You are helping me build the following AI agent workflow.

## Goal
Monitor Brand Sentiment on Facebook Groups: Periodically scans specified Facebook groups for brand mentions using Bright Data and classifies sentiment via LLM.

## Specification
- What it does: You stay on top of your brand's reputation in Facebook groups with automated checks that scan posts using Bright Data and classify sentiment as positive, negative, or neutral via an LLM. The results are automatically saved to Google Sheets so you can review them anytime without manual searching.
- Trigger: On a schedule (Scheduled · daily)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Bright Data: Scraping Facebook group posts
  - HTTP Request: Sending data to external webhook
  - OpenRouter Chat Model: Sentiment analysis and information extraction
  - Google Sheets: Storing sentiment results for analysis

## Known pitfalls, handle each one explicitly in your implementation
1. Bright Data may return incomplete data if Facebook changes its anti-bot measures, so implement a retry mechanism with logging.
2. Facebook group privacy settings may block scraping if the user is not a member, so verify access permissions before running the scraper.

## Reference implementation
https://n8n.io/workflows/4235 (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/monitor-brand-sentiment-on-facebook-groups/ via usecasesforagents.com