Copilot Studio’s New Harness Plans Its Own Steps. That’s Why It Costs More.

On August 3, Microsoft made the GitHub Copilot harness in Copilot Studio generally available. Most of the coverage framed it as a more powerful way to build agents, which is true, and which buries the lead. The lead is one word, harness. A harness is not a model and not a feature, Microsoft is using this word for a reason. The harness in Copilot Studio is the thing you now choose before you build. And the GitHub Copilot harness has one defining trait. Instead of following the steps you laid out, it plans its own. That single trait is why it is powerful. It is also why it shows up on your … [Continue reading]

Reading the Costume Instead of Admiring the Outfit

One company built a product by taking other people's work without asking. The same company, in the same stretch of headlines, is furious that someone took its work without asking. A federal judge gave final approval to Anthropic's $1.5 billion settlement, the largest known copyright settlement in United States history, brought by authors who said Anthropic used their books to train Claude without asking nor without paying. Now set that beside Anthropic's own public accusation that three Chinese labs ran industrial-scale campaigns to harvest Claude's output through roughly twenty-four … [Continue reading]

The Token Price Will Fall. Your Bill Will Not

I ran a task through Microsoft Copilot Cowork last week that cost me $13. I was shocked. What did I asked Cowork to do? At Creaspark, we use the EOS business management framework, as each quarter we host a quarterly business review (QBR). Our QBR's run about eight hours, and we capture the whole thing as one long Teams recording and transcript. I wanted assistance building executive briefing summary, a real Word document we could use to summarize the entire day, what we discussed, our updated priorities, todos, etc.. This is the kind of work I would normally give to an assistant and … [Continue reading]

Let AI Build the Rules It Must Follow

I have written before that the best thing my agents do is not think. The most reliable parts of my personal agents are the parts that never touch a language model, even when AI is used as an overall monitor. Scheduled jobs. Database queries. Slash commands that skip the LLM and hand me an answer in under a second. The conversational engine is the part I trust least and pay the most for. That post described what I built. I need to turn to where I think it all points. I have argued that AI did not erase the entry-level job, it changed it. Mark Zuckerberg has admitted AI agents have not … [Continue reading]

Did AI Really Erase Entry-Level Jobs? No, the Job Just Changed.

I have spent twenty-eight years building things on computers, and I have watched the "this is the end of developers" headline come around more than once. So when the latest round of articles proposing the end of developers because of AI started … [Continue reading]

The AI that could Run a Company is the One We’ll Never Get

A group of people I respect, (full transparency, most of them sharper than me), have been passing around Europe 2031, Juijn et al, and landing in the same place. Dismay. It's a well-reasoned piece of scenario writing. It takes today's real headlines, … [Continue reading]

Banning AI is not the Safe Choice. Govern It.

I notice there is new AI tool worth trying almost every week, or is it everyday? Wait, did I just miss a new one while writing this post? Seems like it! The pace is relentless, and it is not slowing down. I have written about working at the speed of … [Continue reading]

Working at the Speed of Thought

Right now as I'm writing this post, I am running four tasks in parallel, five if you count this writing workstream. Not one after another, the way I used to work. All four, simultaneously, moving forward while I am thinking about and doing something … [Continue reading]

Copilot in Notebooks are the Easy Part. AI Governance is the Real Rollout Project

Microsoft shipped associated identities for Fabric items last week. On April 30th, Copilot and AI capabilities expand to every paid Fabric SKU down to F2. Multi-agent orchestration in Copilot Studio just went GA with native Fabric integration. And … [Continue reading]

The Best Thing Falcon Does Is Not Think

My first interaction with my OpenClaw instance, Falcon, cost me five dollars. I.e. my hello world conversation. That was eye-opening. I turned on OpenClaw, typed "Hi," and started asking basic questions about what was possible. Just getting … [Continue reading]