Branching Paths

When processing data, you often need to take different actions based on intermediate results. This example shows how to create a workflow that splits into separate paths, where each path executes different steps based on the output of a previous step.

Control Flow Diagram

This example shows how to create a workflow that splits into separate paths, where each path executes different steps based on the output of a previous step.

Here’s the control flow diagram:

Diagram showing workflow with branching paths

Creating the Steps

Let’s start by creating the steps and initializing the workflow.

import { Step, Workflow } from "@mastra/core";
import { z } from "zod"
 
const stepOne = new Step({
  id: "stepOne",
  execute: async ({ context: { machineContext } }) => ({ 
    doubledValue: machineContext.triggerData.inputValue * 2
  })
});
 
const stepTwo = new Step({
  id: "stepTwo",
  execute: async ({ context: { machineContext } }) => ({ 
    isDivisibleByFive: machineContext.stepResults.stepOne.payload.doubledValue % 5 === 0
  })
});
 
 
const stepThree = new Step({
  id: "stepThree",
  execute: async ({ context: { machineContext } }) => ({ 
    incrementedValue: machineContext.stepResults.stepOne.payload.doubledValue + 1
  })
});
 
const stepFour = new Step({
  id: "stepFour",
  execute: async ({ context: { machineContext } }) => ({ 
    isDivisibleByThree: machineContext.stepResults.stepThree.payload.incrementedValue % 3 === 0
  })
});
 
// Build the workflow
const myWorkflow = new Workflow({
  name: "my-workflow",
  triggerSchema: z.object({
    inputValue: z.number(),
  }),
});

Branching Paths and Chaining Steps

Now let’s execute the workflow and see the results.

myWorkflow
  .step(stepOne)
  .then(stepTwo)
  .after(stepOne)
  .step(stepThree)
  .then(stepFour)
  .commit();
 
const result = await myWorkflow.execute({ triggerData: { inputValue: 3 } });

View Example on GitHub

Parallel Steps Calling an LLM