You are helping me build the following AI agent workflow.

## Goal
Lead Scoring and CRM Sync: New Mailchimp subscriber? The agent infers their professional details, scores the lead, syncs them to HubSpot and Pipedrive.

## Specification
- What it does: Get new Mailchimp subscribers instantly scored with inferred professional details like role and intent so you can focus on high-priority opportunities. The agent syncs these enriched leads to HubSpot and Pipedrive while automatically creating deals in Pipedrive for your top-scored prospects.
- Trigger: Triggered by an event (Event · on new Mailchimp subscriber)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Mailchimp: Capture new subscribers
  - OpenAI Chat Model: Enrich data and score leads
  - Code: Parse and merge enrichment data
  - HubSpot: Sync enriched lead records
  - Pipedrive: Create deals for high-value leads

## Known pitfalls, handle each one explicitly in your implementation
1. Incorrect field mapping causes silent data loss so verify the payload structure against each CRM's specific API documentation.

## Reference implementation
https://n8n.io/workflows/8909 (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/ai-lead-scoring-and-crm-sync/ via usecasesforagents.com