> ## Documentation Index
> Fetch the complete documentation index at: https://www.tella.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Record with AI agents using Auto Capture

> Yes, an AI agent can record a screen demo for you. With Auto Capture, the Tella Agent, Claude, ChatGPT, Claude Code, Cursor or any AI agent connected to Tella's MCP server opens a web page, explores it and films a product demo, feature tour or how-to with an animated cursor, with no one at the keyboard.

> [!NOTE]
>
> Auto Capture is in **beta**. Tell us what works, what doesn't and what you'd like it to film next at [support@tella.com](mailto:support@tella.com).

Auto Capture films a screen walkthrough of a web page with no one at the keyboard: an AI agent opens the page in its own browser, explores it, plans the demo, and records it with an animated cursor. You start it by asking the [Tella Agent](https://www.tella.com/docs/help/editing/edit-with-the-tella-agent.md) in the editor, or an AI app such as Claude or ChatGPT connected to the [Tella MCP server](https://www.tella.com/docs/help/integrations/mcp-server.md).

Use it for a product demo, feature tour, how-to clip, or b-roll of a page you talk about, when you don't have your own screen recording.

## Can an AI agent record my screen for me?

Yes, for web pages. Auto Capture records a page in a browser on Tella's servers, so there's nothing to install and your own screen isn't used. It can't record desktop apps, mobile apps or pages on your own computer: see [Which pages can Auto Capture record?](#which-pages-can-auto-capture-record)

## Can Claude, ChatGPT or my coding agent record a demo video?

Yes. Connect Claude, ChatGPT, Claude Code, Cursor, Codex or another MCP client to Tella (see [Connect an AI assistant to Tella](https://www.tella.com/docs/help/integrations/mcp-server.md#connect-an-ai-assistant-to-tella)), then ask it to "use Tella to record a demo of" your page's URL. Agents you build can call the same [Auto Capture MCP tools](https://www.tella.com/docs/mcp-tools/auto-capture.md), for example to film each new release.

## What Auto Capture does with your request

Each request is called a **take**, and one take films one page or flow:

1. **Explores.** The agent opens your URL in a fresh browser and decides which features to show and in what order. If the page needs a sign-in and you've saved a login, it signs in here, off camera.
2. **Scripts and checks.** It writes the walkthrough as a script and runs it to check every step works. Anything a check saves is put back first, so the recording starts from your account as it was.
3. **Records.** It plays the script back in a clean browser and films it with an animated cursor.
4. **Delivers.** The finished take is processed like an upload and handed back with a short account of what it shows, chapter markers, and suggested cuts.

A take usually runs for several minutes, partly waiting for a recording machine to start.

## Start Auto Capture from the Tella Agent in the editor

[https://www.tella.com/video/vid\_cmvwkb2xe01ei07l68r2t7kvo/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0](https://www.tella.com/video/vid_cmvwkb2xe01ei07l68r2t7kvo/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0)

The Tella Agent can film a page and put it straight into the video you're editing.

1. Open a video in the editor and open the Tella Agent in the sidebar on the right (**Shift + S** if it's hidden).
2. Ask for the recording in plain language, with the page's full URL. For example:
   * "Record a 30-second tour of [https://example.com/pricing](https://example.com/pricing) for first-time visitors. End on the yearly toggle."
   * "I talk about our new dashboard at 1:20. Film [https://app.example.com/dashboard](https://app.example.com/dashboard) and use it as b-roll over that part."
3. The agent starts the take. Keep editing while it runs.
4. When the take is delivered, the agent places it as b-roll over part of your video or as its own clip, and applies the suggested cuts it agrees with.

The agent can also start a take on its own when an edit needs footage of a web page your video doesn't have, like a step your recording skips. It tells you in one sentence what it's recording and why before it starts.

## Start Auto Capture from Claude, ChatGPT or another AI app

Any AI app connected to the Tella MCP server can start a take. To connect one, see [Connect an AI assistant to Tella](https://www.tella.com/docs/help/integrations/mcp-server.md#connect-an-ai-assistant-to-tella).

1. In a chat with the Tella connector turned on, ask for a recording of a page, with its full URL: "Use Tella to record a product demo of [https://example.com](https://example.com) for new visitors."
2. The app starts the take and checks on it every 30 to 60 seconds until it finishes. Some apps only check when you send another message: if yours goes quiet, ask "Is the Tella capture done?"
3. When the take is delivered, ask the app to make it a video ("Put it in a new Tella video") or to add it to an existing one. The take isn't in your library until it's placed in a video.
4. Open the video in Tella to edit, trim, add narration or share it.

For a longer video that covers several pages, ask for one take per page or flow, then have them added to the same video in order.

