You are helping me build the following AI agent workflow.

## Goal
Return Pickup Reminders: Daily automation that identifies today's pending e-commerce returns and sends personalized WhatsApp messages or voice calls to customers...

## Specification
- What it does: You receive timely, personalized WhatsApp messages or voice calls reminding you of your pending e-commerce return pickup without manual follow-up. The system automatically checks your daily schedule in Google Sheets, delivers the reminder via Twilio, and updates your status to prevent duplicate notifications.
- Trigger: On a schedule (Scheduled · daily)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Sheets: Store pickup data and track status
  - Twilio: Send WhatsApp messages and voice calls
  - Code: Generate personalized message content

## Known pitfalls, handle each one explicitly in your implementation
1. Phone numbers need E.164 formatting or Twilio will reject the message delivery request.
2. Google Sheets row updates can fail if multiple instances run simultaneously, so add a lock mechanism.
3. Voice calls may incur higher costs than WhatsApp messages, so set a budget alert in your Twilio console.

## Reference implementation
https://n8n.io/workflows/12148 (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-return-pickup-reminders/ via usecasesforagents.com