By default, Melodi includes “Positive” and “Negative” feedback types. However, you can customize this entirely to match your specific evaluation needs within your project settings.

Define your own feedback types or scoring systems, such as:

  • Star Ratings: 1-5 stars
  • Quality Scores: “Excellent,” “Good,” “Fair,” “Poor”
  • Sentiment: “Happy,” “Neutral,” “Frustrated”
  • Relevance: “Relevant,” “Partially Relevant,” “Irrelevant”
  • Task Completion: “Goal Achieved,” “Goal Not Achieved”
  • Any other categorical or numerical scale relevant to your analysis.

This flexibility allows you to capture nuanced evaluations beyond simple binary feedback, tailoring the labeling process to your specific AI agent and goals.

When feedback is collected via the API or React component, you will specify the appropriate custom feedback type you have configured.

Was this page helpful?