The evaluate test cases task grades the output of your other LLM tasks during automated tests. The evaluation is never visible to your chatbot users.
You shouldn't edit this prompt...
If you change this prompt, your automated tests may not work properly. We don't recommend changing this prompt.
You need an administrator or publisher role in your team to change a task prompt.
The task contains one prompt:
-
Evaluate Test Cases generates an evaluation of 'PASS', 'FAIL', or 'UNDETERMINED' for the output of another LLM task.
Prompt variables: ${passCase}, ${failCase}.
Changes to these prompts are applied immediately and do not appear in versions.
Prompt variables and requirements
The prompt uses the following prompt variables:
- ${passCase}: the pass criteria defined in the automated test
- ${failCase}: the fail criteria defined in the automated test.
You don't need to provide a value for these variables: they're automatically supplied when the chatbot uses the task to evaluate test cases.