Recommended reading

Google updates its enterprise agents for more autonomy

News
By published

Google updates its AI agents with even more autonomy

A representative abstraction of artificial intelligence
(Image credit: Shutterstock / vs148)
  • Google launches Python ADK v.1.0.0 and Java ADK v.0.1.0
  • Its agent-to-agent communication protocol has also been improved
  • Python SDK for A2A makes it even easier to manage inter-agent communications

Google has announced a series of updates to its AI agents in the hope that they become more streamlined as efficient colleagues, rather than tools that colleagues use.

"We envision a future where intelligent agents are not just tools, but collaborative partners in solving complex challenges, streamlining workflows, and unlocking new possibilities," Product Manager Polong Lin and Developer Advocate for Cloud AI Holt Skinner said in a blog post.

The latest updates focus on enhanced agent management and improved agent-to-agent communication – a sign of AI becoming even more autonomous.

Google wants to make AI agents more autonomous

The tech giant has enhanced its Agent Development Kit (ADK) to include a new production-ready and stable v.1.0.0 release of its Python ADK, which it says is already used by Renault Group, Box and Revionics. To coincide with this stable release, Google has also confirmed its first release of the Java ADK v0.1.0.

In terms of management, acknowledging that the Vertex AI Agent Engine already helps developers deploy, manage and scale agents in production, Google has also launched its Agent Engine UI for better agent lifecycle management.

Key features of the new Google Cloud console UI include a dashboard for managing deployed agents, metrics such as requests and CPU usage, session management and tracing, and deployment details with debugging tools.

Further improvements to the Agent2Agent (A2A) protocol have also been confirmed, including v0.2 which brings stateless interaction support for lightweight communications and standardized authentication using OpenAPI-like schema. A Python SDK for A2A has also been released to make it easier for developers to integration agent-to-agent communication within Python-based agents.

Keen to show off the power of A2A, Google boasted of support from Auth0, Box AI, Microsoft, SAP and Zoom.

"These advancements in our ADK, Agent Engine, and A2A protocol are designed to provide you with a comprehensive and flexible platform to bring your most ambitious agent-driven projects to life," Lin and Skinner commented.

You might also like

Craig Hale
Craig Hale

With several years’ experience freelancing in tech and automotive circles, Craig’s specific interests lie in technology that is designed to better our lives, including AI and ML, productivity aids, and smart fitness. He is also passionate about cars and the decarbonisation of personal transportation. As an avid bargain-hunter, you can be sure that any deal Craig finds is top value!

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.