Explores
Opens your URL in a fresh browser, looks around, and decides what to show and in what order. Signs in off camera with a login you've saved.
Auto Capture · Closed beta
Your AI agent records the demo
Give it a URL. It explores the page, plans the walkthrough and films it.
One request, one finished take
Each request is a take that films one page or flow. It usually runs for several minutes, and you keep working while it does.
Scripts and checks
Writes the walkthrough as a script and runs it once to make sure every step works.
Records
Plays the script back in a clean browser and films it, moving an animated cursor to each thing it points at.
Delivers
Hands back the take with a handoff note, chapters and suggested cuts, ready to edit in Tella.
Ask from the editor or from Claude
Ask the Tella Agent in the editor and it places the take in the video you're editing. Or ask Claude, ChatGPT or any AI app connected to Tella's MCP server, and have it put the take in a new video.
Film the signed-in product
Save a demo login under Settings → Credentials. The agent signs in off camera, so the recording starts inside your app with no login screen. Passwords are masked, and sign-in codes go through a Tella page, never the chat.
Recorded, then edited by the same agent
A take arrives as a normal Tella recording with chapters and suggested cuts. The agent can trim it, add zooms, lay it over your talking head as b-roll, add captions, and share or publish it.
What teams record with it
Product demos
"Record a product demo of our pricing page for first-time visitors."
Help center videos
Have Claude find help articles with no video and record each one from its written steps.
B-roll for your recording
"I talk about our dashboard at 1:20. Film it and use it as b-roll over that part."
Release demos
Film a new feature the day it ships, without anyone sitting down to record.
Frequently asked questions
Auto Capture is Tella's agentic screen recorder. An AI agent opens a web page in its own browser, explores it, plans a walkthrough, and records it with an animated cursor, with no one at the keyboard. You get back a Tella recording you can edit, narrate and share like any other.
Agentic recording means an AI agent makes the recording for you. Instead of you clicking through a product while a screen recorder runs, you describe the demo you want and the agent explores the page, decides what to show, checks its script works, then films it. Tella's Auto Capture does this for web pages.
Ask the Tella Agent in the editor, or an AI app such as Claude or ChatGPT connected to Tella's MCP server, for a recording of a page with its full URL. For example: "Record a 30-second tour of https://example.com/pricing for first-time visitors. End on the yearly toggle."
Yes. Save a login for your product under Settings, then Credentials. The agent signs in off camera while it explores, and the recording starts already signed in. Password fields are always masked. If your product sends a sign-in code, you enter it on a Tella page, never in the chat.
It records http and https pages on public domains. It can't record localhost, IP addresses or intranet hosts, desktop or mobile apps, or sites that block automated browsers with a "verify you're human" check.
A screen recording with an animated cursor, plus a handoff note on what it shows, chapter markers, and suggested cuts for page loads and long pauses. Edit it like any other clip: trim it, add zooms, restyle the cursor, add a voiceover or change the background.
Auto Capture is in closed beta. It's included with paid plans and uses your workspace's AI credits, the same balance the Tella Agent spends, charged when each take ends. Email support@tella.com to ask for access.
Have an AI agent record each new feature with Auto Capture the day it ships. Ask for one take per page or flow, and the agent explores the live product, films it and hands back a recording with chapters and suggested cuts. Any agent connected to Tella's MCP server can start a take, including Claude Code or Codex in your release workflow, and the Tella Agent or your AI app then trims it, adds zooms and captions, and shares it.
Yes, for web apps. Tella's Auto Capture records the walkthrough in its own browser, and the Tella Agent, Claude or ChatGPT then edits it into a finished video: cuts, zooms, captions and chapters. Tella doesn't generate AI narration, so add a voiceover you recorded or record narrated parts yourself. For desktop apps, record your screen with Tella's recorder and let the agent do the editing.
Yes. Give Auto Capture the page's URL and say who the demo is for and what to show or end on. It opens the page in a fresh browser, plans the walkthrough, checks every step works and films it with an animated cursor. The result is a real recording of your live site, not generated footage.
Playwright and Puppeteer film a script you write and give you a raw browser video. Auto Capture writes and tests the script itself from a plain-language request, films it with an animated cursor, and delivers it into Tella's editor with chapters and suggested cuts. No code, and no script to update when your UI changes: ask for a new take.
Only if it's reachable on a public domain. Auto Capture runs on Tella's servers, so it can't record localhost, IP addresses, intranet hosts, desktop apps or mobile apps. Signed-in web apps on a public domain work with a login saved under Settings, then Credentials.
No. Tella doesn't generate AI narration. Add a voiceover you recorded elsewhere as a sound in the editor, or record yourself narrating in Tella and use the Auto Capture take as b-roll over that part.