Unit 4 · Connect AI steps into a workflow

Author or serialize a flow as a diagram

You can write a whole flow as a mermaid flowchart and compile it by passing the string to flow(). Any flow renders back with String(flow), so the diagram and the program stay in sync.

flow(mermaid)7 focused minutesNot started

Unit example (nearest native match)

See the idea in context

mermaid := `flowchart TD
  %%ax classify: request:string -> route:class "support, sales"
  classify{route}`
program := axllm.NewFlow(mermaid)
fmt.Println(program.String())

Write the diagram
Node contracts live in %%ax directives; labeled edges become branches and loops.
Compile with flow()
A string argument to flow() compiles the dialect into a runnable flow.
Render it back
String(wf) returns the diagram, so flow(String(wf)) round-trips the program.

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/flows/branch_flow.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