You are helping me build the following AI agent workflow.

## Goal
Competitor Deal Monitoring & Email Marketing: Scans competitor deals daily, segments customers via AI, and sends personalized coupon emails with performance tracking.

## Specification
- What it does: Stay ahead of competitor pricing by automatically scanning their deals daily so you can instantly segment your customers with AI and send them personalized coupon emails that drive sales. You also gain full visibility into campaign performance through tracked analytics to refine your strategy continuously.
- Trigger: On a schedule (Scheduled · daily)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - HTTP Request: Scanning competitor websites for deals
  - Code: AI segmentation and offer generation logic

## Known pitfalls, handle each one explicitly in your implementation
1. Competitor websites often change their HTML structure which breaks parsing, so add error handling to alert you when selectors fail.
2. Email providers may flag bulk automated sends as spam, so warm up your sending domain and include a clear unsubscribe link in every message.
3. Scraping too frequently can trigger IP blocks on competitor sites, so implement random delays between requests to stay under the radar.

## Reference implementation
https://n8n.io/workflows/6975 (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/automated-competitor-deal-monitoring-email-marketing/ via usecasesforagents.com