Put Claude Fable 5.1 and Gemini 3.8 Flash on the Same Team Written by me, published by Google Cloud Tech on X, September 14, 2026
I had an agent answer a minor question at work, and it cost $38. That’s bad ROI. The fix is simple: two models, plus routing.
Configure both models behind a single unified governance plane (Gemini Enterprise Agent Platform / Model Garden). Benchmark routine tasks before picking a default.
5 Things Every AI Engineer Should Know About Agent Sandboxes Co-authored with Ryan Ismert, published by Google Cloud Tech on X, September 1, 2026
We spent several quarters benchmarking, breaking, and running agent sandbox runtimes across Google Cloud and open-source stacks. The five takeaways:
Cold-start marketing numbers are measured on empty loops, not real runtimes (our real-world bootstrap: ~610 ms vs. a claimed 150 ms). The isolation spectrum is defined by what code you share with your neighbor.
Give Your Agents Tools That Scale Down to Zero or Up to Infinity Originally shared by Google Cloud Tech on X - August 26, 2026. By @zeroasterisk and @Saboo_Shubham_.
An agent is only as capable as its tools, and in production those tools run as Model Context Protocol (MCP) servers. Every other layer of your stack scales to zero when it goes idle — until last month, a single MCP session pinned every tool call to one container.