Mastersystem design.From zero to senior.
A free field guide to building scalable systems. Beginner-friendly fundamentals, deep architectural deep-dives, and 55+ FAANG-grade interview problems — all in one place, all with diagrams.
The crash course
No system design background? Start here. Twelve focused modules that cover the prerequisites — networking, databases, caching, queues — before you tackle full systems.
What Is System Design?
Start here. What system design actually means, why it matters, the framework that turns a vague problem into a defensible architecture, and how to read every other article in this course.
Back-of-the-Envelope Estimation
Capacity math you can do in your head — QPS, storage, bandwidth, memory — the latency numbers every engineer should know, and worked examples for Twitter, URL shorteners, and a chat system.
Networking and HTTP
TCP vs UDP, DNS, TLS, HTTP/1.1 vs HTTP/2 vs HTTP/3, anycast routing, and what actually happens between a browser and a server.
APIs and Communication Protocols
REST, gRPC, GraphQL, WebSockets, Server-Sent Events, and webhooks — when to use each, how to design them, and the patterns that keep them sane at scale.
Featured articles
Real systems — Twitter, Uber, YouTube, WhatsApp — broken down. Every article is tagged by difficulty and ships with sequence and architecture diagrams.
Object-Storage-First: S3 Is Becoming the New Disk
Kafka, warehouses, observability stores, and Postgres are moving durable bytes to object storage. The cost math, the latency floor, and what still needs disks.
Multi-Tenancy — Silo, Pool, and the Noisy Neighbor Problem
Should each customer get their own stack or share one? Tenant isolation models, noisy neighbors, blast radius, and how cross-tenant leaks actually happen.
Durable Execution: How Temporal-Style Replay Works
Durable execution is event sourcing plus deterministic replay applied to your code. How Temporal-style engines journal effects, replay crashes, and break.
Design a Webhook Delivery System
Design a webhook delivery system: fan-out queues, retries with backoff and jitter, HMAC signing, circuit breakers, and dead-letter redelivery at Stripe scale.
Model Context Protocol (MCP) and Tool-Use Infrastructure
How MCP lets any LLM host discover and call any tool server — collapsing N×M integrations to N+M, with the security, reliability, and token math that matters.
Design an LLM Observability Platform
Design an LLM observability platform: distributed tracing for multi-step LLM apps capturing every prompt, token count, and cost to debug failed agent runs.
Browse by topic
Tackle FAANG interviews
Ten classic system design problems pulled from interview reports at Meta, Google, Amazon, Netflix, and more. Each comes with requirements, capacity estimation, and architecture deep-dive.
Build it. Scale it.
Ship it.
Whether you're prepping for a senior interview or just want to understand how the internet's largest systems work — start here.