Google Cloud is making its AI Agent Builder much smarter and faster to deploy
- Developers can now create self-healing AI agents with Google Cloud.
- Go has been added to the list of supported programming languages
- Dashboards Improve Observability and Security
Google Cloud has rolled out a series of updates to its Vertex AI Agent Builder in hopes that developers will continue to build, test and deploy AI agents on its platform, with a focus on faster creation.
The company has updated its Agent Development Kit (ADK) so developers can use prebuilt plugins, like a new one designed to help agents “self-heal,” meaning they can become even more autonomous.
Go has also been added as a supported programming language, on top of existing support for Python and Java, which Google says increases accessibility.
Google wants developers to create their AI agents even faster
Once the agents are created, a single command via ADK CLI will see them deployed. “This is a major upgrade to help you move your agent from local development to live testing and production use quickly and seamlessly,” noted Mike Clark, Director of Product Management.
Once their AI agents are deployed, developers will now benefit from additional observability through dashboard enhancements, including monitoring token usage, latency, errors, and tool calls.
A dedicated playground will also allow them to test and debug faster, while the Traces tab allows you to visualize sequences of agent actions to diagnose issues with clear paths.
Nitin Sharma, PayPal’s Principal AI Engineer, praised Google Cloud’s Vertex AI Agent Builder for its support in inspection operations.[ing] interactions with agents, follow[ing] state changes and management[ing] multi-agent workflows.
But faster development and deployment could lead to increased security risks, which is why Google has been looking into that, too.
“Many developers prototype AI agents, but moving to a scalable, secure, well-managed production agent is much more complex,” Clark added.
Model Armor will filter tool calls and agent responses, verifying rapid injection, while the Security Command Center serves as an inventory of agent assets.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
