Back to evaluations
Public evaluation

aa_credit_underwriting

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

Evaluation type
task based
Challenge
Account Aggregator MSME Credit Agent with OpenAI Agents SDK & Ellipsis
Difficulty
Intermediate
Rigor
Unspecified

Evaluation overview

How the linked challenge is judged: tasks, benchmarks, and criteria count.

Tasks
1
Benchmarks
0
Criteria
0

Task templates

Inputs and expected outputs.

Task 1

aa_credit_underwriting

Evaluates financial statement metrics and yields loan recommendation

Input format

JSON containing bank transaction streams and AA consent token

Output format

JSON with credit_score, decision, and risk_tier