Feature availability
Build agentic systems with a complete AI stack
Vertex AI eliminates the trade-off between accessing frontier models and utilizing a world-class AI development platform. Because building sophisticated agents requires more than just a model, Vertex AI provides a complete agentic stack designed to manage the complexities of production, governance, and global scale.
Rapidly build intelligent agents: Leverage the Vertex AI Agent Builder stack—including the Agent Development Kit—to move multi-step agentic workflows from prototype to scaled production.
Scale agents with fully managed services: Use Agent Engine to deploy and scale agents in a serverless environment. With Memory Bank and Sessions, your Claude-powered agents maintain persistent, long-term context across multiple interactions for a more natural user experience.
Improve performance and reduce costs: Maintain consistent performance during peak demand by reserving dedicated capacity at a fixed cost with Provisioned Throughput. To further improve efficiency, leverage features like the global endpoint for Claude, prompt caching with flexible Time To Live (TTL), batch predictions, web search (preview), and a 1M token context window (preview) for Claude Opus 4.6.
Run on optimized infrastructure: Vertex AI’s infrastructure is purpose-built to handle the compute demands of frontier models to help lower latency and improve efficiency.
Govern and secure at scale: Integrated governance controls keep agents on task and their actions logged. Secure the full AI stack including models and agents with Google Cloud’s foundational security and data residency controls, protect against novel AI threats like prompt injection and tool poisoning with Model Armor, and get advanced AI Protection in Security Command Center to prioritize AI risks and detect threats.
Why builders choose Claude on Vertex AI
Source Credit: https://cloud.google.com/blog/products/ai-machine-learning/expanding-vertex-ai-with-claude-opus-4-6/
About the Author
