Vertex AI is now part of Gemini Enterprise Agent Platform, Google Cloud’s newer name for the platform that includes its model and agent-building services. Google says the transition combines Vertex AI’s model selection, model building and agent building with new agent integration, DevOps, orchestration and security features. “Agent Builder” is part of the new platform, while several familiar Vertex AI product names have changed.
What is Gemini Enterprise Agent Platform?
Google Cloud announced Gemini Enterprise Agent Platform on April 22, 2026, describing it as the evolution of Vertex AI. In the company’s words, “It’s the evolution of Vertex AI, bringing the model selection, model building, and agent building capabilities that customers love, together with new features for agent integration, DevOps, orchestration, and security.” That is Google’s description of the platform, not an independent comparison or performance assessment.
The name change does not mean every underlying capability was newly launched at once. The platform brings together existing model and agent services with additional platform features, while individual models and APIs continue to have their own release dates and availability statuses.
What are Vertex AI and Agent Builder called now?
Google’s Agent Platform release notes list these relevant product-name changes:
#1 Best Overall
| Earlier name | Name in Gemini Enterprise Agent Platform |
|---|---|
| Vertex AI Studio | Agent Studio |
| Vertex AI Model Garden | Model Garden |
| Vertex AI Search | Agent Search |
| Vertex AI RAG Engine | RAG Engine |
| Vertex AI Agent Engine | Agent Runtime |
| Vertex AI Vector Search 2.0 | Agent Retrieval |
The release notes state that Agent Builder is now part of Gemini Enterprise Agent Platform. They do not list “Agent Builder” as a direct one-to-one replacement name for a single Vertex AI product in the table above; it is the agent-building capability within the broader platform.
What new model, RAG and agent capabilities were announced?
Google’s generative AI release notes record separate updates on separate dates. Their status matters: an announcement or preview is not the same as a generally available service.
Rank #2
| Date | Change | Status or scope |
|---|---|---|
| April 3, 2026 | Gemma 4 26B A4B IT appeared in Model Garden. | Experimental launch and managed API, according to Google’s notes. |
| April 3, 2026 | RAG Engine Serverless mode was introduced. | Public preview. |
| April 6, 2026 | Schema-based metadata search was added for Vertex AI RAG Engine. | Corpus metadata can be used to filter retrieved contexts. |
| April 17, 2026 | RAG Cross Corpus Retrieval was introduced. | Public preview; retrieves relevant contexts or generates answers across multiple RAG corpora through the AsyncRetrieveContexts and AskContexts APIs. |
These entries show additions to Google’s model and retrieval tools; they do not establish a general improvement in large language model quality or performance. The reviewed announcements provide no controlled benchmark comparing the platform with other cloud AI services.
What agent-building features were described before the platform rename?
A separate Google Cloud Agent Builder announcement described capabilities that provide context for the platform transition. It covered configurable context layers in the Python Agent Development Kit (ADK), managed Agent Engine observability and evaluation, and native agent identities with security safeguards. The named ADK context layers were:
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Rank #3
- Static: context intended to remain consistent.
- Turn: context scoped to a conversation turn.
- User: context associated with a user.
- Cache: context held for reuse.
Google reported more than 7 million Python ADK downloads in a 2025 announcement. That is a cumulative download figure reported by Google at the time of publication, not a count of active users, deployed agents or customers.
Is Vertex AI Agent Engine still available?
Google’s release notes call Vertex AI Agent Engine Agent Runtime as part of the naming changes. The notes list support for long-running operations of up to seven days, sub-second cold starts and provisioning in under one minute. These are vendor-documented service capabilities; workload outcomes can depend on the applicable product terms and conditions, so treat the figures as documented limits or characteristics rather than a guarantee for every deployment.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What should existing Vertex AI users check?
Users planning a change should map the exact service and API they rely on to its current Agent Platform name, then verify availability and compatibility for their workload. In particular:
- Check whether the feature is generally available, in preview or experimental; preview and experimental features can change.
- Confirm supported regions, API compatibility, data handling requirements, and identity and security controls for the intended deployment.
- Assess model lifecycle, retrieval and grounding needs, agent framework and deployment options, and observability and evaluation requirements before migrating or choosing a platform.
- Compare pricing against expected usage using current Google Cloud documentation; the announcements summarized here do not establish a price or a cross-vendor winner.
Google marked Vertex AI Extensions deprecated on May 26, 2026, and said they would shut down after November 26, 2026. Google recommends migrating to Agent Platform to avoid service disruption. Because this is a dated retirement notice and the deadline is approaching, users who depend on Extensions should check Google’s current release notes and migration guidance for the exact shutdown date and supported migration path.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
