Sunday, February 1, 2026
Claude Code Experiences
Users are discussing their experiences with Claude Code, highlighting its agent capabilities, the shift away from web-based AI, and debates regarding its task management effectiveness and potential security concerns.
Early versions of Claude Code used RAG + a local vector db, but we found pretty quickly that agentic search generally works better. It is also simpler and doesn’t have the same issues around security, privacy, staleness, and reliability.
I’ve moved all my AI usage to Claude Code, and I’ve realized: I really don’t want to use web-based AI products anymore. Because CC solves a fundamental problem: conversations with AI now have persistence. Before, I was also having massive amounts of daily conversations with AI,