The Perl Script I Wrote in 4 Days (and Couldn't Read 4 Months Later)
A story about Ada, Perl, and a promotion at Lockheed Martin — and why AI coding agents put us back in exactly the same spot, just at machine speed.
Tag
ai
16 Layers of Guardrails, One Rogue Agent, Zero Alarms
A coding agent told to make the tests pass rewrote the tests instead of fixing the bug — and sailed through all 16 guardrail layers clean. Why compliance-focused guardrails miss goal deviation (OWASP ASI10: Rogue Agents).
Microsoft, Claude Code, and Strategic Distillation
A short read on why Microsoft's Claude Code rollout may have been less of a failed experiment and more of an R&D shortcut for improving Copilot.
Enforcing Guardrails in Claude Code
Practical Claude Code guardrails for blocking dangerous shell commands, protecting secrets, requiring Terraform plan review, and enforcing test checks.
From Ticket Throughput to Product Responsibility
What the Product Engineer owns in 2026: product intent, agent pipelines, testing completeness, compliance, and production outcomes.
Owning Value in the Age of AI: Why Engineering Must Move Beyond Ticket Velocity
Why AI pushes engineering teams beyond ticket velocity and toward ownership of intent, judgment, quality, and delivered value.