Get started with evaluating AI agents using no-code agents and the Maxim SDK. This guide will walk you through setting up the SDK and running your first agent evaluation test run using a no-code agent.

​
What are No-code Agents?

No-code agents in Maxim allow you to create multi-step AI workflows without code. You can chain multiple prompts together, use variables, and create complex agent-like behaviors through the Maxim platform’s no-code builder.

​
Installation

First, install the Maxim SDK for your preferred language: 
pip install maxim-py

​
Getting Your API Key

Before you can use the Maxim SDK, you need to obtain an API key from the Maxim platform:
  1. Log in to Maxim: Go to app.getmaxim.ai/login and sign in to your account
  2. Navigate to Settings: Click on “Settings” in the left sidebar
  3. Go to API Keys: Click on “API keys” under “Organization settings”
  4. Generate New Key: Click the “Generate new” button
  5. Name Your Key: Enter a descriptive name for your API key (e.g., “Development”, “CI/CD”, “Local Testing”)
  6. Copy the Key: Once generated, copy the API key immediately - you won’t be able to see it again
Store your API key securely! You won’t be able to view the complete key value again after closing the generation dialog.

​
Configuration

Initialize the Maxim SDK with your API key and workspace information: 
from maxim import Maxim

# Initialize Maxim SDK

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

​
Basic No-code Agent Test Run

Here’s how to create and run a basic no-code agent evaluation test run using a dataset: 
# Create a test run with no-code agent

result = (
    maxim.create_test_run(
        name="Basic No-code Agent Evaluation",
        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}")

​
Next Steps

Now that you’ve run your first no-code agent evaluation, explore these guides:
For complex multi-agent workflows, consider using the Maxim observability features to trace individual steps and debug no-code agent execution.