AI Agent Scorecards for Quality Assurance

Maintain exceptional service quality across your AI workforce. The new Scorecards feature lets you create comprehensive evaluation frameworks to audit AI agent conversations and assign scores based on your specific quality parameters.

With Scorecards, you can:

• Create custom evaluation questions: Define specific criteria and prompts that you will assess during conversation reviews, with detailed descriptions to ensure consistent scoring.
• Set weighted scoring: Assign maximum points to each question based on importance, allowing you to prioritize critical aspects of customer interactions.
• Choose evaluation types: Select from binary yes/no assessments or scale-based ratings to match your quality assurance methodology.
• Mark fatal questions: Identify critical criteria where failure results in overall scorecard failure, regardless of total score - perfect for compliance or safety requirements.
• Streamline quality reviews: Provide you with structured frameworks that eliminate guesswork and ensure consistent assessment standards.

How to get started: Navigate to "Scorecards" on the left navigation bar to create a new Scorecard.