Building and implementing agentic AI systems, autonomous workflows, and practical agent patterns.
Best starting post:
From Vibe Coding to Agentic Engineering: What this Means for Software DeliveryRecommended next read:
Tech Horizons 2026: Agentic AI, Hardware Realities, and What's Actually Coming
As coding agents take on more engineering work, model reliability and pricing quietly become delivery risks. This post covers the operational gaps most teams haven't addressed yet.
The UK's NCSC says AI-generated software and vibe coding are inevitable, so security leaders should focus on guardrails and assurance now instead of pretending adoption can be stopped.
Nvidia built NemoClaw to put guardrails around OpenClaw. Meta is firing people for installing it. Microsoft says don't run it on your workstation. Here's what engineering leaders need to know about the security reckoning unfolding around agentic AI.
Anthropic's Claude Cowork brings agentic AI out of the terminal and onto the desktop. Let's look at how it works, why Wall Street panicked, and what it means for how we work.
Vibe coding lowered the barrier to building. But what happens next (security, resilience, maintainability) is where engineering experience starts to matter. This is my take on the journey.