Skip to main content
AI · real-product deep-dives

Real AI products, dissected

7 case studies. Each deep-dive covers: architecture (with Mermaid diagram), key components with citations, request flow step-by-step, published scale numbers, trade-offs the team explicitly accepted, failure modes seen in production, what to copy and what NOT to copy.

Pro
Author me

Cursor· Anysphere

How Cursor beats Copilot at code completion — architecture, latency, cost.

Pro
Author me

Perplexity· Perplexity AI

Search + LLM synthesis + citations, at scale — the answer-engine pattern.

Pro
Author me

Copilot· GitHub

The first mass-market AI product — architecture, scale, telemetry, evolution.

Pro
Author me

Claude Code· Anthropic

The agentic coding CLI — sandboxed tool use, permission model, session state.

Pro
Author me

NotebookLM· Google

RAG-first personal knowledge assistant — audio generation, citation UX.

Pro
Author me

Notion AI· Notion

AI features embedded in a product surface — the design lessons.

Pro
Author me

ChatGPT· OpenAI

The reference AI product — scale, cost, safety, iteration.