Tom Solid | AI Productivity

Wow! 112 of you have already signed up for my upcoming live workshop, where I’ll work with you to build an AI knowledge system from scratch in just 3 hours.

@ClaudeDevs Cannot confirm that anything has changed. Weekly limit remained the same... 🫣

Claude Code weekly limits are increasing 50%, now through July 13. Live now for all Pro, Max, Team, and seat-based Enterprise users.

I'm working on "sovereign AI" productivity - my mentor is @TomSolidPM - Tom has released a GitHub file explaining his process to organize data and setup an AI agent team in a way that is AI agnostic if you are a sovereign individual - check out Tom's approach youtube.com/watch?v=4C2w8e…

This is bigger than it seems.

Larry routes. Nolan hires. Pax researches. Penn writes the journal. Four-person AI team. One folder on my disk. Continuous memory across Claude, ChatGPT, anything. 34 min walkthrough: youtu.be/4C2w8eIG48A

Auto-memory in Claude and ChatGPT is the wrong default. The model decides what to keep. You cannot see it, edit it, or take it with you. A folder on your own disk does the job, in plain text, portable forever. Walkthrough: youtu.be/4C2w8eIG48A

I just made my Personal Knowledge Assistance folder public. Six months of refinement. Free on GitHub. 34 min walkthrough: I open my actual folder, show what my AI writes to every day, and why I switched off auto-memory. youtu.be/4C2w8eIG48A

You can make the math...

Today, we're excited to release the Heptabase CLI — a new way for external AI agents to interact with your local Heptabase knowledge base from the terminal. Once enabled (Settings > AI Features > CLI), any AI coding agent (e.g., Claude Code, Codex) can: - Create, read, and edit note cards and journals - Search your Card Library - Manage tags - Read your AI Tutor courses, lessons, and chat history This is just the first step; we'll keep expanding the CLI surface so AI agents can act on your knowledge at the same depth that you can. If you build something interesting with it, feel free to share with our community!

@evielync Yeah. And people still say 'AI is just hype' 😂 Well done!

Claude at 8pm: You really want to build a full AI knowledge agent system for tomorrow morning's workshop to give away? Me: Yes - you're building it. 5 minutes later. Done ✅

Wow! What an amazing udpate! API unleashed full scale now! 🔥

That after all those years in @clickup it's still not possible to upload files to a custom field via API, and this in time of AI and MCP connections is one thing. But the fact, that this is not even on the roadmap is surprising to say the least. feedback.clickup.com/public-api/p/c…

In this video I show a deep dive how giving AI Teams human like rules will make them thrive. youtu.be/IlhTbhR6el0

"Won't all those rules and guardrails slow the AI down?" No. Structure is what makes speed possible. My AI agents produce more in a day than most teams do in a week. BECAUSE of the guardrails, not despite them.

If your AI keeps producing bad output, at what point do you stop blaming the AI and start looking at the instructions you gave it? Same question applies to every team you've ever managed.

If you want the system I built to manage 30+ AI agents and my entire productivity workflow: Build your Future-Proof AI Productivity System TODAY: myicor.com

Evernote. Notion. Roam. Obsidian. Now AI. Same hype cycle. Same pattern: try it, get excited, can't figure out where it fits, abandon it. It's never a tool problem. It's always a system problem. Build the system first, then plug in the tools.

The mistake most people make: treating AI like one magic assistant for everything. That's like hiring one person for sales, engineering, design, and accounting. Build the system. Scope the roles. Then plug in the workers.

Every agent has a defined scope. One does research. One writes code. One handles support. One manages scheduling. None of them "do everything." Focused specialists with clear boundaries, just like a real team.

I run 30+ AI agents daily. Each has its own role, knowledge base, work instructions, and review checkpoints. People keep asking: "How do you manage that many?" Same way you manage any team. A thread: