Google Cloud announced significant advancements in Vertex AI Agent Builder, enhancing tool governance to support secure, scalable and efficient AI agent development across organizations. The updates empower enterprise administrators and developers to manage tool access centrally and build intelligent AI agents faster with enriched lifecycle capabilities.
The latest release integrates Cloud API Registry with Vertex AI Agent Builder, enabling teams to curate and govern approved tools directly within the Agent Builder Console. This provides IT and platform administrators with tighter control over tool access while helping developers leverage consistently managed toolsets across projects.
Stronger Governance and Simplified Tool Management
The enhanced governance framework addresses a common enterprise challenge: duplicative tool creation and fragmented oversight. With Cloud API Registry integration, organizations now benefit from:
- Pre-built tools for Google services, including support for MCP-enabled APIs such as BigQuery and Google Maps.
- Custom MCP server support, allowing enterprises to expose existing APIs securely through Apigee and federate APIs in a unified hub.
- Improved administrator controls to define and govern a centralized catalog of tools.
- Streamlined developer experiences with the new ApiRegistry object in the Agent Development Kit (ADK), enabling easier integration of governed tools into agents.
Accelerated AI Agent Development
In addition to governance enhancements, Google Cloud expanded the Vertex AI Agent Builder platform with features designed to speed up agent creation and improve developer productivity. These include full ADK support for Gemini 3 Pro and Flash models, extended TypeScript support, advanced state management features, Interactions API integration, and A2UI – a toolkit for building secure, dynamic user experiences without traditional UI limitations.
Also Read: AWS Introduces Serverless Visual Workflow in Amazon SageMaker Unified Studio to Simplify Data Orchestration
Scalable Production-Ready Agents
To support enterprise deployment at scale, Google Cloud has transitioned key Agent Engine capabilities – such as session management and memory bank services – to General Availability (GA). These features enable agents to maintain context over long interactions, a crucial requirement for personalized and consistent responses in production environments. Expanded regional availability and updated pricing were also announced to support broader global adoption.
Customer Success with Vertex AI Agent Builder
To illustrate real-world value, industry users shared early success stories:
“Burns & McDonnell uses Vertex AI Agent Builder to transform how organizational knowledge is applied across the enterprise. With Experience IQ, we are building an AI agent using ADK that turns decades of project data and employee experience into real-time, actionable intelligence. Vertex AI enables this innovation to scale responsibly by combining deterministic business rules with probabilistic reasoning, making AI a trusted operational capability not just a productivity tool. This agent helps teams quickly identify the right experience, reduce manual effort in staffing and planning, and make higher-confidence decisions grounded in verified data. With Vertex AI, Burns & McDonnell isn’t just managing knowledge – we are activating experience to drive faster, more confident decisions.” – Matt Olson, Chief Innovation Officer, Burns & McDonnell
“Payhawk uses Vertex AI Agent Builder to transform agents into financial assistants that truly ‘know’ our customers. Leveraging Memory Bank, we moved from stateless interactions to long-term context retention, allowing agents to recall user constraints and historical patterns with continuity. For example, our Financial Controller Agent now remembers habits like expensing small meals and auto-submits them, reducing submission time by over 50%. Similarly, our Travel Agent proactively applies preferences like aisle seats. This significantly drops cognitive load, allowing agents to anticipate needs based on past behavior rather than just reacting to prompts.”- Diyan Bogdanov, Principal Applied AI Engineer, Payhawk
Additional testimonials underline how memory and context capabilities enhance user experience for consumer and creative applications.
Looking Forward
With these enhancements, Google Cloud continues to strengthen Vertex AI as an enterprise-ready platform, reducing friction from prototype to production and enabling governed AI innovation. Organizations interested in leveraging these features can explore updated documentation and release resources on Google Cloud’s official sites.