Back to evaluations
Public evaluation
cyber_underwriting_assessment
Evaluates dynamic cyber underwriting risk calculations and schema validation.
Evaluation type
task based
Challenge
Pydantic AI Threat Agent: Autonomous Cyber Hazard Underwriting
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
cyber_underwriting_assessment
Evaluates enterprise posture inputs and generates structured risk scores and premium multipliers.
Input format
JSON containing company_id, ai_tool_exposure_score, unpatched_vulnerabilities, MFA_enabled
Output format
JSON matching CyberRiskResult Pydantic schema