A structured 90-day study of AI coding tools across a 70-engineer enterprise team, measuring PR velocity, defect rates, adoption patterns, and ROI. The results were not all positive — and the most important finding had nothing to do with speed.

Agents — Analysis of JetBrains 2026 Developer Ecosystem Survey The landscape of AI‑assisted software...

One study of roughly 800 developers found that engineers using an AI coding assistant produced 41% more bugs, with no meaningful gain in throughput.