🧪 Table Studio is in beta, and it is on for every account. We are actively improving this feature daily.

Table Studio is the new way to build a robot in Browse AI. Point an AI agent at a URL and it reads the page, builds the table structure for you, and fills it with sample data. You review, edit, and save. From then on the robot extracts that data on demand or on a schedule, like any other Browse AI robot.

💡 You do not need to know exactly what you want before you start. The agent proposes the structure from what is on the page.

Watch & learn

Watch the full flow, from a URL to a saved robot:

Is Table Studio the right tool for your dataset?

Table Studio works on most pages, including ones where you need to click, filter or search before the data appears.

✅ Table Studio can now handle most sites where you have to do something before the data shows up: clicking buttons and tabs, picking from dropdowns, typing into a search box, and moving between pages.

Start in Robot Studio instead when:

you need to change what’s typed into a search form on each run (for example, a different search term every time)
the data is behind a login that needs a username and password (not session cookies)
the site needs data stored in your browser to show the page

That is what Robot Studio's visual training is built for.

💡 If the data you are extracting is behind a login and you are already logged in on your browser, check This website needs logging in, choose Login with my session cookies, then select Table Studio. This needs the Browse AI browser extension. For a public page you don't need to install anything.

Not sure? Try Table Studio first. If it hits something it cannot handle, it tells you why and what to do next.

How to build a robot with Table Studio

Step 1: Point it at a URL

From your Browse AI dashboard, click Build New Robot.
Choose Extract structured data (or Monitor for changes if you want to track the page).
Enter the Origin URL: the page that shows the data you want.
Click Start Training Robot (or Train robot), then choose Table Studio under AI Training.

💡 Pick the right starting URL. The closer your Origin URL is to the page that shows the data, the better the result. Point it at example.com/products, not the homepage.

Step 2: The AI agent builds your table

The agent takes it from there. It loads the live page, reads its structure, works out which values appear once and which repeat as lists, proposes the tables and columns, and extracts sample rows. If the data sits behind a button, tab, filter or another page, the agent clicks, types and picks options to get to it, the way a person would.

⏱️ This can take a few minutes depending on the page. You will see progress at the bottom of the screen while it works. There is nothing to configure at this stage; let it finish.

Step 3: Review and edit the data structure

Once the agent is done, you can review, delete, add or edit the data it has captured.

💡 When you save, you'll be asked a few quick questions.

If you chose Monitor for changes, you'll be asked How often should this robot check for changes? (Hourly, Daily, Weekly or Monthly; Daily is the default) and Get an email when the data changes? (on by default). You can change both later in the Monitor tab.

If the table includes a long list, you'll also be asked How many items do you want from [list] at most? Pick 50, 500, 5,000, or type your own number up to 5,000.

How to add data

Add a column to add additional data using plain language. You can add:

Single text
A list
A screenshot

Inside a list table you can add single text; lists and screenshots are added to the main table.

Select the data type you want to capture. Name it and add Instructions in plain language, for example “the listed price before any discount”. Then click Preview. The agent uses your description to find the right element on the page.

How to remove data

The agent by default will include all data on the page it thinks is relevant to you. To remove columns you don't want to capture, click ⋮ on the column header, then Delete column, and confirm. To keep a column but not show it, choose Hide column instead.

Step 4: Save to unlock monitoring, bulk actions, and more.

When it looks right, click Save Robot in the bar at the bottom. Nothing runs on a schedule until you save.

Once you save the robot you'll be able to add things like monitoring, bulk runs, integrations, workflows, and export the data.

Adding columns to an existing table

You can add columns or whole new lists to a table you have already trained without creating a new robot.

Go to the Table you want to edit.
Click Add column and choose Single text, List, or Screenshot.
Click Open Design Mode.
Name the column and add Instructions if needed.
Click Preview, then Save Robot.

🚫 If the robot uses clicks, inputs, or a password login, Table Studio can’t add columns yet. You’ll be asked to retrain it in Robot Studio instead.

Cleaning and enriching the data after extraction

Once the robot is extracting, you can add formula columns that post-process the data the robot captures: clean values, categorise records, or calculate new fields from the extracted data. Click Add column, then Formula. Describe what you want in plain language and AI writes the formula for you.

Formula columns work on data the robot has already extracted, so they apply straight away. No Design Mode or re-save needed.

💡 Say how you want the result to look, for example Percent off the list price, like 19%.

Frequently asked questions

Will my existing robots break or change?

No. Table Studio changes how new robots are built. Existing robots keep running exactly as they did. You can retrain an existing robot in Table Studio if you want to.

Is an AI guessing at my data?

It proposes the tables and columns and shows you real extracted sample data; you review, refine, and approve before the robot is saved. Nothing runs on a schedule until you have saved it.

How does Table Studio handle pagination and long lists?

When the table includes a list, you choose how many items to extract at most. If the count looks like 12+, the preview was capped. Once you save, the robot extracts up to the list limit you set. You don't need to set up pagination. The agent finds the list and how to get to the next page (a next button, load more, or infinite scroll). To open each item and pull data from its own page, connect two robots with a workflow.

A column came back with the wrong data. What should I do?

If a value can't be found, the cell shows Not found and the column is highlighted. Before saving, edit the column’s name or Instructions to be more specific, then click Preview. Still stuck? Share your table URL with [email protected].

Does using Table Studio cost extra credits?

Training is free within your plan’s AI training allowance. Past the allowance, each new robot uses 20 credits, which covers 5 previews. If a preview fails on our side, you aren't charged. You can see this under My plan & usage → Usage, which shows Task credits and Training credits separately, with each session listed under Robot trainings using AI. Once saved, a robot uses credits like any other Browse AI robot.

Can I switch a Table Studio robot to Robot Studio later?

Yes. You can retrain any robot in Robot Studio at any time. The data in the robot's table is preserved.

Can I edit a Robot Studio robot in Table Studio?

You can retrain an existing robot in Table Studio if it doesn’t use clicks, inputs, a password login, or data stored in the browser. Otherwise you'll be asked to retrain it in Robot Studio.

How to train a robot using AI in Table Studio