Unit 1 · Build AI features you can measure

Give every AI call a clear contract

You use one signature vocabulary across generation, tools, agents, flows, and optimization. That shared meaning makes later Ax features easier to combine.

s()6 focused minutesNot started

Unit example (nearest native match)

See the idea in context

var qa = Ax.ax("question:string -> answer:string, confidence:number");

Separate input from output
The arrow puts message on the input side and the generated fields on the output side.
Use a class for fixed choices
category cannot drift beyond billing, technical, or other.
Reuse the parsed signature
s() creates a contract you can inspect, share, and compose.

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/generation/StructuredGenerationExample.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