You can automate pixel-perfect product tutorials with a cloud agent that has its own computer and records itself using your app the way a human would (like Devin). This has technically been possible for a while, but with Opus 5.5 the results have progressed to something better than what... I make by hand. Devin even made a tutorial showing you how it's done:show more

TLDR: Your cloud agent already has it's own computer. Give it a real account in your system with everything set up, access to your docs, a style guide, and any other resources. Then ask it to create tutorials for you, as a human would. Once you have a good workflow you can create these demos for literally every feature you'd like to in parallel, as cloud agents can spin up hundreds or even thousands of their own computers at once. You can automate the process so that when a new changelog goes up, you trigger the videos to be built simultaneously.

this just 10x’d how we do launches

I only click in your tweets to write my name because you are offering 1 month of Devin and in this tweet I clicked and you didn't offer anything 😡😂

Incredible! can't wait to try this on devin🔥🔥🔥

people were hiring whole teams for this. it's an agent and a changelog webhook

NEED

insane.

Looks so cool!

Need to try it with my Mobile Apps, thanks. Was always a pain to use MCP service like argent and it was not always 100% correct

apple rejected my first app partly for a missing screen recording on a physical device. an agent that records itself using the app is exactly what i needed, if it can hold an iphone

is there anything Devin can't do?

saw that devin clip earlier insane quality

If my coffee could record itself doing the same thing, I'd finally have proof I actually finished it. 👏

Genuine question because I've been wanting to try Devin for so long now: why is this different than just asking Claude to do it directly? What does Devin do here? From my understanding Devin is just using Opus to do this task? I'm excited to try it out later

so Opus does the reasoning and Devin supplies the infra around it most notably and importantly: the ability to run these in the cloud in parallel and in any operating system, each session has access to credentials, ENV, etc.. each one of these videos currently takes around 5-20 minutes to record with computer use, and I'm able to do X (100 for example) at once in ~20 minutes since they each run in their own computer at the same time also being able to trigger them to be created by other systems like when a new features is merged etc.. is important this is probably not a big deal for a small company or surface area, but for most software companies with any type docs it's very valuable and something you just couldn't do before

agents recording their own tutorials is wild

Use Devin to create tutorials for Devin

already better than handmade that's wild, already following you, follow back?

The refresh loop is the big unlock for me. When a feature changes, can the agent spot that its old tutorial is stale, or do you still have to tell it which walkthrough to redo?

an agent recording its own tutorials is a wild turn, the by-hand part being worse is what gets me

My Codex Sub ends tomorrow, should I consider buying devin? 🤔

recording itself on your app was always possible. beating what you make by hand is the part that actually moved with opus 5.5

I wish that @devindesktop harness or maybe even enhanced SWE model with built-in skills for UI/UX designs specialization. In my opinion, most harness has poor performance in designs.