Back to evaluations
Public evaluation

AIGeneratedContentDetection

Evaluation will focus on the multi-agent system's accuracy in detecting AI-generated content, adherence to compliance rules, efficiency of the LangGraph workflow, and the quality of explanations provided by Coplay AI.

Evaluation type
task based
Challenge
Multi-Agent System for AI-Generated Content Verification & Compliance
Difficulty
Advanced
Rigor
Unspecified
Open linked challenge

Evaluation overview

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

Tasks
2
Benchmarks
0
Criteria
0

Task templates

Inputs and expected outputs.

Task 1

AIGeneratedContentDetection

Assesses the system's ability to correctly classify human-authored vs. AI-generated text.

Input format

{ "content_id": "string", "text_content": "string", "true_label": "human|ai" }

Output format

{ "content_id": "string", "predicted_label": "human|ai", "confidence": "float", "analysis_report": "string" }

Task 2

ComplianceCheckAccuracy

Measures the agent team's precision in identifying compliance violations against a set of rules.

Input format

{ "content_id": "string", "text_content": "string", "compliance_rules": ["string"], "expected_violations": ["string"] }

Output format

{ "content_id": "string", "violations_found": ["string"], "is_compliant": "boolean" }