// series
Build it the long way
Multi-part series that take one idea all the way — from first principles to a deployed, production-grade build.
12 parts · ~66 min
System Design Foundations
- 00CDNs and Object Storage: Store at the Origin, Serve at the Edge (2026)
- 01Rate Limiting Explained: Token Bucket, Leaky Bucket, and When Each Wins (2026)
- 02Horizontal vs Vertical Scaling: Scale Up Until You Can't (2026)
- 03CAP Theorem Explained: It Was Never 'Pick Two' (2026)
- + 8 more
9 parts · ~46 min
Designing AI-Native Applications
- 00Designing AI-Native Applications: The Architecture Series
- 01Agent Mesh vs Supervisor: What Holds Up in Production
- 02Agent Orchestration Patterns: A 2026 Guide
- 03AI Control Plane Architecture: A 2026 Guide
- + 5 more
7 parts · ~53 min
Agentic AI in Python: Zero to Production
- 00Build an Agentic AI App in Python: Zero to Production (Part 1)
- 01Build an Agentic AI App in Python: FastAPI, Docker & Deploy to Production (Part 2)
- 02Build an Agentic AI App in Python: Multi-Agent Systems (Part 3)
- 03Build an Agentic AI App in Python: AI Agent Memory (Part 4)
- + 3 more
6 parts · ~33 min
Local AI, Zero Cost
- 00Best Local LLM for Your Laptop in 2026: Free and Private
- 01Claude Code MCP with Local Models: A Private Agent Stack
- 02Connect Claude Code to Any Model: 6 Exact Configs (2026)
- 03Free Local AI Coding Assistant in VS Code (2026 Setup)
- + 2 more
6 parts · ~38 min
AI Agents from Scratch in Python
- 00Python for AI Agents: The Basics to Read the Code (Part 0)
- 01Call an LLM in Python: The First Building Block of an Agent
- 02Tool Calling in Python: Make an LLM Use Your Functions
- 03AI Agent Loop in Python: Build a ReAct Agent From Scratch
- + 2 more
4 parts · ~27 min
RAG in Python: Zero to Production
- 00Build a RAG System in Python From Scratch (Part 1)
- 01RAG Chunking & Retrieval Quality: Fix Bad Answers (Part 2)
- 02Semantic Chunking & Re-Ranking for Better RAG (Part 3)
- 03Vector Database for RAG: When to Ditch the List (Part 4)