1. Security & Risk

    Claude 3.5 Haiku, 3.7 Sonnet, GPT-4o: The Deprecation Wave Is Here

    Three major models entering end-of-life in the same window. If you hardcoded model IDs, migration planning just became urgent.

    2 min read

  2. Agents & Tooling

    Claude in Excel Is the Quiet Revolution

    Anthropic isn't building a better chatbot. They're embedding AI where work actually happens.

    1 min read

  3. Agents & Tooling

    SoN 33: The Questions I'm Asking My AI Before the New Year

    Last week I asked Claude a simple question: “What patterns do you see in how I’ve been working this month?” Some hours later, I was reviewing a complete redesign of how I approach…

    7 min read

  4. Agents & Tooling

    SoN 25: Writing With AI Isn't Cheating — It's an Accessibility Tool

    Part 1 Using AI isn’t cheating. It’s an accessibility tool. Some people have brilliant ideas but struggle with formal expression. Some communicate differently due to…

    6 min read

  5. Agents & Tooling

    From "Pick One AI" to "Pick Three" - What Changed My Mind

    Back in April, I told you the AI tool landscape was a mess and gave you a simple framework: pick one core assistant, add research tools, maybe some workflow apps. Some months…

    5 min read

  6. Agents & Tooling

    One Shortcut Is Worth More Than Ten Assistants

    I used to think building a great AI assistant meant covering everything: Project planning. Writing help. Scheduling. Notes. Outreach. You name it. So I built one that could…

    3 min read