Discuss agent architectures and share learnings with the community.
Google's Agent Development Kit is the same framework that powers Agentspace and Gemini Enterprise, open-sourced. Here is the complete map: agents, orchestration, tools, MCP, A2A, A2UI, the dev UI, and a working enterprise build you can deploy with one call.
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.
Cloud Next was less about a new model and more about where agents run, who governs them, and how they get discovered inside an org. Here's what Agentspace and the ADK push mean for enterprise buyers.
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.
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.
Model Context Protocol servers look simple in a tutorial. In enterprise they need auth boundaries, schema versioning, blast-radius limits, and observability. Otherwise they become your next outage.
Hiring managers don't want another prompt course. They want evidence you can orchestrate rejection loops: eval harnesses, critic gates, and shipped agent workflows in public.
Tabular enterprise data needs schema-aware retrieval, SQL or semantic layers, and explicit join logic. Dumping rows into chunks and embedding them is why agents confidently cite the wrong quarter.