10 YouTube channels that will make you an AI expert:
1. Andrej Karpathy - modern, practical lectures
2. Yannic Kilcher - Breaks down AI papers in detail
3. AI Explained - Makes tough ideas easy to get
4. CodeEmporium - Step-by-step AI coding
5. 3Blue1Brown - Visuals for neural networks
6. Lex Fridman - Interviews with top AI folks
7. CodeEmporium - Step-by-step AI coding
8. sentdex - Python for machine learning
9. DeepLearningAI - Courses from Andrew Ng
10. AI Coffee Break - Weekly updates on AI
Save this list.
@donkoclock People need wake up and protest for justice until he is prosecuted and jailed for killing an innocent
Bloody terrorist
Wake 🆙 🇺🇸
Banned ICE
99% of the AI agent tutorials on YouTube are garbage.
I’ve built 47 agents with n8n and Claude.
Here are the 3 prompts that actually work (and make agent-building simple).
Bonus: comment "Agent: and I’ll DM you AI agent system prompt + full guide ↓
Claude Opus 4.5 is ridiculously powerful.
But almost everyone is using it like a basic chatbot.
Here are 5 ways to use it that feel unfair:
(Comment "AI" and I'll DM you a complete Claude Mastery Guide)
Everyone is building AI agents.
Very few understand the agentic frameworks that actually power them.
In 2025, two frameworks dominate agent development —
not as competitors, but as complementary layers:
n8n — Visual Workflow Automation
What it does
• Visually connects AI agents with business tools and APIs
• Flow: Trigger → AI Agent → Tools → Action
• Removes integration complexity and speeds up deployment
Think of it as:
The orchestrator that plugs AI into your entire tech stack
—
LangGraph — Graph-based Agent Orchestration (LangChain)
What it does
• Enables stateful, cyclical, multi-step agent workflows
• Flow: State → Agents → Conditional Logic → State (loops)
• Designed for complex reasoning and coordination
Think of it as:
The brain managing advanced agent decision-making
—
When to use n8n
• AI + business tool integrations
• Customer support and ops automation
• No-code or low-code workflows for teams
• Fast shipping with 700+ integrations
When to use LangGraph
• Multi-agent reasoning systems
• Enterprise-grade AI applications
• Cyclical or long-running workflows
• Fine-grained state control and memory
—
Ecosystem strengths
n8n
• Visual builder for non-developers
• Self-hosted, open-source option
• Strong business automation community
LangGraph
• Deep LangChain integration
• LangSmith for observability and debugging
• Advanced state persistence and control
—
The real insight 👇
The best AI systems use both.
n8n → Visual orchestration and tool integration
LangGraph → Agent logic, reasoning, and state
Think in layers: business automation and intelligent decision-making
—
Your turn 👋
What would you build first?
A visually simple, tool-connected agent (n8n)?
Or a deeply orchestrated, reasoning-heavy agent (LangGraph)?
THE FACEBOOK AD THIEF
I just built an AI agent that "steals" my competitor's best Facebook ads and makes them mine. Perfect for ecom owners, and I'm giving it away for free.
(Saves 15+ hours per week on creative research, boosts ad performance by 40%)
Here's how the Facebook Ad Thief works:
→ Scrapes Facebook's ad library to find competitors' live campaigns
→ Uses Google's Gemini AI to analyze winning ad structures and messaging
→ Rebuilds those ads with your brand and products using advanced prompting and Nano Banana
→ Automatically saves all variations to Google Drive for easy access
→ Handles complex scenarios like multiple product placements
This automation eliminates the manual grind of competitor research and creative ideation. Instead of spending hours scrolling through ad libraries and trying to reverse-engineer what's working, I get proven ad concepts delivered automatically.
The real power? It uses "meta-prompting" - AI writing prompts for other AI - to handle edge cases that generic prompts miss.
Want the complete system? Here's how to get it:
1. Like & RT this post
2. Follow my profile so I can DM you
3. Comment "ADTHIEF"
I'll send you the entire n8n workflow template, all of the prompting, and a full step-by-step setup video for free.
Stop reinventing the wheel. Start stealing what already works.
Nano banana + n8n + Claude = AI Ad Factory
This system pumps out TikTok/FB/IG static ads on autopilot using Google's new image model...
- No writers.
- No strategists.
- No $15K+ monthly content teams.
Just endless, high-converting content at scale.
Perfect for e-comm operators & creative agencies.
Here's how it works:
→ Upload business context into intelligence engine
→ n8n pulls audience psychology & brand voice patterns
→ Claude generates content variations across platforms
→ Auto-formats for LinkedIn, Twitter, newsletters, YouTube
→ Applies psychological triggers & engagement hooks
→ Logs performance data back to system for optimization
Built with Google's Nano Banana image model.
Runs 24/7 without supervision.
Perfect voice consistency every time.
Want the complete system?
Like + comment "FACTORY" + repost, and I'll DM it to you.
(must be following)
This is crazy.
Nate Herkelman turned @n8n_io into a full marketing team! 🤯
His AI agent:
↳ generates and edits images
↳ fetches assets
↳ creates posts
… and logs everything automatically!
Full demo in 🧵 ↓
@WPTutz Never been fun of Elementor 👇
👉 I would rather use Blocksy than Elementor
👉 I would rather use Bricks than Elementor
👉 I would rather use General Press than Elementor
&&&&&&&&&&&& I agree Elementor = Microsoft office
In 1972, Steve Jobs walked in on his girlfriend sleeping with a guy.
Steve became friends with him.
He taught him a philosophy that allowed him to convince anybody of anything. It's why they both became billionaires.
Here’s the philosophy: 🧵