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.
More from coding & agent
- Human Oversight Is 70-75% of AI Agent Costs in Banking, McKinsey Finds — mikeflache · 2026-11-04
- Over 80% of Major Financial Institutions Now Run Agentic AI in Production — mikeflache · 2026-11-04
- Mnemos MCP nears launch after shared memory layer fix — RileyRalmuto · 2026-11-04
- Moving mobile dev to remote machines makes it multiplayer across product, design, engineering — rudrank · 2026-11-04
- Kuaishou's EvoRec: self-evolving agentic recommender lifts ad revenue 4.6% — _reachsumit · 2026-11-04
- TRIO: three specialized agents with aligned objectives refine retrieval-augmented generation — _reachsumit · 2026-11-04