@markfenner: Devin can turn “tested” into a video receipt. After it creates a PR, click Test the app. @DevinAI reads the diff, creat…

X AI KOLs Timeline Tools
ai-testing dev-tools video-receipt pull-request automated-testing

Summary

Devin, an AI tool, now provides video receipts for app testing by generating test plans, executing user flows, and delivering annotated recordings to visually verify work.

Devin can turn “tested” into a video receipt. After it creates a PR, click Test the app. @DevinAI reads the diff, creates a focused test plan, starts the app, clicks through flows like login, forms, and checkout, then sends back an annotated recording. That gives you more than a green check and a completion message. You can actually watch the work being verified. Desktop mode must be enabled. On macOS Outposts, screenshots require Screen Recording permission, mouse and keyboard control requires Accessibility permission, and video capture requires ffmpeg.
Original Article
View Cached Full Text

Cached at: 08/22/26, 01:25 PM

Devin can turn “tested” into a video receipt.

After it creates a PR, click Test the app. @DevinAI reads the diff, creates a focused test plan, starts the app, clicks through flows like login, forms, and checkout, then sends back an annotated recording.

That gives you more than a green check and a completion message. You can actually watch the work being verified.

Desktop mode must be enabled. On macOS Outposts, screenshots require Screen Recording permission, mouse and keyboard control requires Accessibility permission, and video capture requires ffmpeg.

Similar Articles

@dabit3: Underrated feature of advanced cloud agents like @devinai: Infinitely parallelizable human-grade UI testing. They - Sta…

X AI KOLs Timeline

This tweet highlights that advanced cloud agents like Devinai can perform infinitely parallelizable human-grade UI testing by setting up environments, inspecting code, planning e2e tests, handling authentication, using computer vision and mouse-and-keyboard control, and returning annotated video proof, with reusable skills for faster future verification.

Verifying Agentic Development at Scale (8 minute read)

TLDR AI

Cognition's Ido Pesok shares lessons from building autonomous end-to-end testing into Devin, noting that for the first time, more Devin sessions are now triggered asynchronously than interactively, making verified-before-merge results a hard requirement rather than a nicety.