workflows/13704 (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/automate-shopify-product-image-generation/ via usecasesforagents.com