What it does
Matches each PL client to its household record on street and ZIP, scores five rounding signals (multiple properties, out-of-state property, umbrella threshold, high-value home, income step-up), and returns a workbook of conversations with the reason for each and the library leave-behind.
What you get back
- Opportunities workbook ranked by signal score, with suggested conversation
- Unmatched tab showing where CRM address quality falls short
Example prompt
Add the skill to your AI client first, then paste this. Swap the bracketed bits, and the names and numbers, for your own.
Which of our personal lines clients should we be talking to about an umbrella or a second home?
Source: Written for this skill by the R&D AI Experience team.
These buttons try to pre-fill the prompt for you. Open Claude launches the Claude Desktop app (it won't work if you only use Claude in a browser); Open ChatGPT pre-fills the web chat when the browser allows it. Neither is guaranteed, so both also copy the prompt to your clipboard as a fallback -- if the tool opens with an empty box, paste. Connect the Zywave MCP in that tool first, or the prompt has no Zywave data to work with.
More prompts like this: Manage your book of business, 12 more from the Zywave MCP Prompt Library, filterable by line of business.
What it needs from you
Nothing from your client. Everything it needs is already in Zywave. Run it and review the output.
Details to fill in when you run it:
- Nothing. Optionally a state to narrow the book.
Every suggestion is “worth reviewing” because the CRM can’t see what’s already carried. Read-only.
Guides exist for Claude, Microsoft Copilot, ChatGPT, and Google Gemini Enterprise. Custom integrations talk to the MCP server directly, so start from the MCP Apps reference for those.