“The background agent produces a PR that passes CI but is functionally incorrect. This is the most serious error, as it erodes trust in our automation. When performing changes over thousands of components, these changes are hard to spot in reviews.”
Quote · engineering.atspotify.com
From “Background Coding Agents: Predictable Results Through Strong Feedback Loops (Honk, Part 3)”, found 2026-10-14.
Their answer is to verify before the PR exists. The agent runs every relevant verifier through Claude Code’s stop hook, and if one fails, the PR is never opened.