## Write a good request for Auto Capture

Describe the outcome you want, not a list of clicks; the agent finds the buttons itself. Include:

* **Who it's for and what it's for:** "a product demo for first-time visitors", "a how-to for admins setting up SSO".
* **Anything you specifically want shown, skipped or ended on:** "compare the three plans and stop on the yearly toggle", "don't open the settings menu". Steps you name are followed; anything you leave open, the agent decides. What you say not to do also holds while the agent explores and checks its script, not only in the recording. If the take it can make would leave out something you asked for, it asks you instead of delivering it.
* **A length, only if you need one,** such as "about 20 seconds to fill the gap at 1:20". Otherwise the take is as long as the demo needs.
* **Whether to show how to get there.** The agent can navigate to a feature off camera and start the recording on it. If viewers need to see the path, say so.
* **What may change on the account,** if the demo saves something: whether it's a sandbox, which record to use, how to undo a change, and what mustn't change, such as "don't send anything". If you don't say, the Tella Agent or your AI app should ask before a take that saves something. Either way, use a demo account you're happy to have clicked around in.
* **Keyboard shortcuts, if you want them.** By default the agent clicks every control, so viewers can follow it. Ask for a keyboard-driven demo to have it use shortcuts where an experienced user would, then turn on [Keystrokes](https://www.tella.com/docs/help/editing/show-keystrokes.md) so viewers see them.

## What Auto Capture changes on your account

Auto Capture uses the signed-in account for real. Anything the demo saves is saved while the agent explores, on every check, and once more in the recording.

* **Changes it can undo:** before each run, the agent puts back what earlier runs saved, such as deleting a project an earlier run created or turning a setting back off, so every run, the recording included, starts from the account as you described it.
* **Changes it can't undo:** for something like sending an email or confirming an order, the agent stops before making the change and asks you what to do. It can't yet keep such a change for the recording alone: every check makes it too. Answer with a way round it, for example "use a test account where that's fine to repeat" or "stop on the confirmation, don't send", and a new take starts with your answer.
* **What's left changed:** when a delivered take leaves something changed on the account, such as a new record it created, your AI app or the Tella Agent tells you.

## Which pages can Auto Capture record?

Auto Capture records any `http` or `https` page on a public domain. It can't record:

* Pages on your own computer or private network, such as `localhost`, IP addresses, or intranet hosts.
* URLs with a username or password in them.
* Desktop apps, mobile apps, or anything outside a web browser.

Captures run on Tella's servers, so they see a page the way a new visitor does. Some sites block automated browsers or traffic from cloud servers and show a "verify you're human" or "sign in to confirm you're not a bot" page instead; Auto Capture can't get past those. If it's your site, you can let captures through with a firewall rule: see [Let Auto Capture past your firewall or bot protection](https://www.tella.com/docs/help/integrations/auto-capture-site-access.md).

## Record pages behind a sign-in

To film signed-in parts of your product, first save a login under **Settings** → **Credentials**. See [Let Auto Capture sign in to your product](https://www.tella.com/docs/help/integrations/auto-capture-credentials.md).

When a saved login matches the page, the agent signs in once, off camera, while exploring, and the recording starts already signed in. The sign-in is filmed only when you ask to show it, or when the site's sign-in can't be carried over to the recording browser. Password fields are always masked in the recording.

The agent signs in with a matching saved login even when the page also opens signed out, such as a public or shared link to your own project, so the video shows what you see when you're signed in. To film what a signed-out visitor sees, say so in your request. If the login asks you for a code, the take waits for it as described below.

If the page needs a sign-in and you haven't saved a login for it, the take stops and you get a link to **Settings** → **Credentials**. Add the login there, then ask for the take again.

> [!WARNING]
>
> Never paste a password, code, or sign-in link into the chat. Auto Capture only signs in with logins saved in Tella, and asks for codes on a Tella page.

## Enter a sign-in code for Auto Capture

If your product sends a code by email or text message when the agent signs in, the take pauses and asks you for it:

1. Your AI app or the Tella Agent gives you a link to a page on Tella. Some apps open it for you.
2. On the page, check the site under **Tella would like to sign in to**, and the **Account** when it's signing in with a saved login.
3. Type the code you received into **Enter code** and click **Allow access**.
4. When you see **You're all set**, close the page. The take carries on.

The page shows how long is left. If time runs out, the take stops and you need to ask for it again. Only the person who started the take can see or answer the request. Saved logins that are yours (**Only you**) can ask for a code; workspace logins can't.

A take can also ask for a code without a saved login, when a site signs you up or in with only an email address and a code sent there. Give the email address in your request, such as "sign up with [demo@example.com](mailto:demo@example.com)". The code is asked for only while the agent explores, so the recording starts signed in.

To skip this step, save the login from 1Password with its one-time password, and Tella fills in the code itself. See [Sign in with two-factor authentication](https://www.tella.com/docs/help/integrations/auto-capture-credentials.md#sign-in-with-two-factor-authentication).

