You are helping me build the following AI agent workflow.

## Goal
Phone Booking & CRM Updates: On new lead, it validates quality via LLM, makes an AI phone call to confirm the appointment.

## Specification
- What it does: You get instant appointment confirmations for new leads through an automated AI phone call that validates their quality first. The system then updates your CRM and sends personalized email notifications based on the conversation outcome.
- Trigger: Triggered by an event (Event · on new lead via webhook)
- Autonomy: Fully hands-off
- Expected setup effort: a few focused days
- Tools/services involved:
  - n8n: Workflow orchestration and automation logic
  - GoHighLevel: CRM management and appointment storage
  - VAPI.ai: Initiating automated phone calls for confirmation
  - OpenAI Chat Model: Lead validation and post-call analysis
  - Send Email: Sending confirmation or failure notifications

## Known pitfalls, handle each one explicitly in your implementation
1. VAPI.ai latency can cause awkward pauses in conversation, so optimize your prompt for concise responses to keep the flow natural.
2. GoHighLevel webhooks may fail silently if payload structures change, add error handling nodes to log and alert on failed triggers.

## Reference implementation
https://n8n.io/workflows/3759 (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-ai-phone-booking-crm-updates/ via usecasesforagents.com