If AI coding is lowering your code quality, you’re not managing quality rightkept by kotsakis • sep 28With layered quality practices like spec-driven development and AI-assisted testing, coding agents can double output without increasing bugs.AboutSentry · Claude · Codex · Copilot · Cursor · FullstoryFiled#ai-coding#developer-tools#productivity#quality-assurance#software-engineeringRelatedMCP, Skills, and AgentsSkills and MCP tools serve different but complementary purposes for coding agent harnesses, and neither replaces the other despite hype cycles claiming otherwise.also on Sentry, Cursor, #ai-coding, #software-engineering, #developer-toolsclaude code is not making your product betterCoding agents increase senior engineer output but not product velocity, as the bottleneck is product taste and complexity management, not code production speed.also on Sentry, Cursor, #software-engineering, #productivity, #developer-toolsagent-skills/skills/autoreview/SKILL.md at main · openclaw/agent-skillsThe piece defines a structured pre-commit code review skill for AI agents, specifying contracts, scope governance, and engine isolation across multiple review engines including Codex, Claude, and others.also on Copilot, Cursor, Codex, Claude, #ai-coding, #software-engineering, #developer-toolsThe cost of caring about software - Alex Rios SubstackAI reduces code-writing effort but shifts verification cost onto reviewers, creating an externality where comprehension debt rises despite faster generation.also on Copilot, Cursor, Claude, #ai-coding, #software-engineering, #productivity, #developer-tools
If AI coding is lowering your code quality, you’re not managing quality right