Back to evaluations
Public evaluation
aml_detection_eval
Evaluates the agent's accuracy in identifying structured AML rings and compliance with audit logging.
Evaluation type
task based
Challenge
Build a COSMIC Anti-Money Laundering Sharing Agent with Google ADK
Difficulty
Advanced
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
aml_detection_eval
Evaluates detection accuracy of complex structuring networks across anonymized bank data.
Input format
JSON formatted inter-bank transaction logs
Output format
JSON risk assessment report with flagged account IDs and confidence scores