April 10, 2026
Poor deadlines, unrealistic timelines, pressure to finish a project on time, or lack of knowledge, often result as of what we call technical debt. The concept […]
April 2, 2026
There have been a lot of AI-related headlines lately. In this post, I’m questioning whether the investment in Artificial Intelligence will be worthwhile. The Purpose Of […]
March 28, 2026
My new course Generative AI Stakeholder Alignment is LIVE on Pluralsight! 95% of organisations get little return on their AI investments. Not because the technology fails, […]
March 26, 2026
In today’s threat landscape, security teams need more than fast detection—they need confidence in recovery. Commvault’s latest announcement marks an important step forward by deepening its […]
March 25, 2026
There is a point where diagramming starts to feel like admin. You are in the middle of thinking through an architecture, a delivery workflow, or a […]
March 21, 2026
Andrej Karpathy recently published a visualisation tool at karpathy.ai/jobs that maps every occupation in the US economy against AI exposure. It is built on Bureau of […]
March 15, 2026
Generative and agentic AI have reshaped software development in a few short months. This is more than asking a chatbot for help; it’s a mindset shift […]
March 14, 2026
Keeping up with long-form content is one of the biggest time sinks for developers and knowledge workers. Podcasts, conference talks, and YouTube tutorials are invaluable sources […]
March 13, 2026
What happens when the agent itself becomes the threat? Not because of a prompt injection (ASI01) or tool misuse (ASI02), but because the Claude model produces […]
March 13, 2026
Your health data agent says: “Your sleep quality improved 23% this month compared to last month.” You adjust your bedtime routine, change your medication timing, or […]
March 13, 2026
Your AI agent depends on a chain of services. In my side project (Biotrackr), the chain looks like this: Claude API for reasoning, APIM for routing, […]
March 13, 2026
Biotrackr is a single-agent system. One agent, twelve tools, one identity. That is an architectural choice that eliminates an entire vulnerability class Insecure Inter-Agent Communication (ASI07). […]