We’re announcing new capabilities in Managed Agents in Gemini API so developers can build reliable, production-ready agents.
Jul 07, 2026
We’re adding support for new capabilities like background execution for async interactions, easy connection to remote MCP servers, custom functions and credential refresh.
Philipp Schmid
Developer Relations Engineer, Google DeepMind
Mariano Cocirio
Google Deepmind is adding four new features to Managed Agents in the Gemini API. Agents can now run asynchronously in the…
Google's Managed Agents API collapses agent deployment into one API call, handing Google control of the execution layer — a…
This is a submission for the Google I/O 2026 Challenge: Explore Google I/O 2026 Google shipped a lot...
With the launch of Gemini 3, Google introduced “Gemini Agent” as an “experimental feature that handles multi-step tasks.” A big…
Google’s Interactions API is now generally available and becomes the default interface for Gemini models and agents, with managed…
Google named the first mainstream agent to call navigator.modelContext: Gemini in Chrome, 'will soon support WebMCP APIs.' Here's…
