# Code Review

- [92% of AI-Generated Codebases Have Critical Vulnerabilities. Here's Why Agentic Review Is the Fix.](https://sdd.sh/2026/04/92-of-ai-generated-codebases-have-critical-vulnerabilities.-heres-why-agentic-review-is-the-fix..md): The 2026 AI Coding Impact Report reveals that 100% of engineering orgs are shipping more code thanks to AI — and security teams are drowning. 92% of AI-generated codebases contain critical vulnerabilities. The answer isn't less AI. It's better AI review.
- [Five Claude Code Features That Don't Make Headlines But Change Everything](https://sdd.sh/2026/04/five-claude-code-features-that-dont-make-headlines-but-change-everything.md): The benchmark releases get the press. The unglamorous power-user features don't. Here's what /ultrareview, auto mode for Max, xhigh effort, /recap, and the new prompt caching TTL controls actually change about your daily Claude Code workflow.