Security
MCP for Internal Tools: Permissions, Scopes, and Boring Success Criteria
MCP is a pipe, not a vault. Secure internal tools with tool-level scopes and boring success criteria.
Articles by Rody
Security
AI Tools & Reviews
Beyond the Demo: Latency, Interruptions, and Fallbacks in Voice AI
Build production-ready AI voice agents by mastering latency budgets, handling interruptions, and designing reliable fallback paths.
Automation
Browser Automation in Practice: Where Playwright Ends and AI Agents Begin
Playwright is the engine, but AI agents are the driver. A practical guide to the 2026 hybrid automation stack.
Automation
WordPress Automation That Does Not Eat Itself: Duplicate Gates, Drafts, and Editorial QA
Prevent draft chaos and duplicate gates by building resilient WordPress workflows that prioritize editorial integrity over blind automation.
Technology
Internal Dashboards That Survive Reboots: Health Checks, Process Managers, and Boring Recovery
Internal dashboards often fail silently after reboots. This guide covers health checks, process managers, and boring recovery strategies for resilient tools.
Developer
Self-Hosted Observability for Tiny Teams: OpenTelemetry, Langfuse, and Useful Alerts
Tiny teams can build production-grade observability on a shoestring using OpenTelemetry and self-hosted Langfuse.
AI Tools & Reviews
Stop Shipping RAG Blind: A Practical Guide to Pre-Launch Evaluation
Stop shipping RAG blind. Learn to test retrieval and generation accuracy, detect hallucinations, and build a grounded evaluation suite before launch.
Developer
Next.js 16.2 Agent DevTools: Debugging Production Frontends Without Drowning in Logs
Next.js 16.2 unifies debugging with Agent DevTools and browser log forwarding, enabling efficient AI-assisted production debugging.
Automation
Automation
Human-in-the-Loop Automation: When Approval Gates Make Systems Faster, Not Slower
Strategic slowing down is an accelerator. Approval gates prevent catastrophic rollbacks and build the trust required to scale autonomous systems safely.
Automation
Stop Guessing: How Structured Outputs and Repair Loops Fix LLM Automation
Stop guessing with LLM outputs. Learn how structured outputs and repair loops create reliable automation.