You are helping me build the following AI agent workflow.

## Goal
Customer Feedback Analysis & Reporting: Analyzes unstructured customer feedback in Google Sheets with AI, generates visual charts, and emails a comprehensive HTML report.

## Specification
- What it does: Turn your unstructured customer feedback in Google Sheets into clear, actionable insights with AI-generated analysis and visual charts. You receive a ready-to-share HTML report via email that summarizes every row of data without manual effort.
- Trigger: Triggered by an event (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: a few focused days
- Tools/services involved:
  - Google Sheets: Importing raw feedback data
  - AI Agent: Generating analysis prompts and semantic clustering
  - OpenAI Chat Model: Executing row-level text analysis
  - QuickChart: Creating data visualizations
  - Gmail: Delivering final HTML report via email

## Known pitfalls, handle each one explicitly in your implementation
1. Large batches of rows may exceed token limits so split the input data into smaller chunks before sending to the LLM.
2. Inconsistent JSON formatting from the LLM can break the merge step so enforce strict output schemas in the prompt instructions.
3. QuickChart URLs have length restrictions so verify that the generated chart configuration does not exceed URL character limits.
4. Gmail API quotas can be hit quickly during testing so implement a delay between sending multiple report emails.

## Reference implementation
https://n8n.io/workflows/3642 (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-analysis-reporting/ via usecasesforagents.com