Unit 8 · Measure and improve AI quality

Test AI behavior on real examples

You record realistic inputs, criteria, expected or forbidden actions, predictions, and traces. Use deterministic metrics when possible and judges when quality needs holistic review.

9 focused minutesNot started

Unit example (nearest native match)

See the idea in context

var engine = new AxGEPA(reflectionClient, Map.of());
var result = engine.optimize(request, evaluator);

Use a realistic input
The refund request represents the kind of task the agent will face.
Write the success rule
criteria explains that eligibility must be verified before action.
Record observable behavior
expectedActions lets the evaluation check tool selection, not only final prose.

Run itIn your own project

// Gradle (build.gradle):
implementation 'dev.axllm:ax:24.0.15'
// Maven (pom.xml):
<dependency>
  <groupId>dev.axllm</groupId>
  <artifactId>ax</artifactId>
  <version>24.0.15</version>
</dependency>

import dev.axllm.ax.Ax;
import java.util.Map;

public class QuickStart {
  public static void main(String[] args) throws Exception {
    var llm = Ax.ai("openai", Map.of("apiKey", System.getenv("OPENAI_API_KEY")));
    var classify = Ax.ax("review:string -> sentiment:class \"positive, negative, neutral\"");
    var result = classify.forward(llm, Map.of(
      "review", "Useful and boring in the best way."
    ));

    System.out.println("sentiment: " + result.get("sentiment"));
  }
}

Set OPENAI_APIKEY in your environment before running provider-backed code.

In the ax repo

From a clone of the ax repo:

npm run example -- java src/examples/java/optimization/AxgenOptimizationExample.java

Active practice

Show that you can use it

Answer 2 in a row to learn this · attempt 1

Keep exploring

See the idea in context

Show that you can use it

Source-backed follow-up