Engineering video
1:09 · 16 October 2026
An AI agent takes rough bug reports and screenshots, virtualizes the application using Cypress and Playwright with mock production data, reproduces the issue, records a video, and automatically generates a structured board ticket.
Hear it at 0:00 →So basically the refinement agent would try to scope it, figure out the blast gate, you know, reproduce it and then it ends up creating a ticket here in our board. And as you see here, all those tickets have been created by agent. So I usually give them a very rough screenshot and like, okay, can you check this? Is this a bug? Somebody reported this. I have a button in our application where if I get a user message, I just click report a bug and it gets straight into this pipeline. And they do all the hard work.
Uh they use Cypris and play right and they can virtualize the whole application. They have mock production data. And so they can try and reproduce the exact same bug. And they usually take a video with play right so I can even see they reproduced it and they attach that to the ticket and this is how a ticket looks like. Now, a big problem with AI is that tickets are very bows right now and that's something I would work on later. But as you see, it's trying to go over to steps to reproduce it, scope, acceptance criteria and repro evidence and usually it has screenshots and videos, direct figure out okay where the issue is. So rather than me
giving you even code, I usually give you a high level box and figure out do I really need to get into the code. So that's what the refinement agent would be. That's the final result of the refinement agent. It's the actual scope down ticket
