For example:

> Our old architecture was scattered across multiple independent systems. A single change might require touching three or four repositories. From a human engineer's perspective, it is manageable. From an AI agent's perspective, opaque. The agent can't see the full picture. It can't reason about cross-service implications. It can't run integration tests locally.

Your agents can't connect the dots across three or four repositories? Even I, at home, have a set up where an agent is perfectly aware of what is in what repositories and access them as needed, and I'm just an amateur.