From Prompt Engineering to MCP Skills: What Rebuilding My Tokyo Transit Agent Taught Me About AI Architecture

A recent comment on one of my dev.to posts asked a simple but insightful question: What specifically was breaking before MCP: context loss between agents, or tool-call inconsistency? At first, I thought the answer would be straightforward. But after reflecting on my Tokyo Transit project, I realized the real issue wasn't either of those things. The project has gone through three major iterations over the past year, and each version reflects a different stage in my understanding of AI agent...