From agent setup to logs in one place
"Managed Agents," a screen for managing AI agents in one place, is expected to be added to "Google AI Studio," Google's developer service. TestingCatalog, a U.S. outlet that tracks new features, reported it on Oct. 25 and posted it on X.
The screen is divided into five sections: "Agents," "Environments," "Credentials," "Triggers" and "Run logs." Developers can set up agents, connect tools, decide when to run them and review past runs. Some of the same functions were already available in the Gemini API and AI Studio's playground, and the new screen brings them together in one place.
Head of AI Studio also mentions a management screen
According to TestingCatalog, Logan Kilpatrick, head of AI Studio, mentioned on Oct. 25 a management screen built on top of Managed Agents. He also noted that the display of charges currently lags by 10 minutes and said a version that shows them in real time is being built. Google has not said when it will be available.
Competing with Anthropic's platform of the same name
Google on Oct. 22 also announced "Agent Compute Engine," a computing platform for running agents, and said it would release a trial version within a few months. It has not been confirmed whether the new screen will use this platform. Anthropic also offers a platform for running agents under the same "Managed Agents" name, and on Oct. 22 it introduced a way to use Anthropic's platform under existing Google Cloud contracts.
