You are helping me build the following AI agent workflow.

## Goal
Customer Feedback Triage: New Jotform feedback is triaged instantly: urgent alerts for negative sentiment, auto-replies to questions via Gmail.

## Specification
- What it does: You get instant urgent alerts via Telegram when customers leave negative feedback so you can act immediately. Your team receives automatic replies to customer questions pulled from your Google Sheets database right through Gmail. All suggestions are summarized and logged into a structured backlog in Google Sheets for easy reporting.
- Trigger: Triggered by an event (Event · on new Jotform submission)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Jotform: Collecting feedback submissions
  - Google Gemini Chat Model: Classifying sentiment and intent
  - AI Agent: Answering questions using Q&A database
  - Gmail: Sending automated replies to users
  - Google Sheets: Storing backlog and Q&A data

## Known pitfalls, handle each one explicitly in your implementation
1. Jotform webhook payloads may include hidden fields or attachments that confuse simple parsers, so explicitly filter for only the text-based feedback fields.
2. Sentiment analysis can misclassify sarcastic comments as positive, add a rule to flag low-confidence scores for manual review.

## Reference implementation
https://n8n.io/workflows/9636 (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-customer-feedback-triage/ via usecasesforagents.com