In partnership with
Most people trying to learn AI are doing it wrong.
They jump between:
• random YouTube videos
• scattered GitHub repos
• outdated tutorials
• hype posts on social media
After months of effort…
They still don't know how modern AI systems actually work.
The truth?
Learning AI isn’t about watching more tutorials.
It’s about following the right roadmap.
So I built one.
A complete AI learning resource list covering:
• LLM fundamentals
• AI agents
• prompt engineering
• vector databases
• RAG systems
• multi-agent architectures
• LLMOps
• real production AI systems
Everything is curated, structured, and practical.
Let’s dive in.
📹 Best Videos to Understand AI & LLMs
If you're starting out, videos are the fastest way to understand how modern AI systems work.
1. LLM Introduction
2. LLMs from Scratch
Tech moves fast, but you're still playing catch-up?
That's exactly why 200K+ engineers working at Google, Meta, and Apple read The Code twice a week.
Here's what you get:
Curated tech news that shapes your career - Filtered from thousands of sources so you know what's coming 6 months early.
Practical resources you can use immediately - Real tutorials and tools that solve actual engineering problems.
Research papers and insights decoded - We break down complex tech so you understand what matters.
All delivered twice a week in just 2 short emails.
3. Agentic AI Overview (Stanford)
4. Building and Evaluating Agents
5. Building Effective Agents
6. Building Agents with MCP
7. Building an Agent from Scratch
8. Philo Agents Playlist
These explain:
• how LLMs work
• how AI agents are built
• how production AI systems are designed
🗂️ Must-Know GitHub Repositories for AI
The fastest way to learn AI engineering is by studying real codebases.
These repositories show how AI systems are actually built.
GenAI Agents
Microsoft AI Agents for Beginners
Prompt Engineering Guide
Hands-On Large Language Models
Made With ML
Hands-On AI Engineering
Awesome Generative AI Guide
Designing Machine Learning Systems
Machine Learning for Beginners
LLM Course Repository
🗺️ Important AI Guides & Whitepapers
Some of the best AI knowledge comes directly from the companies building the models.
These guides explain how modern AI systems are architected.
Google’s Agent Whitepaper
Google’s Agent Companion
Building Effective Agents (Anthropic)
Claude Code Agentic Best Practices
OpenAI Practical Guide to Building Agents
If you're building AI agents or autonomous systems, these are essential reads.
📚 Best Books to Learn AI & LLM Engineering
Short tutorials teach tools.
Books teach deep understanding.
Understanding Deep Learning
Building an LLM from Scratch
The LLM Engineering Handbook
AI Agents: The Definitive Guide
Building Applications with AI Agents
AI Agents with MCP
AI Engineering (O'Reilly)
📜 Essential AI Research Papers
Many modern AI breakthroughs come from a few key research papers.
These papers explain the core techniques used in AI agents and reasoning systems.
ReAct
Generative Agents
Toolformer
Chain-of-Thought Prompting
Tree of Thoughts
Reflexion
Retrieval Augmented Generation Survey
These concepts power modern AI agents and reasoning systems.
🧑🏫 Best Courses to Learn AI Agents & LLMs
If you want structured learning, these courses walk through real AI system implementations.
HuggingFace Agent Course
MCP with Anthropic
Building Vector Databases with Pinecone
Vector Databases: From Embeddings to Apps
Agent Memory
Building and Evaluating RAG Apps
Building Browser Agents
LLMOps
Evaluating AI Agents
Computer Use with Anthropic
Multi-Agent Systems
Improving LLM Accuracy
Agent Design Patterns
AI moves extremely fast.
These newsletters help you stay updated without doomscrolling.
Gradient Ascent
DecodingML
Deep Learning Focus
NeoSage
Jam With AI
Data Hustle
Final Thoughts
AI is moving toward:
• AI agents
• multi-agent systems
• autonomous workflows
• LLM orchestration
• RAG architectures
The developers who understand how these systems work will build the next generation of software.
If you work through even half the resources in this list, you'll be ahead of most developers entering AI today.