Skip to content

AI

Last updated

An AI agent that works in a real browser

Describe the task in plain English. The agent opens a cloud Chromium browser, clicks, types, logs in, extracts data and writes files. You watch it live, step in when you want, and approve anything risky before it happens.

No credit card required

Free plan available

Cancel anytime

How It Works

Get started in minutes

1

Describe the task

Type what you want done in the chat. Attach a CSV, Excel file, PDF or image if the task needs one.

2

The agent plans and works

It writes a step plan, then drives a real browser, searches the web, runs scripts and calls your connected apps.

3

Watch, guide or take over

Follow the live browser view, send corrections in chat, or take control of the browser and hand it back.

4

Get results, then reuse them

Results come back as a sortable table and downloadable files. Convert the session into a workflow to run it again.

What the AI agent does

Autonoly's agent is an AI that works through a real web browser for you. You describe a task in chat. The agent starts a Chromium browser in an isolated cloud container and does the work step by step: it opens pages, clicks buttons, fills forms, logs in, scrolls, extracts data and saves files. Every step shows up in the chat, and the browser itself is visible in the panel next to it.

It doesn't write a script for you to run. It uses the browser itself and hands you the data or files.

The tools the agent has

The agent works with a fixed set of tools. These are the ones you will see in a session:

  • Browser actions: click, type, scroll (including infinite scroll), select from dropdowns, hover, paste, fill date pickers, go back, go forward and refresh. It reads the page by taking a screenshot and listing the clickable elements, and it can search a page for text or elements.

  • Extraction: single values, lists of repeated items, HTML tables, or the page structure. When selectors fail it can fall back to reading a screenshot with AI vision. See Data Extraction.

  • Tabs: up to four tabs in one browser, so it can work two sites side by side. Tabs share cookies and logins.

  • Web search and fetch: a quick web search, or fetching a page as plain text, without disturbing the browser.

  • Terminal and files: shell commands and Bash, Python or Node scripts in the session's Linux container. Python has pandas, numpy and matplotlib. It can read and write files there and turn any file it creates into a download.

  • Data tools: filter, reshape and summarize extracted data with JavaScript, then save it as CSV, Excel (several sheets if needed) or JSON.

  • Your apps: native integration nodes such as Google Sheets, Gmail, Slack, Notion and Airtable (see Integrations), plus tools from MCP servers you connect.

  • Results: a results table you can sort and download as CSV, with any generated files attached.

Sub-agents for parallel work

For broad tasks the agent can split the work. It hands out up to four sub-tasks at once. Research sub-agents only have web search and page fetching. Browser sub-agents each get their own tab in the same browser, with the same cookies and logins, so one can work on one job board while another works on a second. By default two browser sub-agents run at a time and the rest wait their turn. Sub-agents cannot log in, buy or post on their own. The main agent keeps those steps.

It asks you instead of guessing

The agent pauses and asks you in four situations:

  • It needs an account. If a task needs Google Sheets, Slack or another integration you have not connected, it asks you to connect one or pick an existing one.

  • It needs to log in to a website. With a stored username and password, the agent types them into the login form without ever seeing them. If the site asks for a 2FA code and you have saved a TOTP secret, it generates the 6-digit code and types that too.

  • The action is risky. Before paying, placing an order, sending an email or message to a real person, posting in public, deleting data or submitting a legally binding form, it shows you exactly what it is about to do. You approve or deny. If you deny, or don't answer, it does not go ahead.

  • It is stuck. On a CAPTCHA it cannot solve, or a page it cannot get past, it offers you Take Control so you can sort it out in the live browser. reCAPTCHA v2 and hCaptcha can be solved automatically when CAPTCHA solving is turned on. Others, such as Cloudflare Turnstile, need you.

You stay in control while it runs

The agent shows its step plan and ticks off each step. You can send a correction at any time ("that's the wrong button, use the pagination at the bottom"). You can also take over the browser yourself and hand it back. The agent then carries on from wherever you left the page.

The agent also learns your preferences. If you say "always use DD/MM/YYYY" or "remember our CRM is the customers table", it saves that to your workspace's agent memory, and later sessions start out knowing it.

From one chat to a repeatable workflow

The agent records every step it takes. When a session finishes, Convert to Workflow turns that record into a workflow in the visual builder. It keeps the steps that worked and leaves out the failed attempts and inspection steps. You can then schedule it, add a webhook trigger, or edit it. Some things don't carry over. Agent to Workflow explains exactly what does.

You can also start agent sessions from your own code. The agent trigger API takes a prompt, authenticated with a scoped workspace API key, and returns the status and result. See the developer docs.

