The Gemini API File Search tool now supports natively multimodal RAG with Embedding 2, inline citations, and custom metadata filters.
Building Agents Is Easy. Infrastructure? Not So Much.
Building AI agents shouldn’t mean building agent infrastructure. Vertex AI Agent Builder handles the runtime, governance, and Google Search grounding so you can focus on what the agent actually does.
MCP Is the New REST. Google Cloud Just Made It Enterprise-Ready.
The Model Context Protocol is becoming the standard for how AI agents call external tools. Google Cloud Managed MCP Servers handle the enterprise governance layer so you don’t have to.
Apigee Got a New Job: The Control Plane for Your AI.
Apigee evolved from API gateway to the control plane for LLM traffic, agent actions, and MCP tools. Here is why that matters for anyone building AI features at scale.
A2A Is How AI Agents Finally Learn to Play Nicely
Google’s Agent2Agent protocol, now under Linux Foundation stewardship, gives AI agents a standard way to find, authenticate, and collaborate with each other across any vendor or framework. For ISVs, it changes what a multi-agent product architecture can look like.
Safety Audits That Took 14 Days Now Take One Hour (AES)
AES ran more than 1,500 safety audits a year the hard way. With Anthropic’s Claude on Vertex AI, the same work now takes one hour instead of 14 days, at 99% lower cost.
Wait, Oracle Runs Inside Google Cloud?
Oracle and Google Cloud put actual Exadata hardware inside GCP data centers. That is a strange sentence to type, and it has some interesting implications.