You are helping me build the following AI agent workflow.

## Goal
Real Estate Deal Finder: Every four hours, this agent scans six Facebook real estate groups for deals matching your criteria and texts you the details immediately.

## Specification
- What it does: You receive instant SMS alerts with real estate deal details whenever new posts matching your criteria appear in six monitored Facebook groups. This agent scans these groups every four hours, uses AI to extract key property information, and filters results against your custom requirements before notifying you immediately.
- Trigger: On a schedule (Scheduled · every 4 hours)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - HTTP Request: Scraping Facebook group posts via RapidAPI
  - OpenAI Chat Model: Extracting deal details and classifying offers
  - Twilio: Sending SMS alerts for qualifying deals

## Known pitfalls, handle each one explicitly in your implementation
1. Facebook frequently changes its API access policies so you must implement a fallback scraping method if the official endpoint breaks.
2. Twilio SMS costs can accumulate quickly with high volume, add a daily budget cap to prevent unexpected charges.

## Reference implementation
https://n8n.io/workflows/15431 (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-real-estate-deal-finder/ via usecasesforagents.com