Arsaze
Engineering

Cursor for video editing: what changes when a timeline is something an AI can read

September 20, 2026

Cursor works because code is text.

A model can read the whole repo, change one line, and you can check the result. The models didn't get a special upgrade to make that happen. The material was already in a shape they could handle.

Video isn't. In most editors the timeline is a project file only that editor understands, and the footage under it is just pixels and audio. An AI can watch an export and tell you what it thinks. It can't reach in and move a clip.

That's the gap we built Arsaze around.

What Arsaze is

Arsaze is an AI-native video editing OS from Sidhilynx, a company based in Chennai. Every capability in it (cutting, trimming, moving clips, searching footage) is exposed as an API and MCP tool first. The editor in your browser is one client of those tools, not the thing they hang off.

Internally we call this AI-first, human-second. It sounds harsher than it is. It just describes the build order.

The order matters

Most editing software was made for a person with a mouse. AI showed up later as a panel or a menu item. That works until the AI needs to do something the menu doesn't have.

We went the other way. The primitives came first: add a clip, cut it, move it, trim it, find a scene. Once those existed as clean operations, the human UI was mostly a matter of putting buttons on them. The AI never needed a special path. It calls the same operations you'd trigger by clicking.

Claude, ChatGPT, Gemini and Grok can all connect over MCP and work on a real timeline today. Not a demo reel, the actual surface.

A timeline that knows what's in it

A list of clip names and timecodes isn't enough. What an editor reasons about is content: who's speaking, what's on screen, what just got cut.

Arsaze keeps the timeline as structured state that includes what's in the footage, and it updates as you edit. Trim a clip and the system's understanding of what's now on screen and in the audio changes with it. Cut the sentence where the speaker names the client, and the AI knows the name is gone. It doesn't have to re-watch anything to find out.

I'm keeping the how to ourselves for now. The what is simple: the AI works from what's really in the cut, not from what was in the raw file.

Finding the shot

An agent that can't find the right footage is guessing. So everything that goes into Arsaze (video, audio, images) gets analyzed and indexed, and you can search thousands of assets by scene or by spoken word in under a second.

Most of the value here is boring, which is fine. "Find every take where she mentions pricing" used to eat an afternoon. Now it's one query, whether a person types it or an agent does.

A request like "take this interview, pull every answer about pricing, cut it to a tight piece, caption it" maps straight onto operations Arsaze already exposes: search, cut, arrange, caption.

Watching it happen

Open a project in the browser and you can watch an AI edit it live, including Claude connected over MCP. Cuts land. Assets get searched. The playhead jumps around.

We put a lot of effort into making this look good, probably more than was strictly reasonable. Waiting on an AI is easier when you can see what it's doing.

For developers

Because the UI is only a client, there's no gap between what the product can do and what the API can do. If you can click it, you can call it. That's the part I'd want if I were building on top of a video tool, and it's why we didn't build the API as an afterthought.

The manual tools are still there

Nothing here takes the editor away from you. Rewrite lets you edit the video by editing its transcript. Auto Cut strips silence, or specific words you name. Auto Captions works down to individual words. Instant Voice Cloning takes under a minute, and Voice Over records in the browser while the timeline plays.

Use them by hand, or hand them to an agent. Same tools either way.

What I'm not claiming

Video editing isn't solved. An agent doesn't replace someone with taste, and taste is most of the job.

What changes is the middle: finding footage, assembling a first pass, tightening, the fixes nobody wants to do by hand at 11pm. Once you're dealing with hundreds of clips, some of that is tedious enough to be impractical without help.

Try it

If you build with MCP, connect an agent, give it a real timeline, and tell us where it breaks. If you edit for a living, hand it the tedious pass and see what comes back.

Arsaze is live at arsaze.com.