Creating a Task - Anchor Browser Docs

Overview

Automation Tasks are reusable browser automations you define once and run reliably in production. Anchor generates a versioned task from your input — combining deterministic automation with AI-assisted steps where needed.

Automation Tasks Overview

Visual tour of prompts, demonstrations, the workflow UI, runs, editing, and self-healing.

Ways to create a task

Method	Best for
Demonstration	Show the flow once in a live browser
Prompt	Describe what the task should accomplish in natural language

Both paths produce the same result: a task you can test and call from your application.

Create from a demonstration

Demonstrate a task in a live browser. Anchor captures your actions and builds a reusable task.

Create from a prompt

Describe what the task should accomplish. Anchor generates the task from your description.

Create from a demonstration

Demonstrate a task in a live browser — navigate, click, fill forms, download files. As you work, Anchor captures every browser event and compiles them into deterministic, repeatable code.

In the Anchor UI

Open the Tasks page

Go to Tasks and click Create Task.

Set up identity and describe the task

The creation wizard walks you through four steps:

Identity — enter the application URL (and an identity, if the task requires login).
Task Definition — describe what the task should do in natural language.
Demonstration — choose to demonstrate the task yourself.
Review — confirm the task name, inputs, and outputs before saving.

Start the demonstration

On the Demonstration step, select the option to demonstrate the task manually, then click Continue.A live browser opens at your start URL. Perform the task — navigate, click, fill forms, download files. Anchor captures every browser event as you go.

Pro tip: Right-click anywhere to investigate elements or data. Those inspection moments give richer context to your final task.

Finish and create the task

Click Finish Demonstration when you’re done. Review the generated inputs and outputs on the Review step, then save the task.

Shareable demonstrations

To collect a demonstration from someone who works outside your Anchor workspace, use the Demonstrations API to issue a secure demonstration link. They complete the task in a hosted browser session; Anchor processes the session and delivers the generated task to your workspace.

Demonstrations API

Create demonstration links, monitor session status, and retrieve the generated task.

Create from a prompt

Describe what the task should do. Anchor generates the automation from your taskPrompt.

How to structure your prompt

Section	Include
Objective	What the task should accomplish
Start URL	Where the browser opens
Inputs	Runtime values as `{{parameter_name}}`
Steps	Ordered actions, one per line
Output	Fields to return when the task completes

Example prompt

Objective: Export the monthly invoice report as a PDF.

Start URL: https://www.princexml.com/samples/

Inputs:
- report_name (required): The report to export

Steps:
1. Open Reports
2. Search for {{report_name}}
3. Open the first matching result
4. Click Export → PDF
5. Wait 5 seconds after clicking the download
6. Confirm the download completed

Output: report_title, exported_file_name

Add edge cases when they matter — e.g. “If no exact match is found, use the closest result.”

In the UI

Open Tasks and click Create Task.
Enter a name and describe the task — what site to visit, what to click, what data to return.
Wait for generation to finish, then test with sample inputs.

Via API

Call POST /v2/tasks/generate, then poll GET /v2/tasks/{taskId}/generation-status until status is ready.

import AnchorBrowser from 'anchorbrowser';

const anchorClient = new AnchorBrowser({ apiKey: process.env.ANCHOR_API_KEY });

const { id: taskId } = await anchorClient.post('/v2/tasks/generate', {
  body: {
    taskName: 'invoice-report-export',
    description: 'Export the monthly invoice report as a PDF',
    taskPrompt: `Objective:
Export the monthly invoice report as a PDF.

Start URL:
https://www.princexml.com/samples/

Inputs:
- report_name (required): The report to export

Steps:
1. Open Reports
2. Search for {{report_name}}
3. Open the first matching result
4. Click Export → PDF
5. Wait 5 seconds after clicking the download
6. Confirm the download completed

Output:
- report_title
- exported_file_name`,
  },
});

let status;
do {
  ({ status } = await anchorClient.get(`/v2/tasks/${taskId}/generation-status`));
  if (status === 'failed') throw new Error('Task generation failed');
  if (status !== 'ready') await new Promise((r) => setTimeout(r, 3000));
} while (status !== 'ready');

console.log('Task ready:', taskId);

import os
import time
from anchorbrowser import Anchorbrowser

anchor_client = Anchorbrowser(api_key=os.getenv('ANCHOR_API_KEY'))

response = anchor_client.post(
    '/v2/tasks/generate',
    body={
        'taskName': 'invoice-report-export',
        'description': 'Export the monthly invoice report as a PDF',
        'taskPrompt': """Objective:
Export the monthly invoice report as a PDF.

Start URL:
https://www.princexml.com/samples/

Inputs:
- report_name (required): The report to export

Steps:
1. Open Reports
2. Search for {{report_name}}
3. Open the first matching result
4. Click Export → PDF
5. Wait 5 seconds after clicking the download
6. Confirm the download completed

Output:
- report_title
- exported_file_name""",
    },
)
task_id = response['id']

while True:
    status_response = anchor_client.get(f'/v2/tasks/{task_id}/generation-status')
    status = status_response['status']
    if status == 'failed':
        raise RuntimeError('Task generation failed')
    if status == 'ready':
        break
    time.sleep(3)

print('Task ready:', task_id)

Optional fields on POST /v2/tasks/generate:

Field	Purpose
`application_id`	Tie the task to a managed application
`identity_id`	Pre-authenticate with a saved identity
`input_schema` / `output_schema`	Define typed inputs and outputs up front
`human_intervention`	Allow the task to pause for human input
`task_browser_default_configuration`	Default browser session settings for runs

Next steps

Run a Task — execute a task via API with inputs, identity, and session options
Which task type? — compare Automation Tasks with Perform Web Task
Demonstrations API — shareable links for demonstrating a task
Task Examples — browse ready-made tasks in the library

​Overview

Automation Tasks Overview

​Ways to create a task

Create from a demonstration

Create from a prompt

​Create from a demonstration

​In the Anchor UI

​Shareable demonstrations

Demonstrations API

​Create from a prompt

​In the UI

​Via API

​Next steps

Overview

Ways to create a task

Create from a demonstration

In the Anchor UI

Shareable demonstrations

Create from a prompt

In the UI

Via API

Next steps