Your AI agents are stepping on each other

The missing coordination primitive. New research ( AgenticFlict, arXiv 2604.03551 ) confirms what a lot of teams are learning the hard way: AI-generated PRs are producing a measurable new class of merge conflicts. The agents have no concept of each other's intent. An average conflict rate of 20% is enormous, both in terms of cognitive load and in terms of total cost. "What are you working on?" is not a question any harness is currently asking. Except kawacode.ai Agent (and human) intent declarat