Building with AI
Start with the curated reading path, or browse related writing below, newest first.
- Send Your AI Assistant to My MCP Service --
A working example of asking an AI assistant to use my public MCP service, with plain-language prompts and the curl command behind tool discovery.
- Give Your MCP Service a Predictable Address --
A practical naming convention for business MCP services: use mcp.yourdomain.tld and publish clear connection instructions.
- Your Next Customer Might Send an AI Agent --
Preparing your business for AI-assisted customers starts with reliable answers, clear permissions, and one useful interaction.
- I No Longer Think Python Is the Most Important Programming Language I Know --
Pseudocode has become the design language of AI-assisted software engineering, where clear intent and system judgment matter more than memorized syntax.
- Semantic Objects Come Before Semantic Indexes --
A semantic index is only as good as the object model underneath it: meaning, metadata, provenance, and classification define what the index can preserve and improve.
- Semantic Indexing's Dirty Little Secret: Entropy --
Semantic indexes age as organizational meaning shifts; durable semantic infrastructure needs provenance, review, and rebuild paths, not retrieval alone.
- Token Accounting and the Flow of Machine Cognition --
Token accounting treats AI usage as an observable flow of machine cognition, not merely a billing line item.
- Local-First AI: Put the Control Plane Back Inside the Business --
An architecture option for model-assisted routing, with permissions, budgets, and approvals enforced independently of the model.
- Chaos Is the New Order --
A reflection on operating through continuous shocks by balancing efficiency with resilience, adaptability, and faster feedback loops.
- Runtime Isolation Is Not Governance --
AI agent runtimes solve the execution problem, but serious autonomous systems also need governance, authorisation, escalation, and provenance.
- AI Can Generate Software. Reality Still Gets A Vote. --
AI-assisted software has lowered the barrier to building, but real systems still need structured review, operational judgement, and respect for consequence.
- Building for the Break: Why many of today’s public MCP servers are an accident waiting to happen --
Why public MCP servers and agent-facing tools need governance before the first preventable failure.
- The Morris Worm Moment for Autonomous Agents --
Why mature systems design often arrives just after the first preventable incident.
- Agent Readiness Is a Design Discipline --
Agent readiness is a structural property of a system, not an AI feature.
- The Confidence Trap: How AI Turns Beginners Into Believers and Veterans Into Cynics --
There’s a strange and slightly hilarious thing happening in the tech world right now. The people who most need to hear warnings about AI are the same people who are least capable of understanding them. Not because they’re stupid. Not because they don’t care. But because they literally do not yet have the cognitive tools
- AI Isn’t Killing Creativity — It’s Killing “Good Enough” --
An argument for using AI to move beyond generic output, with human judgment, originality, and direction at the centre of creative work.
- Grimm Truths of the Goldilocks Paradox: Why Your AI Strategy Needs a Fairy-Tale Wake-Up Call --
Once Upon a Time (But Not Really) In the comforting lull of corporate strategy sessions, AI often gets talked about like it’s porridge—too hot, too cold, or “just right.” That neat framing—the Goldilocks paradox—is appealing. It suggests you can simply find the middle lane, settle in, and all will be well. But let’s be blunt.
