Those of us who spend any time thinking about AI agents tend to think about them as loops around a language model. Something wakes the agent, like a message. The agent sends that message, plus whatever context it has assembled, to a model. The model returns. Maybe it requests a tool, and the tool executes, and the result goes back, and so on. The loop continues until the model decides it is finished....
Fair warning: this one is long. I kept finding things I couldn’t leave out. Pour a coffee. If you’d like to go straight to the infographic, head to the bottom of the article below. As I mentioned in my last post, around the year 2000 I took an AI course at the University of Guelph, and the thing I remember most is Lisp. Lots of Lisp, in the dark CIS lab....
For years, as an enterprise architect, I’ve spent a lot of time reviewing systems through the lens of threat models, control frameworks, and residual risk. Long before I started building AI agents, I was asking questions like: What can this system access? What happens if it fails? What controls prevent that? What’s the residual risk once those controls are in place? One thing that I’ve noticed since moving into agentic AI is that many conversations about agent governance seem to ignore decades of security and architecture practice and instead, reduce an agent’s residual risk to a single question: How autonomous is it?...
Around 2000 I took an AI course at the University of Guelph. I don’t think I learned too much. We didn’t talk about neural networks, as far as I can remember. My end of term project was, I think, a pathfinding algorithm wearing an AI costume. There were certainly no discussions of transformers. No CUDA. No PyTorch. None of that existed. But what I remember doing a lot of was coding in Lisp - a lot of Lisp in the dark University of Guelph CIS lab....
Years ago I read Thomas Friedman’s The World Is Flat, and what stayed with me wasn’t any particular argument so much as the feeling it left behind. The feeling was optimism. The idea that connectivity was dissolving geography, that talent anywhere could plug into everywhere, that someone in Waterloo or Bangalore or Nairobi could participate in the same economy as anyone else and the old walls just wouldn’t matter very much anymore....
Canada Has an AI Strategy. Now Comes the Hard Part. Canada has a national AI strategy. After months of delay, Mark Carney and AI Minister Evan Solomon unveiled it in Toronto this morning. It’s called AI for All, and on the surface it has all the ingredients you’d expect: federal money, national ambition, and a lot of language about innovation, growth, trust, skills, adoption, and sovereignty. But underneath the policy framing there’s a more interesting admission....
Fair warning: this one is long, and it gets fairly technical. But I think this particular security discussion matters, now that LLM calls are starting to look more like infrastructure. Calling an LLM Is a Data Exposure Decision Most teams integrate LLMs the same way they integrate any API. You grab a key, wire up the endpoint, send a prompt, get a response. It works. The product ships. Then six months later someone asks:...
Time is doing that thing again where it moves slowly day to day and then, somehow, three months disappear. It feels like about five minutes ago that I stepped away from work and jumped into this sabbatical / retirement trial / self-directed chaos experiment. And yet here we are. Three months in. Already. I’m not sure I have some grand conclusion about that yet. I don’t think I’m magically transformed. I haven’t emerged from the cocoon as a perfectly optimized human founder monk with a six-pack, a completed SaaS business, and a radically simplified garage....
I have been chasing some version of passive income for the better part of twenty years. Not always consistently. Not always intelligently. Not always with anything resembling a plan. Sometimes it looked like side projects. Sometimes it looked like domain names purchased late at night with too much optimism and not enough execution. Sometimes it looked like half-built apps, abandoned blogs, monetization ideas, affiliate schemes, YouTube concepts, newsletters, digital products, and vague plans to eventually “build an audience....
There’s a moment that happens when you run more than one AI agent at the same time. At first it feels powerful. Then it feels confusing. Then, very quickly, it feels like you are managing a very strange remote team where everyone is brilliant, forgetful, overconfident, occasionally useful, and somehow unable to remember where they put the document they just claimed to have created. Which, to be fair, is not entirely unlike managing humans....