Back to evaluations
Public evaluation
voice_scam_detection
Evaluates Pydantic AI agent speed and typed detection accuracy on scam transcript streams.
Evaluation type
task based
Challenge
Deploy Real-time Anti-Scam Voice Intelligence with Pydantic AI and VAPI
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
voice_scam_detection
Parse streaming transcript frames and produce structured ThreatAssessment model
Input format
JSON object representing transcript event frame with caller_id and transcript_segment
Output format
JSON object strict matching ThreatAssessment model (is_scam, threat_category, urgency_score)