Back to challenges
Challenge

Account Aggregator MSME Credit Agent with OpenAI Agents SDK & Ellipsis

MSME loan underwriters suffer from manual bank statement reconciliation across fragmented Account Aggregator streams. Build an automated credit scoring and consent verification agent using OpenAI Agents SDK and Ellipsis to process AA financial payloads and reach a 92% accurate risk classification.

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.

Build an AA-compliant automated MSME credit assessment pipeline using OpenAI Agents SDK and Ellipsis code automation tools.

Delivery guide

How work is evaluated

Evaluation

Evaluates MSME risk scoring precision and consent verification compliance on simulated AA financial data.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
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

check_risk_bounds

Verifies that credit decisions strictly follow risk threshold parameters

Binary check

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

Dimension 2

underwriting_precision

Precision of risk categorization compared to standard financial rubric • 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

  • Process Account Aggregator FIU JSON payloads for cash-flow underwriting

  • Implement OpenAI Agents SDK runner loops with structured output parsing

  • Integrate Ellipsis for automated code synthesis of custom financial indicators

  • Verify consent artifact validity and digital signatures

Resources and assets

Reference links and supporting material

Dataset notes

Anonymized AA financial transactions dataset containing cash flows, GST filings, and repayment records.

How this agent runs

Evaluates MSME risk scoring precision and consent verification compliance on simulated AA financial data.

Challenge input

JSON containing bank transaction streams and AA consent token

OpenAI Agents SDK

Agentic framework for building autonomous agents with function calling.

Ellipsis

Automated code transformation and generation developer utility.

Evaluated output

JSON with credit_score, decision, and risk_tier

Checks for
  • Verifies that credit decisions strictly follow risk threshold parameters
  • Precision of risk categorization compared to standard financial rubric • target: 0.92 • range: 0-1
Proof of success
  • Benchmark: Indian SME Credit Decision Benchmark
  • Underwriting Precision target: 0.92
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Ellipsis · Required
  • OpenAI · Optional
  • Writer · Optional

Evaluation contract

  • check_risk_bounds · Weight 1
  • underwriting_precision · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Account Aggregator MSME Credit Agent with OpenAI Agents SDK & Ellipsis