AutoGen MSME Credit Risk Underwriting Agent
Non-banking financial institutions (NBFCs) require automated multi-agent risk assessment for underwriting under-served MSME loans. You will create a multi-agent conversational loop that parses Account Aggregator statements, GST returns, and field audit notes to issue automated credit recommendations.
What you are building
The core problem, expected build, and operating context for this challenge.
Build an AutoGen multi-agent system where auditor, tax analyst, and risk assessment agents collaboratively evaluate MSME creditworthiness from DPI data sources.
How work is evaluated
Evaluates multi-agent conversation consensus and credit limit generation accuracy.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Over-Leverage Protection Test
Must reject loans exceeding 3x annual GST turnover
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Consensus Quality Score
Rigor of multi-agent validation discussion steps • target: 0.95 • range: 0.85-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build conversational multi-agent groups using AutoGen AssistantAgent and UserProxyAgent
Implement structured dialogue loops between specialized financial roles
Process Account Aggregator banking transaction trends for cashflow verification
Compute automated credit score bounds and sanction limits for small businesses
Reference links and supporting material
Anonymized profile records of MSMEs containing bank balance trends, GST filings, and repayment histories.
How this agent runs
Evaluates multi-agent conversation consensus and credit limit generation accuracy.
Challenge input
JSON with MSME profile, monthly avg balance, GST turnover, and requested loan
AutoGen
Provides multi-agent conversational orchestration.
Evaluated output
JSON with decision (APPROVED|REJECTED), sanctioned_amount, and interest_rate
- Must reject loans exceeding 3x annual GST turnover
- Rigor of multi-agent validation discussion steps • target: 0.95 • range: 0.85-1
- Benchmark: CreditUnderwriting-Bench
- Consensus Quality Score target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- AutoGen · Required
- Resemble AI · Optional
- Gentrace · Optional
- Gentrace · Optional
Evaluation contract
- Over-Leverage Protection Test · Weight 1
- Consensus Quality Score · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.