I like OpenAI Codex but not a fan of the delays and the rebuilding and refreshing etc.
Can you please suggest the best way to get a tight feedback loop?
Ideally: I can speak a command to affect the code and I see the page refreshed as soon as it is parsed and executed.
Like for a dev server? Are you using a file watcher? I also find a test watcher helpful to increase confidence in the agents changes.
Recently, the cursor agent panel supports multiple tabs and sometimes I use that to kick off multiple non conflicting agents. You may prefer a separate window. Further, to avoid file conflicts completely, you could use a git work tree.
Yes a dev server. I can use a file watcher and on the JS side do the automatic page refresh there too, but was curious about local options. I haven't tried Cursor.