Skip to content
← Made for your kind of work

Vertov for founders & builders

Show your agent what you mean.

Point at the bug. Talk through the change. Give your agent the transcript and, with the extension’s click capture, the pages and buttons you used. If your agent has a recording of its work, it can upload it back for you to review.

Free plan · Starts in your browser

Here’s where the checkout gets stuckInteractive example
checkout-fix.md

# A brief your agent can read

00:04 Opened /checkout

00:08 Clicked “Annual billing”

## The change

Keep the button price in sync
with the selected billing period.

## Review

Upload a recording of the fix.

Example screenBrief with context
Edit by textTry it

Click any word to cut it from the take.

Your first take doesn’t have to be your final take.

Record. Refine. Send.A transcript and captured clicks give your agent context.

An interactive preview of transcript editing. Try it on your own recording when you’re ready.

Made for this part of your day

01

Show the problem where it happens.

Record the flow in your browser. The extension’s optional click capture adds the pages and buttons you used to the recording’s context.

Choose what to showExample
Browser tabWindowEntire screen
A walkthrough of the work.Show the
whole picture.
Ankur in the example recording
Here’s what I had in mind.
Your work, in context
Talking pointsOne quick walkthrough.
Your screen + optional cameraYour voice
02

Hand over something an agent can read.

Share, then Copy for an AI agent, copies a Markdown brief with a summary, chapters and a timestamped transcript. Or connect the MCP server and the agent reads and searches your videos itself.

Interactive example
Your recordingExample
Checkoutyour-app / billing

Pick your billing period

MonthlyAnnual
Continue with monthly
“This label should say annual.”
Context your agent can readMCP / API
# Checkout feedback

00:04 Opened /billing

00:08 Clicked “Annual”

## The change

Make the button label match
the selected billing period.

## Review

Send back a recording of the fix.

An illustrated brief with captured clicks. Connect your agent through MCP or the API.
03

Review the result by watching it.

An agent that already has a recording of its work, from Playwright, a screencast or ffmpeg, can upload it through MCP or the API and return a share link. You watch it and comment on a specific moment.

A walkthrough, ready to send

Here’s the update. The second layout is the one I’d go with.

Example AI summary & chapters

A walkthrough of the homepage and the changes to make next.

00:00 Overview00:12 The first step00:28 Next changes
One link. No viewer account needed.
An illustrated link preview. Your explanation comes with the work.
Read the API and MCP docs

Record, brief, connect, review

From a recording
to your agent.

Each step says what has been checked. Your agent does the work; Vertov supplies what it needs to read and a place to send the result.

Setup commands, every tool and the sign-in flow are in the MCP setup guide. Scripts without an MCP client can use the REST API.

1. Record the issue or the change you want Verified
Record in the web recorder or the Chrome extension and say what is wrong or what should change. Stopping uploads the recording and transcribes it.
A full recording, transcript and brief were checked on production with a test account on 4 November 2026. The extension's click capture was only tested with simulated clicks.
2. Copy a Markdown brief for your agent Verified
In the video's Share menu, Copy for an AI agent puts a Markdown brief on your clipboard to paste into Claude, Cursor or any agent. Anyone who can open the video can copy it, and the same text is served at /api/prompt/<video id> and by the MCP tool get_video_prompt.
The brief was generated and read back through the share menu, the API and the MCP tool on production, 4 November 2026. A private video's brief needs the same access as the video, so a script needs an open link or a signed-in session; MCP covers that case.
MCP tools: get_video_prompt
3. The brief is built from the transcript Verified
It holds the title, link and length, the summary, the chapters, the pages and buttons the extension captured when click capture was on, and the transcript with a [m:ss] stamp on every line. Each stamp maps to ?t=<seconds> on the video link, so the agent can point you to a moment.
A spoken test clip was transcribed and its brief read back on production on 4 November 2026. A silent recording gets no transcript or summary, so an agent's silent Playwright video has only a title and link. Files over 25 MB sent through the API or copied from a URL are not sent for transcription.
4. Connect the agent through MCP or an API key Built, not fully tested
Add https://vertov.app/mcp to Claude, ChatGPT or Codex and sign in, or give a script an API key from Settings, under Agents. Sign-in shows a consent screen (with a workspace choice if you have several) and can be undone in Settings, under Connected apps.
API-key calls were exercised on production. The sign-in (OAuth) flow was tested locally and its discovery documents on production, but not yet inside the real Claude, ChatGPT or Codex apps, so those steps are unverified.
5. The agent reads the recording and transcript Verified
It can list and search your videos, read a video's summary, chapters and transcript, fetch the brief, and list spaces. It sees only what your account can open: your own videos and anything in a space, and workspace owners and admins can open any video in the workspace by its link.
Each read tool was called over production MCP with a test account on 4 November 2026. Listing without a search shows only your own videos that are not in a space or folder; searching also covers videos in spaces.
MCP tools: list_videos, get_video, get_video_prompt, list_spaces
6. The agent writes and reads AI documents Built, not fully tested
From a video's transcript an agent can write an SOP, bug report, meeting notes, changelog, handoff, action items, summary or message, and read one that already exists. Only the video's owner or a workspace owner or admin can; writing replaces an earlier document of the same kind.
AI documents were generated and read on production on 4 November 2026, and get_ai_doc was among the read tools called over MCP. A generate_ai_doc call over MCP is not separately logged. Every account can write them during early access; they are planned for paid plans.
MCP tools: generate_ai_doc, get_ai_doc
7. Your agent does the work Not built
Vertov does not write code or run your agent. Your coding agent makes the change from the brief; whether it can finish a task depends on the agent and the task.
No end-to-end run of an agent fixing something from a Vertov brief has been recorded, so we make no claim about results.
8. The agent uploads a recording of its work Verified
An agent that already has a video file, for example from Playwright, a screencast or ffmpeg, sends it as base64 (the limit is about 15 MB, but the model writes every character, so keep it short) and gets a share link back. Larger files go through the API with a key. The upload uses your workspace's default sharing setting, so check it before a client link goes out.
Uploading a video inline over MCP was tested on production on 4 November 2026 with valid, invalid-base64 and no-data calls. No tool starts a recording of your screen (start_tutorial, a pilot, only records Vertov's own screens on an owner-run runner): an agent needs its own recording source, and Playwright's recordings are silent.
MCP tools: upload_video
9. Other ways the agent can answer Built, not fully tested
It can copy a video from a public https URL into your library, and add a comment, with an optional timestamp, as you.
Copy-from-URL has no logged production run and a failed download leaves the video marked failed. A comment was part of the 4 November 2026 production tests, but the log does not say it went through the MCP tool, so it is not counted as verified.
MCP tools: create_video_from_url, add_comment
10. The whole loop, with a real agent Built, not fully tested
You record a request, the agent reads the brief, does the work and returns a recording you watch and comment on.
Each half has been exercised separately. A run of the whole loop with a real coding agent, recorded for this page, has not been made yet.
What an agent cannot do
No tool records your screen. An agent uploads a file it already has. Separately, owners and admins can have an agent record a narrated how-to of their own verified web app in a hosted browser (record_tutorial); that is not a recording of your screen.
No tool deletes a video or changes who can see it.
Inline uploads stop at about 15 MB; larger files use the API with a key (or a public URL).
A silent recording has no transcript or summary.
A connection acts as you in one workspace and sees only what you can open.

