You are helping me build the following AI agent workflow.

## Goal
Website On-Page SEO Audit: Paste a URL and get a deep technical SEO audit with 10 specific recommendations emailed to you.

## Specification
- What it does: Paste any website URL to instantly receive an email with ten specific technical SEO recommendations designed to boost your search rankings. The system analyzes the site's code using AI to identify key issues and delivers a clear action plan directly to your inbox.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - HTTP Request: Scrape URL HTML source code
  - OpenAI Chat Model: Analyze SEO and generate recommendations
  - Gmail: Send audit results email

## Known pitfalls, handle each one explicitly in your implementation
1. The scraped HTML might be dynamically rendered by JavaScript so you need to use a headless browser or API that supports JS execution to get full content.
2. Email providers often flag automated messages as spam so ensure you authenticate your Gmail account with SPF and DKIM records.
3. Large HTML payloads can exceed token limits so implement a strategy to truncate or summarize the source before sending it to the model.

## Reference implementation
https://n8n.io/workflows/3224 (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/website-on-page-seo-audit/ via usecasesforagents.com