Anthropic measured how AI coding habits shifted across 400,000 Claude Code sessions

Anthropic analyzed 400,000 real Claude Code sessions from Oct 2025 to Apr 2026. Debugging sessions dropped from 33% to 19%, while ops and writing/data analysis each roughly doubled. About 56% of sessions involve direct coding; over 40% don't center on writing code. Humans handle ~70% of planning decisions, agents ~80% of execution decisions. Novice verification success is ~15%, intermediate+ jumps to 28%–33%, but in hard sessions novices succeed only 4% vs. 15% for experts. Three practice directions: add acceptance criteria before prompting, locate the deviation point when stuck instead of restarting, and break tasks into multi-step workflows. Data covers interactive sessions only, no CI pipeline calls. Success signals are CI pass, green tests, or user confirmation—no long-term maintenance cost measured.

Why it matters: Anthropic's usage analysis from 400K real sessions brings proprietary data, concrete numbers, and behavioral trend judgments — not a press release. All three HKR axes hit. Not 85+ because this is a usage report, not a product launch; impact is softer than a model or capability...