You are helping me build the following AI agent workflow.

## Goal
Generate Marketing Campaign ROI Reports: Pulls marketing campaign data from Google Sheets, analyzes performance with GPT-4o, and emails a structured ROI recap.

## Specification
- What it does: You get an automated email with a structured ROI recap that analyzes your marketing campaign data from Google Sheets using AI to summarize key performance metrics. This process pulls the raw numbers, interprets them, and delivers clear insights without you needing to manually review rows of data.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Sheets: Pull campaign data
  - OpenAI Chat Model: Summarize performance data
  - Code: Process logic within n8n

## Known pitfalls, handle each one explicitly in your implementation
1. Non-numeric values in metric columns will cause calculation errors, so add validation steps to skip or flag invalid rows before parsing.
2. Schema mismatches between your parser and the LLM output can crash the pipeline, so validate the JSON structure immediately after generation.

## Reference implementation
https://n8n.io/workflows/7586 (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/generate-marketing-campaign-roi-reports/ via usecasesforagents.com