Why AI coding agents keep re-learning the same lessons — and what that costs a team that runs them all day, every day
Anyone running Claude Code or Cursor across a team has watched this happen: one engineer's agent spends ten minutes re-deriving something another engineer's agent already nailed down the day before, because there was nowhere for that answer to live where an agent could read it back. Here's what that actually costs, and what we built to fix it.
1. The problem: agents forget, teams pay for it
AI coding agents — Claude Code, Cursor, and everything else built on the Model Context Protocol (MCP) — are genuinely good within a session. They can read a codebase, hold a lot of it in context, and reason through a gnarly bug faster than most humans would.
Then the session ends, and all of that gets thrown away. The next session, whether it's the same engineer tomorrow morning or a teammate an hour later, starts from a blank slate:
