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.
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.
How work is evaluated
Evaluates MSME risk scoring precision and consent verification compliance on simulated AA financial data.
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.
check_risk_bounds
Verifies that credit decisions strictly follow risk threshold parameters
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
underwriting_precision
Precision of risk categorization compared to standard financial rubric • target: 0.92 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
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
Reference links and supporting material
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
- Verifies that credit decisions strictly follow risk threshold parameters
- Precision of risk categorization compared to standard financial rubric • target: 0.92 • range: 0-1
- Benchmark: Indian SME Credit Decision Benchmark
- Underwriting Precision target: 0.92
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- 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.