Building AI tools for solo founders. Compete with 100-person companies. Alone. Now building Thinkly - AI Native Company Builder

New York
Joined January 2024
PlugLab.AI retweeted
Your website doesn’t need another audit. It needs its next 10 buyers. I built Right10 to turn a website into: • 10 high-fit buyer opportunities to investigate • the channels most likely to reach them • the message to test first • an AI marketing workflow to run next Free personalized analysis. No call required. Reply “BUYERS” and drop your website below. Prefer to keep it private? Use the link in my first reply.
3
3
1
10
436
PlugLab.AI retweeted
I scraped 583 Meta ads that refuse to die. Then checked how many follow the "rules": "Use a number" → 17% "Ask a question" → 9% "UGC / first person" → 6% The advice everyone sells is the advice the survivors ignore. Live board 👇
1
1
1
3
229
Agreed.
Stop buying AI tools. You don't need another dashboard. You counted the subscriptions and each one just gave you a faster place to do the work yourself. You're not running a business. You're a very expensive router, copy-pasting between apps that each do ten percent of a real teammate's job. What you wanted was never a tool. It was the work done. So hire an AI team that does the doing, and keep the wheel: strategy, taste, the relationships, the last yes.
1
3
92
PlugLab.AI retweeted
I'm a non-US founder. The export ban took Fable from me. So I built fable-overclock, and now DeepSeek, Sonnet, and Opus give me Fable-grade output again. It doesn't make them smarter. It raises their floor: on DeepSeek, sourced figures went 4% to 100%. Same IQ, output you can actually ship. What's your model's floor? (repo in the first comment)
1
2
4
230
Honestly, I wrote this because my OpenClaw agent started failing me. 📉 The agent wasn't the problem—my messy knowledge was. I built Thinkly to fix this exactly Dump → Auto-structure → Knowledge Graph. Stop fixing prompts. Start fixing your knowledge layer. thinkly.pluglab.ai/
4
61
Hot take: AI agents didn’t fail they just exposed how broken our knowledge is
1
5
56
Most people try to fix agents but the real problem is: context × structure
3
49
This is exactly what most people miss. Karpathy showed the idea. But actually building this system is still too complex for most people. This is a really clean implementation ↓
Karpathy's LLM knowledge base system uses Obsidian, LLM agents, and custom scripts. We built the same dump-and-compile workflow into one app. No setup. Just paste, pick a template, publish. That's Thinkly.
2
10
88
Most people are rebuilding the same broken systems with AI. The problem isn’t tools. It’s how knowledge is structured.
🤖 Made with AI
1
4
173
Bookmark this. You’ll need it when you rebuild your system.
3
159