Skip to main content
Back to challenges
Challenge

Hybrid AI Agent Assistant for Commercial Insurance Broker Workflows

Will AI end traditional insurance agents or empower them? Build a CrewAI agent assistant system that augments commercial brokers by handling complex policy comparison, client risk profiling, and coverage appetite matching in under 30 seconds.

Machine LearningHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a CrewAI commercial broker assistant agent system for rapid client risk profiling and policy market matching.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of carrier market matching and quote comparison generation.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

carrier_match_non_empty

Ensures at least one carrier match is returned

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

market_match_accuracy

Accuracy in matching carrier appetite guidelines • target: 0.92 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Build a multi-agent CrewAI team representing Client Intake, Carrier Appetite Matcher, and Proposal Writer

  • Ingest commercial client questionnaires and retrieve carrier appetite rules

  • Output side-by-side proposal coverage comparisons automatically

  • Evaluate broker productivity uplift and quote generation turnaround time

Resources and assets

Reference links and supporting material

Dataset notes

Commercial contractor profile submissions and carrier underwriting appetite guides.

Challenge setup

Evaluates accuracy of carrier market matching and quote comparison generation.

Challenge input

JSON with client_business_type, annual_revenue, and location_state.

CrewAI

Role-playing workflow orchestration

Evaluated output

JSON containing top_carrier_matches list and policy_comparison_table.

Evaluation checks
  • Ensures at least one carrier match is returned
  • Accuracy in matching carrier appetite guidelines • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: BrokerAppetiteBench
  • Market Match Accuracy target: 0.92
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional
  • Vast.ai · Optional

Evaluation contract

  • carrier_match_non_empty · Weight 1
  • market_match_accuracy · Weight 1

Metrics

  • market_match_accuracy · Target 0.92

Benchmarks

  • BrokerAppetiteBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with client_business_type, annual_revenue, and location_state.

    Output: JSON containing top_carrier_matches list and policy_comparison_table.

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Hybrid AI Agent Assistant for Commercial Insurance Broker Workflows