Skip to main content

​
How to test no-code agents on Maxim?

Test AI agents using no-code agents that are configured and stored on the Maxim platform. This approach leverages the With Prompt Chain Version ID function to execute pre-configured no-code agents without needing to implement custom logic.

​
Basic No-code Agent Testing

Use the With Prompt Chain Version ID function to test agents configured as no-code agents on the Maxim platform: 
from maxim import Maxim

# Initialize Maxim SDK

maxim = Maxim({"api_key": "your-api-key"})

# Create and run the test using a Maxim no-code agent

result = (
    maxim.create_test_run(
        name="No-code Agent Test", in_workspace_id="your-workspace-id"
    )
    .with_data_structure(
        {
            "input": "INPUT",
            "expected_output": "EXPECTED_OUTPUT",
        }
    )
    .with_data("your-dataset-id")
    .with_evaluators("Bias")
    .with_prompt_chain_version_id("your-prompt-chain-version-id")
    .run()
)

print(f"Test run completed! View results: {result.test_run_result.link}")

​
Using Presets

If you have saved test configuration presets on the Maxim platform, you can use them to automatically load datasets, evaluators, and other settings without specifying them manually:
Python
from maxim import Maxim

maxim = Maxim({"api_key": "your-api-key"})

# Test using a saved preset — dataset, evaluators, and context
# settings are loaded from the preset automatically
result = (
    maxim.create_test_run(
        name="No-code Agent Test with Preset",
        in_workspace_id="your-workspace-id",
    )
    .with_prompt_chain_version_id("your-prompt-chain-version-id")
    .with_preset("My Saved Preset")
    .run()
)

print(f"Test completed! View results: {result.test_run_result.link}")
Any values you set explicitly via other builder methods will take priority over the preset defaults:
Python
result = (
    maxim.create_test_run(
        name="No-code Agent Test with Preset Override",
        in_workspace_id="your-workspace-id",
    )
    .with_prompt_chain_version_id("your-prompt-chain-version-id")
    .with_preset("My Saved Preset")
    .with_data("different-dataset-id")  # Overrides the preset's dataset
    .run()
)
If the preset includes human evaluators, you must also call with_human_evaluation_config to provide the reviewer emails.

​
Next Steps

For complex multi-agent endpoints, consider using the Maxim observability features to trace individual steps and debug no-code agent execution.