Unit 1 · Build AI features you can measure

Turn a prompt into a reliable program

You describe what goes in and what must come out, so your app stops parsing model prose. Ax turns that contract into the prompt and validation loop.

ax()6 focused minutesNot started

Worked example

See the idea in context

const classify = ax('review:string -> sentiment:class \"positive, negative, neutral\"');

Name the input
review is the value your application supplies.
Constrain the output
sentiment can only be one of the three declared classes.
Keep the contract reusable
The same program can be tested, traced, and improved without changing its call site.

Run itIn your own project

npm install @ax-llm/ax

import { ai, ax } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });
const classify = ax('review:string -> sentiment:class "positive, negative, neutral"');

const result = await classify.forward(llm, {
  review: 'Useful and boring in the best way.',
});

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 -- typescript src/examples/typescript/generation/structured.ts

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