Room for the work. Room for everyone.

Your library grows.
Your seat bill doesn’t.

Team workspace$29/ month
200 hours stored
No seat charge
Add a teammate. The workspace price stays the same.

Priced per workspace. Pick a plan in Settings after you sign in. Only workspace owners and admins can change a plan; the Free plan needs no card.

Free

$0/ month

5 hours stored

Every recording and editing feature, no plan limit on video length.

Start free

Pro

$9/ month

50 hours stored

AI titles, summaries and chapters, and room for a real library.

Choose Pro

Business

$99/ month

1,000 hours stored

A thousand hours for larger teams.

Choose Business

All plans include editing, captions, downloads and free members.

More room: 50 hours for $5/month. Annual billing is 10 monthly payments for 12 months.

Storage is measured by duration, or file size at 2 GB per hour when that is greater. On the Free plan, unwatched videos may be removed after advance email warnings. Read the details ↓

The practical things

Before you
hit record.

Does Vertov make the code changes?
Your coding agent makes the changes. Vertov supplies the recording, transcript and brief, and gives the agent a way to upload a recording of its work for you to review. Whether an agent can finish a task from a brief depends on the agent and the task; no such run has been recorded yet.
What does Copy for an AI agent give my agent?
A Markdown brief: the title, the link and length, a summary, chapters, the pages and buttons the Chrome extension captured when click capture was on, and the transcript with a timestamp on every line. Paste it into Claude, Cursor or any agent. A silent recording has no transcript, so its brief is only the title and link.
What can an agent do through MCP?
After you sign in with OAuth or give it an API key, an agent can list and search videos, read a video’s summary, chapters and transcript, fetch the brief, upload a video (up to about 15 MB inline), copy one from a public https URL, add timestamped comments, list spaces, and write and read AI documents. It sees only what your account can open, and uploads get your workspace’s default sharing setting. No tool starts a recording of your screen or deletes a video (the pilot start_tutorial tool only queues a recording of Vertov's own screens on a runner the owner has set up).
Does the API record my computer?
No. An agent uploads video it has already recorded, for example with Playwright or ffmpeg. You record your own screen through the web recorder or Chrome extension.
Who can use the AI document tools?
Writing and reading a document (SOP, bug report, meeting notes, changelog, handoff, action items, summary or message) needs you to be the video’s owner or a workspace owner or admin. Writing replaces an earlier document of the same kind. On the hosted service, writing them needs a paid plan.
Has the connection been tested in Claude, ChatGPT and Codex?
Not yet in the real apps. The sign-in (OAuth) flow was tested locally and its discovery documents on production; API-key calls and every read tool were exercised on production. Treat connecting from the apps themselves as unverified. The setup guide at /docs/mcp lists the commands.

A few good reasons to hit record

Same recorder.
Your kind of work.

For the team

Keep the project moving.

Client walkthroughs, clear feedback, fewer calls. One workspace price, however many people join.

See this workflow
Homepage walkthroughExample
A walkthrough of the work.Show the
whole picture.
Ankur in the example recording
Here’s what I had in mind.
Feedback, in the right place
C
Client 00:12

Could we give this headline a little more room?

Share controlsPasswordExpiryMembers only
Choose a timestamp. See the feedback in context.

Less explaining. More getting somewhere.

Give your agent the context.

Record a brief

In your browser. No card. No install to get started.

Commands and recent recordings
Actions
Go to
↑ ↓ Select↵ OpenEsc Close