Unit 1 · Build AI features you can measure

Measure whether your AI feature improved

You pair realistic examples with a metric, then compare versions on the same evidence. This turns prompt tweaking into a repeatable improvement loop.

7 focused minutesNot started

Worked example

See the idea in context

const metric = ({ prediction, example }) => prediction.sentiment === example.sentiment ? 1 : 0;

Keep a known answer
Each example records the behavior you want the program to reproduce.
Score one prediction
The metric returns 1 only when the predicted sentiment matches the example.
Compare on the same set
Reusing the dataset makes a new score meaningful instead of anecdotal.

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