"Google Cloud has updated its Vertex AI Agent Builder with new observability dashboards, faster build-and-deploy tools, and stronger governance controls, aiming to make it easier for developers to move AI agents from prototype to production at scale. The update adds an observability dashboard within the Agent Engine runtime to track token usage, latency, and error rates, along with a new evaluation layer that can simulate user interactions to test agent reliability."
"New governance tools, such as agent identities tied to Cloud IAM and Model Armor, which block prompt injection attacks, are designed to improve security and compliance. The ADK, which Google says has been downloaded more than seven million times, now supports Go in addition to Python and Java. This broader language support is aimed at making the framework accessible to a wider developer base and improving flexibility for enterprise teams building on multi-language stacks. Google has also expanded managed services within the Agent Engine runtime."
Google Cloud updated Vertex AI Agent Builder with observability, faster build-and-deploy tools, and stronger governance to enable moving AI agents to production. The update adds an observability dashboard in Agent Engine to track token usage and latency and an evaluation layer that simulates user interactions to test reliability. Developers can deploy agents with a single ADK command. Governance features include agent identities tied to Cloud IAM and Model Armor to block prompt injection. The ADK now supports Go in addition to Python and Java. Managed services allow deployment from the ADK CLI without a full Google Cloud account. Agents can be registered in Gemini Enterprise to centralize custom agents and integrate internal tools with generative AI workflows.
Read at InfoWorld
Unable to calculate read time
Collection
[
|
...
]