New module live in Implementation Playbooks: Building Websites Three lessons covering how to build and deploy a real website using Claude Code and GitHub Pages. Free hosting, no Wix, no monthly fees. I also break down how Claude Code already writes project memory for you (you do not need to build a complex memory system, it is already happening) and how I structure my prompts to keep token usage as low as possible throughout a real build. Start with 3.1. The video walks through the entire process from analyzing a reference site to having a live URL you can send to anyone. Under 10 prompts total. 3.2 and 3.3 go deeper on the pieces that went by fast in the video(And I will be recording new videos for soon). If you have ever pushed an API key to a public repo or burned through tokens rebuilding something you should have planned first, those two are for you.

For those who want to take a deeper dive into my more philosophical writings. Wrote It a bit back. https://open.substack.com/pub/jakevanclief/p/calculating-consciousness?utm_source=share&utm_medium=android&r=3bot2i

For those of you who've been following me on social media for a while, you've heard me say this over and over: building your own agent frameworks is a waste of time. Stop doing it. Stop paying people to do it. Stop learning how to do it. (Unless you like local projects, that's fun) Anthropic just published this today: https://www.anthropic.com/engineering/managed-agents Here's what it is in plain terms. Managed Agents is a hosted service where Anthropic runs the entire agent infrastructure for you. The loop that calls Claude, the sandbox where code runs, the context management, crash recovery, security, scaling. All of it. You define what the agent should do (system prompt, tools, connections to your systems) and they handle the rest. The key line from their own engineering team: "Harnesses encode assumptions about what Claude can't do on its own. Those assumptions need to be frequently questioned because they go stale as models improve." They gave a specific example. They built a workaround into their harness because Sonnet 4.5 would quit tasks early when it sensed its context limit approaching. When they ran the same harness on Opus 4.5, the problem was gone. The fix became dead weight. One model release made their own engineering work obsolete. Now think about what that means for every startup and every freelancer building custom agent harnesses and selling them to clients. Every assumption they baked into their code is a bet against the next model release. And the frontier labs are shipping new models faster than anyone can maintain a harness. This is the thesis. Your value lives above whatever just got commoditized. The infrastructure layer of agents just got commoditized. The thinking about what to build, why to build it, and how to structure the work around it did not. That's what we teach here. That's why we focus on the 60/30/10 framework, on understanding which layer a problem belongs on, on prompt architecture and workflow design.