1 min lesson
How agents reshape the coverage problem
Work through this: "Cursor's security team says agents have 'lowered the bar on the level of depth we can cover for all changes.' What does that actually mean, and why is it a bigger deal than just reviewing faster?"
Step 1 of 2
Security has always been a sampling problem. No team reviews every PR in real depth, threat-models every change or ramps into every unfamiliar system. Capable, tireless agents move the bar on all three at once.
This is worth understanding even for an interview, because it's how the role's impact actually shows up day to day. Cursor's security team frames the payoff not as finding more bugs faster but as covering depth that was never tenable before.
The point isn't speed for its own sake. It's that practices which used to be a luxury - deep review on a sampled few changes - become the default on every change.
What it's really done in my opinion is lower the bar on the level of depth that we can cover for all changes. Things like threat modeling for any change that were previously untenable are now tenable.
The honest version of the math: on older models one engineer described agents as making him roughly 5x more effective, and closer to 7.5–10x now. Take the multiple loosely. The durable claim is that the value isn't doing the same work faster - it's doing more to protect the business and ramping into systems you've never touched in hours instead of a week.