You are helping me build the following AI agent workflow.

## Goal
Shopify Order Fulfillment: Automatically marks unfulfilled Shopify orders as fulfilled by resolving Fulfillment Order IDs and handling edge cases.

## Specification
- What it does: You save time on order management by automatically marking your unfulfilled Shopify orders as completed. The agent resolves the necessary Fulfillment Order IDs and handles edge cases like partial fulfillments or API errors to ensure every valid order is processed efficiently without manual intervention.
- Trigger: Run manually (Manual · on demand or Scheduled)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Shopify: Retrieve unfulfilled orders and mark as fulfilled
  - HTTP Request: Handle API requests for fulfillment order IDs

## Known pitfalls, handle each one explicitly in your implementation
1. Partial fulfillments require careful state management because marking an order as fully fulfilled when only some items are ready will cause API errors.
2. The fulfillment_order_id is mandatory for the modern API so omitting it will result in a 400 Bad Request error instead of using legacy methods.

## Reference implementation
https://n8n.io/workflows/3296 (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/automatic-shopify-order-fulfillment/ via usecasesforagents.com