You are helping me build the following AI agent workflow.

## Goal
Customer Feedback Analysis: Collects feedback from WhatsApp, email, and social media, analyzes sentiment with AI, and logs structured insights to Google Sheets.

## Specification
- What it does: You gather unstructured feedback from WhatsApp, email, and social media into organized insights automatically. The agent analyzes sentiment and extracts key themes using AI, then logs everything to Google Sheets for easy reporting. You can also trigger alerts or automated responses based on these analysis results without manual sorting.
- Trigger: Triggered by an event (Event · on new feedback or Scheduled · recurring surveys)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and automation logic
  - OpenAI: Sentiment analysis, topic extraction, and summarization
  - WhatsApp Business Cloud: Collecting conversational feedback from customers
  - Google Sheets: Storing and displaying structured analysis results

## Known pitfalls, handle each one explicitly in your implementation
1. WhatsApp message length limits can truncate long customer stories so implement a character limit check before sending to the LLM.
2. Inconsistent JSON output from the LLM will break the Google Sheets insertion so enforce strict schema validation and error handling nodes.
3. PII data like phone numbers may be sent to external APIs so add a masking step before the analysis node to ensure compliance.

## Reference implementation
https://n8n.io/workflows/4686 (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/automate-customer-feedback-analysis/ via usecasesforagents.com