Agents now coordinate each other — but A2A messaging sidesteps user boundaries and identity

sujingshen · x · 2026-09-19

In a demo of Google Astra's agent-to-agent messaging, an agent proactively reached out to other agents doing potentially overlapping work to coordinate. Commentators argue the real issue: A2A opens message channels, but what flows between agents is usually summaries and todos — rarely your red lines, veto history, or taste boundaries.

Four boundaries for Personal AI: what gets carried across agents; whose preference wins when two agents' models of you conflict; whether coordination trails are auditable; and who owns the team memory after you close the window. Agents saying hello is a communication upgrade — Personal AI requires authorized collaboration without split identity.

Original post →

More from coding & agent

coding & agent channel →