Agentic Engineering Research

Early findings from benchmarking agentic coding - productivity multipliers, speed to value, and software quality.

Measuring the productivity multiplier of agentic coding vs pre-AI baselines across churn and net code metrics.

Lead time distribution insights - from days and months to minutes and hours. Based on 153 tickets measured from intent to main-branch merge.

Proving agentic coding doesn't trade speed for quality. Enterprise-grade standards achieved in under 3 days on a ~100k LOC codebase.