You are helping me build the following AI agent workflow.

## Goal
New Customer Onboarding: On new customer signup, the agent schedules a welcome meeting, generates a personalized HTML email via Gmail.

## Specification
- What it does: You get a scheduled welcome meeting and a personalized email immediately after signing up. The system automatically pulls your owner details from HubSpot, uses AI to set up the meeting and craft the message via Gmail, then assigns you for tracking.
- Trigger: Triggered by an event (Event · on new contact in HubSpot or webhook)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - HubSpot: Retrieve owners and assign customer contacts
  - OpenAI Chat Model: Generate personalized welcome email text
  - Gmail: Send the formatted HTML welcome email
  - AI Agent: Schedule welcome meetings in calendar tools

## Known pitfalls, handle each one explicitly in your implementation
1. OpenAI might generate malformed HTML tags, validate the output structure before passing it to the Gmail send node.
2. Calendar conflicts can cause scheduling errors, add error handling to retry with alternative time slots if the first attempt fails.

## Reference implementation
https://n8n.io/workflows/3958 (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/automate-new-customer-onboarding/ via usecasesforagents.com