- When Automation Becomes Noise: Fighting AI Fatigue with Meaningful Tech --
TL;DRWe’re drowning in shallow AI tools—auto-content generators, SEO spam bots, and “smart” chat widgets that no one trusts. The pendulum is swinging back. People want tech that respects their time, privacy, and intelligence. The next wave of automation isn’t louder—it’s smarter, smaller, and more human-aligned. The Overload is Real AI hype is everywhere, and so
- How AI Will Transform Training and What It Means for Solopreneurs & Small Businesses --
There’s no polite way to say this: AI is going to disrupt the world of coaching, training, and small service businesses in a big way. If you sell expertise—especially in areas like social media strategy, SEO, content marketing, or general business coaching—you are standing in the path of a tsunami. But here’s the thing: you
- Just Over 1000 Saturdays Left: A Midlife Reality Check (With Laughs) --
I turn 56 next week. That’s 2,912 weeks down—give or take a few summer vacations lost to flu, heartbreak, or regrettable life choices. If we go by the increasingly-popular idea that life is roughly 4,000 weeks long (hat tip to Oliver Burkeman), I’ve got about 1,088 weeks left. More to the point: just over 1,000
- When AI Writes the Code, Wisdom Writes the Rules --
It used to be that the measure of a software developer was how fast they could code. How cleanly. How cleverly. But in a world where AI can now write, refactor, test, and deploy code faster than most juniors can Google the syntax, raw coding speed and rote memory are rapidly losing their edge. The
- Why Experts Struggle at the Edge of Change --
“An expert is an expert on how the world used to be, not what it might become.” That quote (or some variation of it) has been rattling around in my head for years. And the more I see the world tilting on its axis—especially with tech—the more I believe it. See, expertise is a double-edged
- Judgment as a Service: Why AI Agents Need a Moral OS --
We don’t need more AI agents. We need better ones. That might sound contrarian in a world rushing to automate everything from customer service to creative ideation, but hear me out: the core problem with most agents isn’t capability — it’s judgment. Today’s AI agents are like eager interns. They act fast, they follow instructions,
- If It Can’t Say No, It’s Not an Agent --
Let’s talk about AI agents. Not the marketing buzzword, not the product demos hyped on Twitter, and definitely not the chore-doing bots people are rigging up with Zapier, LangChain, and a handful of prompts duct-taped together. I mean real agents. The kind that act with autonomy. The kind that think for themselves. The kind that,
- What is Vibe Coding? The Hype, Hope & Hidden Hazards --
In the ever-evolving world of software development, new trends pop up faster than you can say “deprecated.” Some make sense. Others are marketing spin masquerading as progress. And then there’s vibe coding—a concept that sounds cool, feels empowering, but falls apart under scrutiny. If you haven’t come across the term, vibe coding refers to the
- We Don’t Invent the Future-We Discover It --
Most people think we invented electricity. We didn’t. It was always there—ripping through the sky as lightning, building up in your socks on the carpet, pulsing through every atom in your body. What changed wasn’t the presence of electricity. What changed was us. We learned how to observe it, understand it, name it, and eventually
- The Ethics of AI: Balancing Innovation and Responsibility in Business --
Welcome to the sixth edition of Tech with a Twist! As we enter March 1st, it’s time to tackle a topic that’s as important as it is complex: the ethics of AI. Artificial intelligence is transforming industries, boosting efficiency, and creating incredible opportunities. But with great power comes great responsibility. How do we, as business
- Embracing AI: Why Using Technology to Enhance Our Capabilities is Absolutely Acceptable --
We’ve all heard it before: “If you’re using AI, aren’t you cheating a little?” It’s a sentiment that, admittedly, might give us pause. After all, less than a century ago, people faced similar scrutiny for undergoing cosmetic surgery, a mere few decades ago for choosing a calculator over mental math, and even now (still?) for
- The AI-Fueled 4-Day Workweek: A Pipe Dream, Not Nirvana --
The idea of a four-day workweek has captured the imagination of many as the ultimate reward for technological advances. Proponents argue that artificial intelligence (AI) will finally deliver the dream of working less while maintaining—or even increasing—productivity. It’s a tantalizing vision of the future: more leisure, less stress, and greater work-life balance, all made possible
- AI for Content Creation: Tools and Strategies to Save Time and Boost Creativity --
Welcome to the fifth edition of Tech with a Twist! As we head into February 15th, let’s tackle a topic that’s transforming the way businesses approach marketing: AI for content creation. Whether you’re a solopreneur, a small business owner, or part of a growing team, AI tools can help you save time, generate fresh ideas,
- AI Agents: Transforming SaaS and Intelligent Automation --
An introduction to AI agents in SaaS, including potential applications, business benefits and implementation challenges.
- The Paradox of Trust: Human Instincts vs. Technological Imperatives --
Trust, humanity’s age-old glue that has cemented societies, economies, and relationships for millennia, is now under scrutiny in our rapidly digitizing world. It often adopts a seemingly contrasting avatar: “Zero Trust.” Why this dichotomy? Why do human-driven ecosystems treasure trust while their digital counterparts appear to advocate skepticism? This piece delves deep into this enigma,
- Model Collapse: What Synthetic Training Data Can—and Cannot—Tell Us --
A corrected look at model collapse, recursive synthetic training data, and why prose style is not reliable proof of AI authorship.
- Alchemy to AI: Historical Parallels in Public and Governmental Attitudes Towards Groundbreaking Technologies --
In the medieval period, the practice of alchemy captivated the imagination and fear of both the public and the government. Alchemists, driven by the pursuit to transmute base metals into gold, were seen not only as pioneers of early chemical science but also as potential threats to the economic and political stability of the era.