You are helping me build the following AI agent workflow.

## Goal
Qualify Insurance Leads via WhatsApp: Inbound WhatsApp insurance inquiries are qualified via conversational AI.

## Specification
- What it does: Capture and qualify inbound insurance leads directly on WhatsApp while they speak their native language. You get structured lead scores and intent data automatically synced to HubSpot without manual entry. The system instantly alerts your team via Slack whenever a lead requests human assistance.
- Trigger: Triggered by an event (Event · on new WhatsApp message)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - WhatsApp Business Cloud: Inbound lead communication trigger and reply
  - OpenAI Chat Model: Conversational AI and data extraction
  - HubSpot: Storing qualified lead records
  - Slack: Alerting sales team for human handover

## Known pitfalls, handle each one explicitly in your implementation
1. WhatsApp message history can grow large quickly so implement a sliding window strategy to manage token costs and context limits.
2. Slack alerts can become noisy during peak times so batch multiple escalation requests into a single summary message.

## Reference implementation
https://n8n.io/workflows/16007 (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/qualify-insurance-leads-via-whatsapp/ via usecasesforagents.com