Limits worth knowing

  • Sites with strong bot protection can still block the browser. Autonoly does not offer proxy rotation or residential IPs.

  • Each step the agent takes uses credits. See pricing.

  • The agent works in its own cloud browser, not in your browser, so it starts logged out. You log in through stored credentials, or by taking control and logging in yourself.

Capabilities

Everything in AI Agent Chat

Powerful tools that work together to automate your workflows end-to-end.

01

Real browser, real actions

The agent drives a Chromium browser in an isolated cloud container and does what a person would do on the page.

Click, type, select, hover, paste, fill dates, scroll

Up to 4 tabs that share cookies and logins

Screenshot plus element list to read the page

Runs JavaScript on the page when needed

02

Logins without exposing passwords

Stored credentials are typed into login forms on the server side. The AI model never sees the secret.

Username and password autofill

TOTP 2FA codes generated from a stored secret

Asks you to connect an integration when one is missing

Credentials encrypted with AES-256-GCM

03

Approval before risky actions

Payments, orders, outgoing messages, public posts, deletions and binding form submissions all wait for your approval.

Shows the exact action and the risk

Approve or deny in the chat

Denied or unanswered means it does not proceed

Take Control offered when it gets stuck

04

Sub-agents for parallel work

Broad tasks can be split into up to four sub-tasks that run at the same time.

Research sub-agents use web search and fetch

Browser sub-agents each get their own tab

Two browser sub-agents at a time by default

Findings come back to the main agent to check

05

Terminal, files and data

A Linux container with a shell and Python sits next to the browser, so the agent can process what it collects.

Bash, Python and Node scripts

Attach CSV, Excel, PDF, JSON or images (up to 50 MB each)

Save CSV, multi-sheet Excel or JSON

Sortable results table with CSV download

Use Cases

What You Can Build

Real-world automations people build with AI Agent Chat every day.

01

Collect listings into a spreadsheet

Ask the agent to search a job board or product category, extract the fields you name across a few pages, and write them to Google Sheets or an Excel file.

02

Fill web forms from your data

Attach a CSV and have the agent enter each row into a web form. It asks for approval before the final submit if the form is binding.

03

Compare several sites at once

Have browser sub-agents check the same product or role on different sites in parallel tabs, then combine the results in one table.

04

Research with a written summary

Let research sub-agents search and read sources in parallel, then have the agent write up the findings and attach the data as a file.

05

Prototype an automation you will schedule

Do the task once in chat, check the result, then convert the session into a workflow and put it on a schedule.

FAQ

Common Questions

Everything you need to know about AI Agent Chat.

Related automations, integrations and terms

Where this feature is used in practice.

DefinitionAI AgentAn AI agent is an autonomous software system that uses large language models to perceive its environment, make decisions, and take actions to accomplish goals with minimal human direction.GuideBrowser Use Alternatives: Best No-Code Options for Non-DevelopersBrowser Use is a powerful open-source Python library for AI browser automation, but it requires coding skills. This guide covers the best no-code alternatives for non-developers who want the same AI-powered browser automation capabilities without writing a single line of Python.GuideAI Agent Platform: The Complete Guide to Autonomous Task Execution (2026)A guide to AI agent platforms in 2026. Understand platform architecture, key capabilities, evaluation criteria, and how to choose the right AI agent platform for your business. Includes a comparison of 8 platforms.FeatureAI & Content GenerationGenerate text, social graphics, narrated videos, slide decks and Word/PDF documents inside your automations. Built-in renderers need no API key; AI APIs use your own key.FeatureAI VisionThe agent looks at screenshots of the page as it works, and falls back to reading data from a screenshot when selectors fail. The AI_VISION node does the same in workflows.FeatureCross-Session LearningThe agent remembers your standing instructions and what worked on each website, so new sessions start informed instead of from zero.TemplateReal-Time Cryptocurrency Market Monitor AI Agent Automate cryptocurrency market monitoring with Autonoly's Real-Time Crypto AI Agent. Track Bitcoin, Ethereum & 1000+ altcoins across major…TemplateLinkedIn Company Page Scraper AI AgentAutomatically extract comprehensive company information from LinkedIn company pages with this intelligent AI Agent workflow. This template…GuideAutomation Platform Comparison: 47 Critical Features You Must Evaluate Before BuyingComplete automation platform evaluation guide covering 47 critical features. Compare workflow automation tools, integration capabilities,…

Ready to try AI Agent Chat?

Start automating your work with Autonoly. Start free, no credit card required.

No credit card

Free plan available

Cancel anytime