Joshua Boys

Doing a little side project in Cursor and I ve observed a pattern each time I ask it to implement a tiny feature close to my authentication code, it rewrites some parts of the authentication process that were untouched by me, in a manner that seemed more elegant but actually affected the functionality. Even removing a session expiration check at one point during some unrelated refactoring.

No errors have been thrown. My tests have passed since I didn t have a test for such a scenario, which was found out when I accidentally kept myself logged in for much longer than expected.

I created an awesome dashboard. MRR, signups, DAU, churn, one chart each. I stared at it religiously for months, but it never once gave me a clue as to what to do next.

What I do look at now is a Slack channel, that tells me whenever somebody takes their first action within the product, along with when they signed up. If the interval becomes bigger than ten minutes, I know something's broken in our onboarding. It has spotted two bugs before users reported them.

I ve run into this with longer agent runs and I m curious how others handle it.

The original issue might contain the scope, constraints and evidence required. But when another model or session picks up the work later, those conditions often get reduced to a summary.