You are helping me build the following AI agent workflow.

## Goal
E-commerce Customer Support Chatbot: Instantly answers e-commerce queries by checking order status in Supabase and generating personalized product recommendations via OpenAI.

## Specification
- What it does: Get instant answers to your e-commerce questions as the agent checks your order status in Supabase and suggests personalized products powered by OpenAI. It handles support tickets automatically while keeping track of your conversation history for smooth follow-ups, delivering real-time replies that reduce wait times and improve satisfaction.
- Trigger: Triggered by an event (Event · on customer inquiry via webhook or email)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and automation logic
  - OpenAI Chat Model: Generating AI responses and product recommendations
  - Supabase: Storing order details and customer data
  - Webhooks: Receiving real-time customer inquiries

## Known pitfalls, handle each one explicitly in your implementation
1. Context window limits can truncate conversation history during long threads, so implement a sliding window strategy in Simple Memory to keep only recent turns.

## Reference implementation
https://n8n.io/workflows/7256 (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/e-commerce-customer-support-chatbot/ via usecasesforagents.com