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.
Where A2A Fits in the Open Agent Ecosystem Co-authored with Angie Jones on the Agentic AI Foundation blog, August 20, 2026
A2A defines how one independent agent works with another: negotiating scope, keeping a task going over time, asking for more input, and streaming intermediate updates, while the remote agent decides how to do the work behind its endpoint. Commerce is a concrete example. UCP defines an A2A binding for checkout, and AP2 carries verifiable payment authorization inside the same interaction.
Introduction to Agents Lead author, with Antonio Gulli, Shubham Saboo, Michael Zimmermann, and Vladimir Vuskovic, on Kaggle, November 2025
Day 1 of the Kaggle × Google 5-Day AI Agents Intensive, which reached 1.5M+ learners. It is written for developers, architects, and product leaders moving from proof-of-concept to production-grade agents:
Taxonomy: Level 0 (core reasoning) → Level 4 (self-evolving systems) Architecture: Model (“brain”), Tools (“hands”), Orchestration (“nervous system”) Agent Ops: LM-as-judge quality, metrics-driven go/no-go, OpenTelemetry traces, human feedback Security: the utility vs.