Google Bolsters Gemini API with AI Agent Enhancements
Google has expanded its Gemini API Managed Agents platform with new features that make it easier for developers to build autonomous AI agents. The platform, which launched on May 19, now includes background execution for asynchronous tasks, integration with remote Model Context Protocol (MCP) servers, custom function calling, and streamlined credential refreshing during live interactions.
The Managed Agents platform centers around the Antigravity agent, an AI that runs inside a secure, Google-hosted Linux sandbox. Powered by models including Gemini 3.6 Flash, the Antigravity agent lets developers spin up autonomous agents with a single API call. Those agents can reason through problems, execute code, manage files, and perform web searches.
The new capabilities address the gaps that separate a cool demo from something deployable in production. Background execution is perhaps the most consequential addition, as it allows agents to kick off long-running tasks and report back when they're done.
Crypto developers may be interested in the potential applications of these features. The credential refreshing feature alone solves a pain point that anyone who's built trading bots knows intimately - API tokens expiring at the worst possible moments.