MSManos Saratsisindromeas.hashnode.dev·Sep 17 · 8 min readBehavioral Bugs Are Still Slipping Through AI Code Review. Here's What Actually Catches Them.Originally published on the Dromeas blog. The pull request looks clean, the linter's green, the tests pass — and the code still does the wrong thing the moment someone hands it an input nobody thought00
MSManos Saratsisindromeas.hashnode.dev·Sep 13 · 8 min readShadow AI in Your Codebase: The Governance Gap Most CISOs Haven't Mapped YetYour AI code governance policy probably covers the tools you approved. It says nothing about the ones your developers are actually using. That gap has a name now, shadow AI, and in 2026 it's stopped b00
MSManos Saratsisindromeas.hashnode.dev·Sep 13 · 5 min readWhich AI Model Writes the Most Secure Code? What the 2026 Data Actually ShowsAsk five engineering leaders which AI coding model is "safe," and you'll get five confident, contradictory answers — most of them based on a vendor's marketing page rather than an actual security test00
MSManos Saratsisindromeas.hashnode.dev·Sep 9 · 3 min readMCP for Code Review: What It Is, and How to Add a Review Layer to Claude Code or CursorOriginally published on the Dromeas blog. Your coding agent writes code. MCP is how you give it a reviewer. Here's what the protocol actually does — and a working setup you can copy in minutes. MCP, i00
MSManos Saratsisindromeas.hashnode.dev·Sep 9 · 4 min readPR Review vs. Trunk Review: A Practical Guide to Choosing (or Combining) BothOriginally published on the Dromeas blog. PR review and trunk-based review solve different problems, and most teams already run a hybrid without naming it. This guide is backed by data from 100,000+ r00
