Turn AI Chat Into a 15‑minute Personalized Daily Brief
Ten months ago, building a truly personalized daily brief from your connected tools wasn’t really practical. Now you can do it in about 15 minutes. This changes what’s possible. A lot of people are still treating AI like a chat window. They paste in a calendar or a transcript and stop there. The higher-leverage move is turning those same connectors into one clean brief that actually matches how you work and what you care about. I’m doing a live session walking through exactly how to build it in Claude Cowork. We’ll cover the setup, what’s worth automating, and how to make it yours instead of generic. You’ll leave with a working version plus a simple approach you can use on any recurring workflow. This is for operators who already have tools connected but are mostly just chatting with the AI. If you’re still spending 20 to 40 minutes every morning piecing context together, this is worth your time. Before we build it live, think about this: What do you usually have FOMO about at work? What recurring admin do you wish you could hand off? What would you actually want to know first thing in the morning? The clearer those answers are, the more useful the brief becomes. I’m running it on Friday, May 22 at 10am PT. Link in comments.
Investors Should Recruit, Not Charge Separate Fees
Recruiters should charge recruiting fees. Investors should help their companies recruit. One of the core reasons founders take money from VCs, angels, or accelerators is that those investors are supposed to help with company-building. This includes hiring, customers, follow-on capital, advice,...
Slack Bots Bring Future-Ready AI to Teams
Shopify has figured out what makes AI work inside of companies. This is exactly what I've been doing at my companies since OpenClaw came out. Get a bot in Slack for team usage in public channels and it'll feel like...
CEO's Paid Partnership Repost Sparks Authenticity Doubts
Just saw a CEO quote repost a paid partnership post. Made me question the authenticity of what they shipped and whether to believe the claims made or not. Glad this label now exists. https://t.co/SR0Lh3nvtO
Calling Out AI Slop Without Burning Bridges
How do you tell someone that everything they are building and publishing is AI slop?
Local LLMs Thrive: New Model Boosts Product Quality
I'm obsessed with running local LLMs. Been working with an engineer to build product(s) that are 100% local. A new model that came out recently instantly improved the quality of our product. We live in really interesting times.
Long‑time OpenClaw User Shares AI Agent Workflow
Been using @openclaw for work since the first week it came out. Still using it and other AI harnesses including Hermes Agent. These agents run on computers as well as in the cloud. Using both local models and cloud models....
Slack AI Must Navigate Ambiguity, Not Just Answer
Private AI chat is the sandbox. Slack is the workplace. That distinction matters more than people think. In private chat, an agent only has to satisfy one person in a narrow context. In Slack, it has to survive ambiguity, side threads, buried decisions,...
Memory Bandwidth, Not GPUs, Drives AI Speed
When people say "AI is about GPUs," they are usually pointing at the wrong bottleneck. If you have ever wondered why one machine feels like you are talking to the model and another feels like it is thinking through molasses, @om...
Internal LLM Token Modeler Proves So Useful, Might Go Public
Been building an LLM token modeler for internal use. It’s so useful. Might ship it for everyone.
OpenClaw's Failures Expose Hidden Complexities of AI Agents
OpenClaw is interesting because it breaks in the right places. That sounds like criticism. I mean it as the reason to study it. The AI agent demos with OpenClaw are impressive, but the failures are more useful. They show the real work hiding...
Act First, Reflect Later: The Shortcut to Mastery
The fastest learners have the fewest excuses between thought and action. They do the thing. Then they study what happened. That loop beats almost every form of preparation. At some point, more input becomes avoidance that feels productive.
Keep Experience Adaptive, Not Fixed, Thanks to AI
This gets at something I see all the time. Experience only stays valuable when it keeps updating. AI lowers the cost of trying, learning, and changing your mind. That makes stale judgment easier to spot. The most effective operators treat experience like a...
Treat AI as a Collaborative Partner, Not a One‑shot Tool
A lot of people use AI like Google. One question, one answer, move on. That's the shallow end. Pair prompting is different. You treat AI like a partner. Loops, context and your reactions to what it gives you. You tighten the constraints and...
Learn AI Fast by Watching Pair Prompting in Action
The fastest way to get good at AI is to watch someone good use it. Pair prompting makes that possible in public, or semi-public, channels where the work accumulates and others learn by following along. This essay is my attempt to name...