---
name: al-684-cut-insurance-visit-prep-from-hours-to-minutes-let-an-age
description: "Salesforce's Nov 5, 2026 Aflac Japan story covers agentic proposal preparation with Agentforce for about 113,000 insurance agency representatives. Reps previously spent hours gathering history and policy details across disconnected systems before and after visits. The agent suggests icebreakers, product recommendations and talking points, helps with policy illustrations, suggests efficient travel routes, then drafts meeting summaries, logs engagement, prepares thank-you emails and suggests next best actions—all in Japanese. Leadership frames it as a response to Japan's shrinking labour force so newcomers can propose like veterans, with permissions and Trust Layer masking so contract detail access stays role-scoped. Use when the user wants help with agentic insurance proposal prep for agency reps (sales) for a small business."
---

# Cut insurance visit prep from hours to minutes: let an agent pull customer history, recommend products, draft icebreakers and log the follow-up so new reps propose like veterans

Salesforce's Nov 5, 2026 Aflac Japan story covers agentic proposal preparation with Agentforce for about 113,000 insurance agency representatives. Reps previously spent hours gathering history and policy details across disconnected systems before and after visits. The agent suggests icebreakers, product recommendations and talking points, helps with policy illustrations, suggests efficient travel routes, then drafts meeting summaries, logs engagement, prepares thank-you emails and suggests next best actions—all in Japanese. Leadership frames it as a response to Japan's shrinking labour force so newcomers can propose like veterans, with permissions and Trust Layer masking so contract detail access stays role-scoped.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Insurance / financial advisory
- Japanese / English / other
- CRM, policy admin, past visits
- Language
- Your own material (text, notes or data)

## Instructions

Do the task below with the user's inputs in place of each [bracket].

Build an agentic visit-prep workflow for [insurance / financial advisory] reps. Products: [list]. Languages: [Japanese / English / other]. Data sources: [CRM, policy admin, past visits]. Hard rules: mask sensitive fields before any external model call; enforce role-based access to contract details; never auto-send customer email—draft only; log every recommendation for audit. 1) Checklist for pre-visit (icebreaker, needs hypothesis, product shortlist, illustration inputs, travel). 2) Post-visit automation (summary, thank-you, next action). 3) Draft the agent system prompt in [language] plus English. 4) Define a 2-week pilot with 10 reps and success metrics (prep time, proposals per week, new-rep close rate). Output a playbook I can paste into our Agent Builder.

## Safety checks (share these with the user)

- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records.
- Anything legal, tax or compliance-related is a first draft for a qualified person to check. It is not professional advice, and clause references and deadlines must be checked against the source.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Salesforce Agentforce, Financial Services Cloud, Experience Cloud, Data 360, ChatGPT, Claude
- Based on this real-world example: https://www.salesforce.com/customer-stories/aflac/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-684-cut-insurance-visit-prep-from-hours-to-minutes-let-an-agent/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/