Card #1544 · Cursor (AI IDE)
Automations lack computer and browser use capabilities
Merchants want cloud agents in automations to be able to use a browser to test changes and verify fixes. They need the ability to take screenshots or recordings as proof of successful execution and include them in pull requests.
Pain score
0.56/ 1.00 · weighted product of four components
Reach0.63distinct authors (log-normalized)
Recency0.63freshness decay, half-life months
Engagement0.41upvotes + comments, normalized
Monetization0.50willingness-to-pay cues in evidence
§ Evidence — 3 verified quotes
some reliable way to let the agent “proof” via video and/or screenshot that it fixed something that got triggered via an automation would be incredible helpful for us.
A big use case for the cloud agents is having it be able to test the changes in the browser, take screenshots/recordings, and “prove” to us (and itself) that it works.
I feel like computer use is even better for automation than the normal agent, as it’s the one time I actually won’t be at a computer to use it and that’s kinda the point.
Comments are a Pro feature — join the conversation, share what you've shipped, hear what others are building.
Upgrade to Pro