Browser Use

Overview of the Browser Use book.

The following documentation is for Browser Use v1.9.9 (BDK).

Overview

The Browser Use book enables you to perform web automation using natural language. Use plain English to describe a task, and a remote browser agent will execute it.

The browser agent can perform a range of web automation tasks, including navigating pages, filling out forms, and extracting structured data, all with full traceability. Every action is logged with detailed step plans and unique session IDs. Take a look at this quick example:

Prerequisites

1. Required Books

The following Book(s) need to be added to your agent so it can learn and understand the automation procedures defined within them:

• Browser Use

How to Add the Book(s)

1. Go to Books → All Books.

2. Search for the name of the book and click on it.

3. Click on Install or Add Connection to add the book to your agent.

4. If adding a connection, you'll be prompted for connectivity details.

Create a new playground after adding the book so the agent can recognize its procedures.

Connectivity

The Browser Use book can be used with or without credentials.

Getting Started

Follow these steps to write an automation that performs a web-based task:

1

Provision a Browser

The first step is to provision a browser, which sets up a browser instance for the Kognitos automation to control. This is required for any browser automation task. In the editor, write:

provision a browser

2

Prepare to Perform a Task

On the following line, write:

perform <the task> on the browser and get the visual log, the detailed plan, the result and the browser run id

This procedure will send the actual task to a remote browser agent and return a detailed plan of the steps taken, a visual log showing what happened in the browser, and the task results.

3

Create a Web Automation Task

Replace <the task> in the previous line with a Browser Automation widget:

1. In the editor, type / to open the widget menu and select Browser Automation.

Don't see the widget in your menu? Contact our support team to have it enabled in your agent.

1. Enter a Task Name and Task Instructions in plain English:

   1. Task Name: A short, descriptive name for your automation.

   2. Task Instructions: Step-by-step instructions for the browser to follow.

Examples

Task Name	Task Instructions
Check Product Prices	Navigate to the Acme store homepage, search for “laptop,” and record the prices of the first five results.
Download Daily Report	Go to the analytics dashboard, filter for today’s date, and download the report as a CSV.
Extract News Headlines	Visit the news site homepage and list the titles of the top 10 articles.

1. Optionally, specify an Output Format for the results (e.g., CSV, JSON, etc.). You can define which fields or data to include in the output.

2. If the automation task needs access to a website, service, or account that requires authentication (username and password), provide Credentials by selecting from existing connection details or adding a new one.

3. Click Save to finalize your task.