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

Unit example (nearest native match)

See the idea in context

qa := axllm.NewAx("question:string -> answer:string, confidence:number", nil)

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

go get github.com/ax-llm/ax/packages/go

package main

import (
    "context"
    "fmt"
    "os"

    axllm "github.com/ax-llm/ax/packages/go"
)

func main() {
    client := axllm.NewAI("openai", map[string]axllm.Value{"apiKey": os.Getenv("OPENAI_API_KEY")})
    classify := axllm.NewAx("review:string -> sentiment:class \"positive, negative, neutral\"", nil)
    result, err := classify.Forward(context.Background(), client, map[string]axllm.Value{
        "review": "Useful and boring in the best way."
    }, nil)
    if err != nil {
        panic(err)
    }

    fmt.Println("sentiment:", result.(map[string]axllm.Value)["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 -- go src/examples/go/generation/structured_generation.go

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