gepa_evaluate_prompt
Assess the effectiveness of AI prompts by evaluating their performance against multiple tasks, enabling iterative optimization for improved creativity and reliability.
Instructions
Evaluate prompt candidate performance across multiple tasks
Input Schema
Name | Required | Description | Default |
---|---|---|---|
parallel | No | Whether to run evaluations in parallel | |
promptId | Yes | Unique identifier for the prompt to evaluate | |
rolloutCount | No | Number of evaluation rollouts per task | |
taskIds | Yes | List of task IDs to evaluate the prompt against |