Cursor shipped its first native iPhone and iPad app on June 29, in public beta for paying users. It is not a code editor squeezed onto a small screen. It is a remote control for AI agents.
What it actually does
Pick a repo, pick a model, then describe the task by typing or talking. Cursor spins up an always-on cloud agent, or you remotely drive an agent already running on your Mac. Slash commands sharpen the prompt. The agent writes, you review the diff on your phone and merge the PR.
The killer scenario is on-call. Pager goes off at 2am, you point an agent at the incident from bed, it investigates and proposes a fix. Annotate a screenshot to nudge a UI change. Reproduce a bug from a coffee shop.
Why it matters
This is the clearest sign yet that coding is shifting from writing code to managing agents that write it. The phone, not the laptop, becomes the place you assign work.
Cursor is also running Composer 2.5 batch jobs at 75% off through July 5 to get people hooked.
You Might Also Like
- Cursor Composer 2 Takes on Anthropic and Openai With a 0 50 m Token Coding Model and the Benchmarks Back it up
- Roborock Saros 20 Sonic Launches Globally With a 7 98cm Chassis and an Open api Your Home Assistant Agent can Actually Call
- Agent Builder by Thesys When ai Agents Stop Talking and Start Showing
- Entire the 60m bet on Fixing ais Code Review Headache
- Cloudrouter Gives Your ai Coding Agent its own Cloud Machine and Thats a big Deal
Top AI Product 
Leave a comment