@ericzakariasson: https://x.com/ericzakariasson/status/2062199026544787576
Summary
Cursor introduces Debug Mode, which lets the AI agent instrument code, collect runtime logs, and fix bugs based on actual evidence instead of guessing, improving accuracy and handling hard-to-reproduce issues.
View Cached Full Text
Cached at: 06/03/26, 05:53 PM
Don’t let your agent guess, give it runtime context
If you’ve ever watched an agent try to fix a bug, you’ve watched it guess. It reads the code, comes up with a theory, makes an edit, and hopes. Sometimes it’s right. A lot of the time you get a fix that looks confident and quietly hides the real bug.
Debug Mode is what we built for that. Instead of sitting there reasoning about the code, the agent goes and gets evidence about what the code does when it runs.
Here’s the loop
-
Agent comes up with multiple hypotheses, and starts to work on the most plausible first
-
Then, logging is added to test one hypothesis (without touching implementation)
-
A little debug server collects the runtime output to .cursor/debug.log while your program runs.
-
You reproduce the bug, and agent can now read the logs and understand what happened instead of having to guess
-
Cursor finds the root cause in the logs, makes the fix, and pulls out the logging it added.
Here it is on a real bug, sped up to about a minute:
eric zakariasson@ericzakariasson·May 5here’s me using debug mode to fix a small bug in an swift app i just built
issue was the initial characters were cut off when typing it out, so i had cursor
- instrument the code
- ask me to reproduce the issue
- read the debug logs
- implement the fix
- ask me to reproduceShow more0:569618515K
How the team uses it
Some interesting things that we’ve solved internally with debug mode:
-
A race condition that hit 1 in 20 runs. It was corrupting git metadata in our best-of-N runs. Debug Mode pinned it down in under an hour
-
A memory leak, traced in one pass. It came down to a misuse of our frontend framework. The fix was a single line.
-
A native crash deep in C++. An Electron crash people would normally route around. The logs made it findable.
-
An SSR flicker that had been given up on. A rendering bug nobody wanted to touch, fixed once the agent could see what the page was doing at runtime.
Try it with Shift+Tab (it’s in the CLI too, via /debug).
I’m sure people are using it in ways I haven’t thought of, so let me know!
Similar Articles
@cursor_ai: We recently shipped quality-of-life improvements to the Cursor CLI to make working with agents in the terminal more del…
Cursor CLI adds /debug command to help agents quickly find and fix hard-to-reproduce bugs in the terminal.
@leerob: https://x.com/leerob/status/2065469795529588940
Cursor AI describes its recursive agent system for scaling training of its Composer model, using a fleet of agents that self-manage and alert humans when issues arise. The system enables parallel experiments and accelerates research, treating researcher time as the scarcest resource.
@eladgil: https://x.com/eladgil/status/2079561730263531771
Cursor's team of AI agents reconstructed SQLite from its manual into Rust, passing all tests, with costs varying 15x based on model mix.
@sjwhitmore: We're trying a new experiment at @cursor_ai - interviewing devs we admire. I chatted with @oneill_c & @part_harry_ from…
Cursor AI launches a new interview series with developers, starting with a conversation with the Baseten team about their use of coding agents, current workflows, and future predictions.
@kentcdodds: Y'all are sleeping on how good @cursor_ai is. It's easy more than the desktop or mobile app. Their cloud agents and bug…
Kent C. Dodds praises Cursor AI's cloud agents and bugbot as critical parts of his software factory, while Debbie O'Brien highlights the underrated mobile experience.