## What you get when an Auto Capture take is delivered

[https://www.tella.com/video/vid\_cmw108p6z002v08k18p3h4zjg/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0](https://www.tella.com/video/vid_cmw108p6z002v08k18p3h4zjg/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0)

Each delivered take comes with:

* **A handoff note:** what the clip shows, anything the agent did off camera that isn't in the clip, and where it departed from your request.
* **Chapters:** where each section of the walkthrough starts, for titles, narration or splitting it up.
* **Suggested cuts:** page-load waits and over-long pauses that can go. The Tella Agent applies the ones it agrees with; in other AI apps, ask for them to be applied.
* **Key presses:** every key the take pressed is recorded with it, except what's typed from a saved login, so you can show them with [Keystrokes](https://www.tella.com/docs/help/editing/show-keystrokes.md).

The take is a screen recording with an animated cursor, so you can edit it like any other clip: trim it, add [zooms](https://www.tella.com/docs/help/editing/add-a-zoom.md), [restyle the cursor](https://www.tella.com/docs/help/editing/customize-animated-cursor.md), add a voiceover, or change the background.

## Change or redo an Auto Capture take

If a take is almost right, ask the Tella Agent or your AI app to revise it and say what to change: "Revise that take so it also clicks **Completed** and ends there." The agent starts a new take from the earlier one's script and notes, changing only what you asked, so a revision is usually quicker and uses fewer credits than starting over.

* The earlier take is never changed. The revision arrives as a new take for you to place.
* Only the person who started a take can revise it, from the same workspace.
* A take that's still running can't be revised until it finishes.
* A take that stopped at a sign-in or on a page that blocked the capture browser can't be revised. Ask for a new take instead.
* Takes made before revisions were available can't be revised. Ask for a new take with the change in your request.

To shorten or reorder what you already have, edit the clip in the editor.

If a take went wrong, such as filming the wrong page, missing a step you asked for, or stuttering or freezing, tell the Tella Agent or your AI app what was wrong. It reports the take to Tella so the cause gets fixed. A report doesn't change the take or use credits, so also ask for a revision to get a better one.

## Stop an Auto Capture take

[https://www.tella.com/video/vid\_cmw10mqcc000102k94bwi6owg/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0](https://www.tella.com/video/vid_cmw10mqcc000102k94bwi6owg/embed?b=0\&title=0\&a=1\&loop=0\&t=0\&muted=0\&wt=0)

Ask the Tella Agent or your AI app to cancel it, for example after starting one with the wrong URL. A cancelled take usually stops within seconds and produces nothing to place.

## Why didn't my Auto Capture take finish?

A take can end without a recording in one of these ways, and your AI app or the Tella Agent tells you which:

* **It needs guidance.** The agent got stuck on something only you can answer, such as which of two accounts to use, or reached a change to your account it can't undo, and asks you a question. Answer it, and the take is revised with your answer.
* **It needs a login.** The page asked for a sign-in and no saved login matched. Add one under **Settings** → **Credentials**, then try again.
* **It failed.** The message says why. If the failure was temporary, like the AI model being briefly unavailable, ask for the same take again in a few minutes. Otherwise, check the URL works in a private browser window.

## Who can use Auto Capture, and what does it cost?

Auto Capture is included with paid plans and the free trial; on a workspace without either, a take can't start and you're told to upgrade. It uses your workspace's [credits](https://www.tella.com/docs/help/billing/ai-credits.md), the same balance the Tella Agent spends. Each take uses credits for the AI that explores and scripts the page and for the machines that record it, and is charged when the take ends, including takes that end with a question, fail or are cancelled partway. If you've [connected your ChatGPT or Claude plan](https://www.tella.com/docs/help/integrations/use-your-chatgpt-or-claude-plan.md), takes on that provider's models run the AI on your plan and use credits only for the machines. A take can't start when the workspace is too low on credits; ask a workspace owner to add more.

## Choose the AI model Auto Capture uses

Auto Capture runs on Anthropic's Claude by default. If ChatGPT is the only plan you've connected, it runs on OpenAI's GPT instead, on your plan. If you've connected both, it uses whichever matches the AI you asked. To use a different model, or have it think harder on a complicated page, say so in your request: "use Claude Opus at high effort". More effort takes longer and uses more credits. Most takes don't need either.


## Related topics

- [Auto Capture](https://www.tella.com/docs/mcp-tools/auto-capture.md)
- [Get started with Auto Capture](https://www.tella.com/docs/help/integrations/auto-capture-get-started.md)
- [Make videos for your help articles with Auto Capture](https://www.tella.com/docs/help/integrations/auto-capture-help-center-videos.md)
- [How do Credits work?](https://www.tella.com/docs/help/billing/ai-credits.md)
- [Let Auto Capture sign in to your product](https://www.tella.com/docs/help/integrations/auto-capture-credentials.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.