LLM Simulation Testing
Batch test your agent
This feature is only available for conversation flow agents.
Overview
When testing your agent, you may have multiple test cases to verify. Running them in batch can significantly save time and effort.
Additionally, since Language Models (LLMs) can sometimes produce inconsistent or unexpected results, running tests multiple times helps ensure more reliable and accurate outcomes.
Steps
Step 1: Navigate to the Simulation Tab
Step 2: Set Up Your Test Cases
You have two options for test cases:
- Use existing test cases
- Create new test cases
For creating new test cases, you can either do it here or in the LLM Simulation Testing page. For detailed instructions, see LLM Simulation Testing.
Step 3: Define the parameters
Step 4: Execute the Tests
Choose the test cases you want to run from your test suite.
Was this page helpful?