Discuss agent architectures and share learnings with the community.
I/O, Cloud Next, Build, re:Invent, and Interrupt across one season. The throughline isn't a winning framework; it's that the whole industry quietly admitted reliability and governance are the unsolved part.
AutoGen taught Microsoft conversation loops; Semantic Kernel taught it enterprise plumbing. The Agent Framework is the merger, and the migration story matters more than the feature list.
ADK makes sense when you're already in Google Cloud and need governed agent deployment. The playbook isn't learning the SDK; it's eval gates, IAM boundaries, and critic loops.
Multi-agent bugs look like model failures but they're state-machine failures. The fix is replaying the critic's last rejection and finding the fork, not re-prompting the worker.
Self-hosted agents trade API convenience for data-plane control. For regulated industries that's not ideology; it's the only architecture legal will sign.
Stakeholders ask for 'productivity gains.' The honest metric is bad outputs caught before they ship: encoded judgment, not word count.