You are helping me build the following AI agent workflow.

## Goal
Facebook Comment Sentiment Analysis: Fetches comments from a Facebook post, analyzes sentiment with Gemini, and updates a Google Sheet without duplicates.

## Specification
- What it does: You automatically gather comments from your Facebook posts, analyze their sentiment using AI, and save the results to a Google Sheet without duplicates. This workflow handles pagination seamlessly so you can run it manually for testing or trigger it as part of your automation pipeline.
- Trigger: Run manually (Manual · on demand or Scheduled)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Facebook Graph API: Fetching post comments
  - Google Gemini Chat Model: Sentiment classification
  - Google Sheets: Storing analysis results

## Known pitfalls, handle each one explicitly in your implementation
1. Sentiment models often misinterpret sarcasm or context-heavy comments, so add a low-confidence flag column for manual review later.

## Reference implementation
https://n8n.io/workflows/13234 (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/facebook-comment-sentiment-analysis/ via usecasesforagents.com