Starting Workflows

Once you’ve defined your workflow functions, you need to trigger them to begin execution. This is done using the start() function from workflow/api, which enqueues a new workflow run and returns a Run object that you can use to track its progress.

The `start()` Function

The start() function is used to programmatically trigger workflow executions from runtime contexts like API routes, Server Actions, or any server-side code.

import { start } from "workflow/api";
import { handleUserSignup } from "./workflows/user-signup";

export async function POST(request: Request) {
  const { email } = await request.json();

  // Start the workflow
  const run = await start(handleUserSignup, [email]);

  return Response.json({
    message: "Workflow started",
    runId: run.runId
  });
}

Key Points:

start() returns immediately after enqueuing the workflow - it doesn’t wait for completion
The first argument is your workflow function
The second argument is an array of arguments to pass to the workflow (optional if the workflow takes no arguments)
All arguments must be serializable

Learn more: start() API Reference

The `Run` Object

When you call start(), it returns a Run object that provides access to the workflow’s status and results.

import { start } from "workflow/api";
import { processOrder } from "./workflows/process-order";

const run = await start(processOrder, [/* orderId */]);

// The run object has properties you can await
console.log("Run ID:", run.runId);

// Check the workflow status
const status = await run.status; // "running" | "completed" | "failed"

// Get the workflow's return value (blocks until completion)
const result = await run.returnValue;

Key Properties:

runId - Unique identifier for this workflow run
status - Current status of the workflow (async)
returnValue - The value returned by the workflow function (async, blocks until completion)
readable - ReadableStream for streaming updates from the workflow

Most Run properties are async getters that return promises. You need to await them to get their values. For a complete list of properties and methods, see the API reference below.

Learn more: Run API Reference

Common Patterns

Fire and Forget

The most common pattern is to start a workflow and immediately return, letting it execute in the background:

import { start } from "workflow/api";
import { sendNotifications } from "./workflows/notifications";

export async function POST(request: Request) {
  // Start workflow and don't wait for it
  const run = await start(sendNotifications, [userId]);

  // Return immediately
  return Response.json({
    message: "Notifications queued",
    runId: run.runId
  });
}

Wait for Completion

If you need to wait for the workflow to complete before responding:

import { start } from "workflow/api";
import { generateReport } from "./workflows/reports";

export async function POST(request: Request) {
  const run = await start(generateReport, [reportId]);

  // Wait for the workflow to complete
  const report = await run.returnValue;

  return Response.json({ report });
}

Be cautious when waiting for returnValue - if your workflow takes a long time, your API route may timeout.

Stream Updates to Client

Stream real-time updates from your workflow as it executes, without waiting for completion:

import { start } from "workflow/api";
import { generateAIContent } from "./workflows/ai-generation";

export async function POST(request: Request) {
  const { prompt } = await request.json();

  // Start the workflow
  const run = await start(generateAIContent, [prompt]);

  // Get the readable stream (can also use run.readable as shorthand)
  const stream = run.getReadable();

  // Return the stream immediately
  return new Response(stream, {
    headers: {
      "Content-Type": "application/octet-stream",
    },
  });
}

Your workflow can write to the stream using getWritable():

import { getWritable } from "workflow";

export async function generateAIContent(prompt: string) {
  "use workflow";

  const writable = getWritable();

  await streamContentToClient(writable, prompt);

  return { status: "complete" };
}

async function streamContentToClient(
  writable: WritableStream,
  prompt: string
) {
  "use step";

  const writer = writable.getWriter();

  // Stream updates as they become available
  for (let i = 0; i < 10; i++) {
    const chunk = new TextEncoder().encode(`Update ${i}\n`);
    await writer.write(chunk);
  }

  writer.releaseLock();
}

Streams are particularly useful for AI workflows where you want to show progress to users in real-time, or for long-running processes that produce intermediate results.

Learn more: Streaming in Workflows

Check Status Later

You can retrieve a workflow run later using its runId with getRun():

import { getRun } from "workflow/api";

export async function GET(request: Request) {
  const url = new URL(request.url);
  const runId = url.searchParams.get("runId");

  // Retrieve the existing run
  const run = getRun(runId);

  // Check its status
  const status = await run.status;

  if (status === "completed") {
    const result = await run.returnValue;
    return Response.json({ result });
  }

  return Response.json({ status });
}

Next Steps

Now that you understand how to start workflows and track their execution:

Learn about Common Patterns for organizing complex workflows
Explore Errors & Retrying to handle failures gracefully
Check the start() API Reference for complete details

Getting Started

Installation

Core Concepts

Building AI Agents

How It Works

Deployment

Observability

Testing

Error Reference

The `start()` Function

The `Run` Object

Common Patterns

Fire and Forget

Wait for Completion

Stream Updates to Client

Check Status Later

Next Steps

​The start() Function

​The Run Object

​Common Patterns

​Fire and Forget

​Wait for Completion

​Stream Updates to Client

​Check Status Later

​Next Steps

The `start()` Function

The `Run` Object

Common Patterns

Fire and Forget

Wait for Completion

Stream Updates to Client

Check Status Later

Next Steps