You are helping me build the following AI agent workflow.

## Goal
YouTube SEO Optimization Automation: Pulls YouTube URLs from a sheet, uses AI to generate three SEO titles and one conversion description, then updates the row with new assets.

## Specification
- What it does: Get ready-to-publish YouTube content by having this automation pull your video URLs from Google Sheets and generate three SEO-optimized titles plus a conversion-focused description using AI. It then updates your sheet with these new assets so you can publish immediately without manual editing.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Sheets: Store video URLs and optimization data
  - HTTP Request: Fetch current YouTube metadata
  - Code: Process and format data between steps
  - DeepSeek Chat Model: Generate SEO optimized titles and descriptions

## Known pitfalls, handle each one explicitly in your implementation
1. The HTTP request might fail if the video is private or deleted, so add error handling to skip invalid URLs and log them for manual review.
2. Google Sheets API quotas can be exceeded with frequent updates, so batch write operations instead of updating row-by-row in a loop.

## Reference implementation
https://n8n.io/workflows/5229 (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/youtube-seo-optimization-automation/ via usecasesforagents.com