Learning
Slideshow lessons with animated visualizations and sequence diagrams. Each slide explains one idea — hit Recap for a 30-second summary, or ⚒ Hands-on to run the lab yourself.
AI Architecture
moduleBuild production-ready AI systems — RAG pipelines, vector databases, self-hosted inference, and private AI stacks.
Part 1 of 3
RAG: Retrieval-Augmented Generation
Ground your LLM in real data — how retrieval-augmented generation works, from embeddings and vector search to chunking strategies and advanced patterns.
Part 2 of 3
AI Infrastructure Design
How to architect reliable, cost-effective AI systems — model serving, inference routing, caching, GPU sizing, and observability.
Part 3 of 3
Private AI Stack with Open WebUI
Run a fully self-hosted ChatGPT alternative — Ollama + Open WebUI on Docker, with built-in RAG, multi-user auth, and model management.
Lessons
Caching & Redis
What a cache is, where it can live, and why Redis is so fast — data structures, the single-threaded event loop, and how persistence works under the hood.
Message Queues & Kafka
Why services shouldn't call each other directly — queues, pub/sub, delivery guarantees, and what makes Kafka the backbone of event streaming.
Authentication
2 lessonsPart 1 of 2
OAuth 2.0
How apps request delegated access without ever seeing your password — the authorization code flow, tokens, scopes, and PKCE.
Part 2 of 2
OpenID Connect
Why OAuth 2.0 alone is not enough for authentication — OIDC adds an identity layer, the ID token, and standardized user profile claims.
More lessons coming
Load balancing · Database indexing · WebSockets · gRPC