Unit 4 · Connect AI steps into a workflow

Build a workflow with explicit steps

You define application-owned state and a visible sequence of typed nodes. Input mappings feed each node, and the return mapping selects the final result.

flow()8 focused minutesNot started

Worked example

See the idea in context

const wf = flow().node('draft', 'topic:string -> text:string').execute('draft', s => ({ topic: s.topic })).returns(s => ({ text: s.draftResult.text }));

Declare a typed node
draft states exactly what the AI step receives and returns.
Map state into the node
execute() passes the workflow topic into the draft program.
Choose the public result
returns() exposes only the final text to the caller.

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/flows/branch-flow.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