I checked 1,598 coding agent PRs and 1,119 human PRs from the same public repos. Agents changed tests about as often as people, almost always for a reason.
Coding agents weaken tests about as rarely as people do
Related
How our Pipeline orchestrates LBO Due Diligence ?
Welcome to the third chapter of our four-part series, **Building Sovereign, Hallucination-Free...
Orchestrating Agents: The Graph Is Yours, the Judgment Isn't
Verified on 2026-11-13 against strands-agents 1.63.0, Python 3.11 and Bedrock in us-east-1. Every...
Vibe coding vs spec-driven development with Claude Code: we built the same app both ways
We wanted to know what it really takes to ship a public app with Claude Code when you don't write the...