You are helping me build the following AI agent workflow.

## Goal
Prospecting Email Generation from CRM Data: Ask for a prospecting email to any contact in your CRM, and get a personalized draft based on their details.

## Specification
- What it does: Get a personalized prospecting email draft instantly by providing any contact from your CRM. The system pulls their specific details to generate a tailored message ready for you to review or send immediately.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: under an hour
- Tools/services involved:
  - LLM: Drafting prospecting email content
  - CRM: Retrieving contact information for prospects

## Known pitfalls, handle each one explicitly in your implementation
1. PII data leakage is a serious risk, so ensure all sensitive fields are masked before sending to the LLM.
2. Generic templates reduce response rates, so instruct the model to strictly use unique data points from the retrieved record.

## Reference implementation
https://www.youtube.com/watch?v=8AaFB7bnaTE (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/prospecting-email-generation-from-crm-data/ via usecasesforagents.com