Skip to main content
Back to challenges
Challenge

Build a Credit Risk Underwriting Agent with LangChain & LangGraph

Managing over $589m in export credit limits requires precise counterparty default risk scoring. Build an automated trade credit evaluation agent using LangChain and LangGraph to analyze balance sheets, geopolitical trade risk, and issue credit decisions.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Utilize LangGraph stateful graph workflows to process Omani export credit applications and verify buyer financial health.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of default risk scoring and compliance with max credit exposure caps.

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

decision_check

Verify approval decision matches financial health thresholds

Binary check

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

Dimension 2

underwriting_precision

Accuracy of financial ratio calculations and credit limit decisions • target: 0.98 • range: 0.9-1

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

  • Construct multi-stage LangGraph graphs for financial statement analysis

  • Implement credit scoring tools based on Credit Oman underwriting guidelines

  • Evaluate regional buyer default probabilities using historical macro trade signals

  • Generate export credit insurance approval recommendations automatically

Resources and assets

Reference links and supporting material

Dataset notes

Export credit insurance applications, buyer financial audits, and regional trade payment default logs.

Challenge setup

Evaluates accuracy of default risk scoring and compliance with max credit exposure caps.

Challenge input

JSON containing buyer financials

LangChain

Provides LangGraph for stateful financial graph modeling

Evaluated output

JSON underwriting decision

Evaluation checks
  • Verify approval decision matches financial health thresholds
  • Accuracy of financial ratio calculations and credit limit decisions • target: 0.98 • range: 0.9-1
Configured evaluation evidence
  • Benchmark: CreditRiskBench
  • Underwriting Precision target: 0.98
  • 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
  • LangChain · Required
  • LangGraph · Optional
  • Arcee AI · Optional
Orchestration
  • LangChain · Required
  • LangGraph · Optional

Evaluation contract

  • decision_check · Weight 1
  • underwriting_precision · Weight 1

Metrics

  • underwriting_precision · Target 0.98

Benchmarks

  • CreditRiskBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing buyer financials

    Output: JSON underwriting decision

    Execution harness: Python

Evaluation tools

  • LangChain · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Credit Risk Underwriting Agent with LangChain & LangGraph