JetBrains studied 4,782 real coding-agent sessions.
~94% of SWE-Bench Pro tasks are features or bug fixes. In real use, thatโs under half. The rest: explaining code, planning, reviews.
No benchmark is universal. Measure how your team uses agents.
Weโre opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
This feels short-sighted. The goal shouldn't be to measure the productivity of your individual developers.
The goal should be to build a system (i.e software factory) that minimizes the need for developers to be in the loop (i.e maximizes agent autonomy).
What if your AI budget went to the engineers who use it best?
Blanket usage caps are a hiring freeze in disguise.
Introducing efficiency-based auto-approvals for your most productive engineers, plus Devin Coach to help everyone get there.
https://t.co/or2tz1XOmw