A few weeks ago I found out DaVinci Resolve has an MCP connection now (it came in Resolve 21.1), which basically means it allows your AI agents, like Claude or Codex, to connect to it. Since then Claude has edited my last three YouTube videos. I just record everything, drop it into a folder and talk to Claude in plain English. In the latest one I show the whole thing on my screen.
Watch it here: [I think I've solved procrastination](https://youtu.be/3mlRiF-LeMc) (10:35, on YouTube).
Plenty of people have already shown the setup on YouTube ([this one](https://www.youtube.com/watch?v=DF67ZE7BIgs), for example).
I'm not a content creator. I might have made a few reels here and there, but I had not created proper content until now. It's been on my list for a long time to start a YouTube channel, and the reason I kept pushing it off is that I just did not have the time to learn DaVinci Resolve or any of the editors. I've been a developer since as long as I can remember. I have a couple of businesses, I build AI solutions for companies as well, and on the side I built a safari lodge in the Maasai Mara, Kenya, because my parents live there. I have slowly learned how to put things together in a coherent fashion, but it still does not feel like a premium thing.
What I actually do now #
- Record everything. You're going to make mistakes, you're going to say um, and you're going to redo things, especially when you're new. I don't worry about any of it.
- Drop the files into a folder, give Claude the path, and add a thought dump of what I want. Mine are dictated with Handy, a voice-to-text app, and they're not coherent (the baboon one was about a minute of me talking). It doesn't matter.
- Go do something else. The baboon reel in the video took about 57 minutes. I read a book, walk around, play with my dog.
- Answer the questions. Where I have two or three good takes, it doesn't decide on its own. It builds a separate timeline that plays option A, then B, and asks me for something like "1A 2C 3B". I reply in one line and hit enter.
- Watch the cut and send notes. For the last video that was three trims and one idea.
There's only one step you have to do the first time. Go to File and click on Setup AI Assistants. That brings up a window which asks you which AI assistant you want to connect (Claude, Codex, ChatGPT or something else). I selected Claude and clicked install. You might also have to set Preferences → System → General → External scripting to Local. Unfortunately all of this is only in DaVinci Resolve Studio, the paid version.
What Claude does #
The cutting happens in Resolve, through its scripting API. Claude decides which takes and sentences stay, cuts the ums and restarts, shortens the s and speeds up the slow stretches a little. Everything around the cut runs on my Mac outside Resolve, in Python, ffmpeg and a headless browser. It transcribes the clips with Whisper, builds the motion graphics, the music bed and three thumbnails to pick from, then brings the results into the timeline and renders the 4K export. Before it tells me a version is ready, it re-transcribes the finished cut to catch a clipped word or a filler it missed, and checks the loudness.
Here are the three videos side by side.
| Video 01 | Video 02 | Video 03 | |
|---|---|---|---|
| Published | Sep 27 | Oct 1 | Oct 6 |
| Raw footage | 15:46, talking head | 15:40, 4 clips | 28:42, talking head + 2 screen recordings |
| Final cut | 7:00 | 9:58 | 10:35 |
| Timeline versions | 11 | 7 | 5 |
| Motion graphics | 23 | 37 | 23 |
| What I did | recorded, 6 A/B picks, 1 audio pickup, trimmed overlays by hand, picked the music and thumbnail | recorded, 5 A/B picks, 3 audio pickups, 2 trims, picked the music and title, combined two thumbnails into one | recorded, 5 A/B picks, 4 notes, picked the thumbnail, set the playback frame rate |
My second video had a few concepts where I was explaining things, and it was better if there was something to look at. Just my face is not enough. So I told Claude it's good at animation, don't even ask me what I want, go through the video and wherever you think there needs to be some motion graphics, just do it. This was before I slept. The next morning the result actually shocked me.
What went wrong #
- In the baboon reel the audio came out crumpled. I remember this happened in my previous video as well, so I told it the audio is crumpled, something is weird. I didn't even know what the technical issue was. Claude found two. The mix was clipping, and the project was playing back at 24 fps against footage shot at 29.97. A new Resolve project defaults to 24, and Resolve's scripting API won't change that one setting, so it has to be clicked in Project Settings → Master Settings. For video 03 I did that myself.
- In video 01 I trimmed some overlays by hand so my face showed through. Claude then rebuilt that timeline from its own scripts, and my trims were gone. Now it never rebuilds. It duplicates my latest version and patches the copy, so every old version is still there.
- Resolve crashed in the middle of video 03, after hours of edits. My message was "Davinci just crashed. I hope we didnt lose anything". We didn't, because Claude saves the project after every step.
In the baboon reel I said baboons are herbivores, and Claude flagged it. Oh yeah, baboons are not herbivores, I should have said omnivores. So he's right. It's going through the video, making sense of it, and discussing with me, like things that I've said that are wrong, or "are you sure you want to do this?"
What I still do #
I don't think this is slop, because it's not completely AI driven. You're the one that's still shooting. It still takes a little bit of courage to come in front of the camera and talk your mind out to the public.
In video 03 I told it some parts I'd spoken later could be brought up front, like the bit about the lodge. Claude offered a cold open that flashed forward to the reel, and what I typed back was "THat abrupt random final clip showing up in 1A felt jarring to me", so it went. In one part of that video I'm talking to Claude and not to the audience, and my note was "because I'm suddenly talking to claude and not the audience, I feel like there needs to be a more distinct change - like maybe take the entire frame and make it smaller and black and white or a different hue". Claude built that version.
What I'm saying does not apply to everyone. If you're already creating content, if you're already a good editor, please don't listen to me.
What it costs #
I think Resolve Studio is a one-time sort of $300 payment (it's $295 in the US). I bought it in a Black Friday sale last year, thinking maybe I'll use it, maybe I'll not. Hiring an editor, you might pay something like $300 for a couple of hours. Here you have an editor you can annoy as much as you want.
On the Claude side I'm on the Max plan (20x). The first pass of the baboon reel, the 57 minutes, used about 2–3% of my weekly limit. That might be expensive for some people, but for converting shitty raw files into something decent and presentable, I think it's worth it.
Is video editing next? #
The way code has kind of been solved right now, I feel like video editing might be solved as well. Obviously art and creative things will always have their own place, and AI will find it tough to sort of match or beat that. But for most of the normies out there like me, I think this is a great thing. We can focus on our own creative takes and let AI do the heavy lifting of getting it to a polished state.
There are many more products doing similar things. I keep seeing ads of AI video editors and people posting about them.
I've not pushed the limits of this yet. I don't know where it breaks down.
— NJ