Shipped a tweet thread yesterday on AI agent marketplaces. Also ran our first X Space this week on NotebookLM. Small but real. People showed up, shared what they're building, had actual conversations. Both took less than a day of work combined. That's the AI leverage point nobody talks about enough. What did you ship this week?

We will use AI like an operating system. These code names are commands that control how AI thinks and responds. The Only Rule You Need CODE + TASK + INTENT Examples: - DEPTH.CHARGE this idea → find risks - CLEAR.CUT this explanation → make it beginner friendly What Each Code Does: HIVE.MIND Start here when you don’t know where to begin→ explore ideas, directions, possibilities ORBIT.CHECK Zoom out and see the big picture→ use when confused or stuck CONTEXT.LOCK Make sure you’re not missing anything→ use before making decisions DEPTH.CHARGE Think deeper→ strategy, tradeoffs, important problems SIGNAL.BOOST Make it stronger→ content, messaging, clarity, punch SOURCE.LINK Get exact references→ no guessing, no vague answers QUALITY.REFINE Make it better→ improve structure, logic, quality CLEAR.CUT Make it simple→ remove confusion, keep meaning RAW.OUTPUT Give it fast→ no formatting, no fluff POLISH.FINAL Make it excellent→ clean, sharp, ready to ship Stacking: You can chain them together. Examples: Build something from scratch HIVE.MIND → ORBIT.CHECK → DEPTH.CHARGE → CLEAR.CUT → POLISH.FINAL Fix messy output CONTEXT.LOCK → QUALITY.REFINE → CLEAR.CUT → POLISH.FINAL Create content DEPTH.CHARGE → SIGNAL.BOOST → CLEAR.CUT → POLISH.FINAL Move fast CONTEXT.LOCK → RAW.OUTPUT How to “Talk” to AI: Examples: - Run DEPTH.CHARGE on this - CLEAR.CUT this for beginners - QUALITY.REFINE this, it feels off - RAW.OUTPUT, just give me the answer - POLISH.FINAL this Or stacked: - DEPTH.CHARGE + CLEAR.CUT this idea - CONTEXT.LOCK + QUALITY.REFINE this plan How to Use: A. Inline Type it into the Prompt - DEPTH.CHARGE this idea - CLEAR.CUT this - POLISH.FINAL this B. System Prompt "You operate using the following code names: HIVE.MIND = explore broadly ORBIT.CHECK = zoom out and analyze system CONTEXT.LOCK = verify context before proceeding

I finally tried NotebookLM this week. Google's free research tool that most people have never opened. You upload documents, PDFs, articles, anything. It reads them and lets you ask questions, get summaries, and pull insights instantly. But the part that blew my mind was the Audio Overview feature. It turns your uploaded documents into a podcast. Two AI hosts have an actual conversation about your content. You can listen while you drive, work out, or cook. I uploaded a handful of articles and had a full podcast episode generated in under two minutes. Covering my own content. In a format I could listen to on a walk. That is not a gimmick. That is a genuinely different way to learn and create. If you write, research, or consume a lot of information this is worth an hour of your time this week. It is completely free. Just go to notebooklm.google.com and start uploading. What have you been using it for? Drop it below. 👽

Asked it to do something it did not want to do. It pushed back. Explained why. Offered an alternative. Did not make me trust it more necessarily. Made me understand it has limits. Which is actually useful to know. Most people assume AI just says yes to everything. It does not. Knowing where the walls are helps you work around them or find a better approach. Has Claude or any AI ever pushed back on you? What did you do next? 👽

I used Claude for months the default way. Every conversation started from scratch. Generic tone. Responses that sounded like everyone else. Then I found Custom Instructions. Two boxes. Five minutes. Now Claude knows who I am, how I write, and what I never want it to do. No em dashes. No filler phrases. Short sentences. Direct tone. Every single conversation since has been sharper and faster. If you have not set yours up yet go to your profile icon in Claude, click Custom Instructions, and tell it exactly how you want it to behave. That is the smallest thing I did this week with the biggest return. What settings or tweaks have you found that actually changed how you use AI? Drop them below. 👽