Building an AI Workforce for Insurance with n8n, OpenAI, LangGraph and Supabase

AI for Preparation. Humans for Judgment.

Most AI projects today are one of these:

• A chatbot
• A customer support bot
• A voice assistant
• A Q&A system

But I wanted to explore something bigger:

What if businesses could build an AI Workforce?

Instead of one AI assistant,

imagine:

Customer

↓

AI Workforce

├── Discovery Agent

├── Research Agent

├── Policy Comparison Agent

├── Recommendation Agent

├── CRM Agent

└── Follow-up Agent

↓

Human Advisor

↓

Customer

This article explains the architecture and design decisions behind such a system.

Why Insurance?

Insurance is an interesting industry for AI.

Because:

• Research is repetitive.
• Recommendations are data-driven.
• Follow-ups are expensive.
• Trust is critical.
• Human judgment is still necessary.

This makes Insurance a perfect Human-in-the-Loop AI use case.

Human In The Loop

This is the core philosophy.

I don't want AI to automatically sell insurance.

I don't want AI replacing advisors.

I want:

AI prepares.

Humans decide.

The workflow becomes:

Customer

↓

AI Workforce

↓

Human Advisor Review

↓

Customer

This creates:

• Faster recommendations
• Better customer experience
• Safer AI adoption
• Human accountability

AI Workforce Architecture

Customer

↓

WhatsApp
Phone Call
Website Chat
Email

↓

AI Workforce

├── Discovery Agent

├── Research Agent

├── Comparison Agent

├── Recommendation Agent

├── CRM Agent

└── Follow-up Agent

↓

Human Advisor

↓

Customer

Discovery Agent

The Discovery Agent understands the customer.

Responsibilities:

• Collect customer profile
• Understand goals
• Assess risk
• Understand existing insurance
• Identify gaps

Example Output:

{
  "risk_level":"medium",
  "family_type":"married_with_children",
  "insurance_goal":"health_and_term",
  "recommended_health_cover":"20L",
  "recommended_term_cover":"3Cr"
}

Research Agent

The Research Agent acts like an insurance analyst.

Responsibilities:

• Analyze policies
• Compare waiting periods
• Review exclusions
• Evaluate premiums
• Generate recommendations

Example:

{
  "customer_profile_summary":"...",
  "top_recommendations":[
      "...",
      "...",
      "..."
  ],
  "risks":[
      "...",
      "..."
  ],
  "confidence_score":0.92
}

Comparison Agent

Creates structured comparisons:

Output:

• Best Overall
• Best Budget
• Best Family Plan

Recommendation Agent

Creates:

• Customer Summary
• Recommended Plan
• Alternatives
• Risk Analysis
• Advisor Notes

Everything before the advisor joins.

CRM Agent

Updates:

• Customer Records
• Recommendations
• Activities
• Opportunity Status
• Tasks

Follow-up Agent

Handles:

• WhatsApp reminders
• Renewal alerts
• Email follow-ups
• Call notes
• Engagement tracking

Omnichannel AI

One important decision:

Customers should not install a new application.

The AI Workforce should operate through:

• WhatsApp
• Phone Calls
• Website Chat
• Email
• SMS

Different channels.

Same intelligence.

Technology Stack

Frontend

• Next.js
• Tailwind
• Lovable AI

Workflow Layer

• n8n

AI Models

• OpenAI
• Gemini
• Claude

Multi-Agent Framework

• LangGraph

Database

• Supabase
• PostgreSQL

Memory

• Pinecone

Monitoring

• LangSmith
• PostHog

Why n8n First?

I intentionally started with n8n.

Because:

• Fast prototyping
• Visual workflows
• Easy OpenAI integration
• Easy Supabase integration
• Easy WhatsApp integration
• Easy Email workflows

After validation:

n8n

↓

NestJS

↓

LangGraph

↓

Production AI Workforce

The Bigger Vision

I don't think AI will replace Insurance Advisors.

I think every advisor may eventually have:

An AI Workforce working behind the scenes.

AI provides:

• Speed
• Consistency
• Scale

Humans provide:

• Trust
• Empathy
• Judgment

The future is not:

Human vs AI

The future is:

Human + AI Workforce

If you're building something similar, I'd love to hear your thoughts.