You are helping me build the following AI agent workflow.

## Goal
Google Maps Lead Scraping And Outreach: Submit a location and keyword to scrape Google Maps leads, generate personalized cold call scripts via AI, and store everything in Supabase.

## Specification
- What it does: Submit your location and keyword to instantly find businesses on Google Maps, receive AI-generated cold call scripts tailored to each lead, and have all results saved securely in your database.
- Trigger: Run manually (Manual · on form submission)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Bright Data: Scraping Google Maps data
  - LLM: Generating personalized cold call scripts
  - Supabase: Storing enriched leads and scripts

## Known pitfalls, handle each one explicitly in your implementation
1. Google Maps data often contains missing phone numbers so implement a fallback strategy like email extraction or manual review.
2. LLM outputs may vary in format so enforce strict JSON schema validation before storing results in Supabase.
3. Personalization quality drops if the scraped data lacks details like business description so filter out incomplete leads early.

## Reference implementation
https://n8n.io/workflows/6993 (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/google-maps-lead-scraping-and-outreach/ via usecasesforagents.com