Case Studies
Architecture decisions in Cursor, Claude Code, Shopify, and OpenAI
01
Lv.4
Case Study: How Cursor Wires MCP + Skills + Harness Together
From Tab completion to Agent mode—product architecture and why Cursor is today's best AI coding harness.
read →
02
Lv.4 Pro
Case Study: Claude Code's Long-Running Agent Design
How Anthropic's Claude Code manages 50+ step coding tasks—context compression, permissions, and CLAUDE.md project memory.
read →
03
Lv.4
Case Study: Shopify's RAG Path to AI Support
How Shopify built Sidekick with RAG + agents—from MVP to ~82% automation, with real engineering milestones.
read →
04
Lv.5 Pro
Case Study: OpenAI Responses API and Agent Orchestration
How OpenAI's 2025 Responses API unifies chat, tools, and code interpreter—and how it compares to the MCP route.
read →