You are helping me build the following AI agent workflow.

## Goal
Shopify Abandoned Cart WhatsApp Reminders: Every 5 minutes, the agent cleans pending WhatsApp numbers via Rapiwa, sends personalized cart reminders to valid contacts.

## Specification
- What it does: Recover abandoned Shopify carts by sending personalized WhatsApp reminders directly to your customers every 5 minutes. This process automatically cleans and verifies phone numbers using the Rapiwa API before delivering messages only to valid contacts, ensuring you reach real buyers without wasting time on invalid data.
- Trigger: On a schedule (Scheduled · every 5 minutes)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and automation logic
  - Google Sheets: Storing contact data, status tracking, and message templates
  - Rapiwa API: Sending WhatsApp messages via HTTP request

## Known pitfalls, handle each one explicitly in your implementation
1. WhatsApp message content must not contain prohibited promotional links or sensitive customer data so you avoid account bans.
2. Phone number formatting errors can cause Rapiwa validation to fail, add a normalization step before the HTTP request.

## Reference implementation
https://n8n.io/workflows/9031 (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-abandoned-cart-whatsapp-reminders/ via usecasesforagents.com