Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
Overview
To use Vertex AI Agent Engine, you must first develop an agent that can be deployed on Vertex AI Agent Engine. The easiest way to develop an agent is to use one of the framework-specific templates that we provide. Framework-specific templates automatically handle some of the common aspects of developing an agent such as serializing objects and separating the code that initializes an agent from the code that responds to prompts. We provide the following framework-specific templates:
Designed based on Google's internal best practices for developers building AI applications or teams needing to rapidly prototype and deploy robust agent-based solutions.
If you are building a multi-agent system, we highly recommend reviewing the A2A Protocol. A2A Protocol is an open standard that enables seamless communication and collaboration between AI agents, regardless of their underlying frameworks. It was donated by Google Cloud to the Linux Foundation in June 2025. To use the A2A SDKs, or try out the samples, check out the GitHub repository.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-28 UTC."],[],[],null,["# Develop an agent\n\nOverview\n--------\n\nTo use Vertex AI Agent Engine, you must first develop an agent that can be deployed on Vertex AI Agent Engine. The easiest way to develop an agent is to use one of the framework-specific templates that we provide. Framework-specific templates automatically handle some of the common aspects of developing an agent such as serializing objects and separating the code that initializes an agent from the code that responds to prompts. We provide the following framework-specific templates:\n\nIf your use case doesn't align with one of the framework-specific templates, you can [develop your own custom agent](/vertex-ai/generative-ai/docs/agent-engine/develop/custom).\n\nAgent2Agent (A2A) protocol\n--------------------------\n\nIf you are building a multi-agent system, we highly recommend reviewing the [A2A Protocol](https://a2a-protocol.org/). A2A Protocol is an open standard that enables seamless communication and collaboration between AI agents, regardless of their underlying frameworks. It was [donated by Google Cloud to the Linux Foundation in June 2025](https://developers.googleblog.com/en/google-cloud-donates-a2a-to-linux-foundation/). To use the A2A SDKs, or try out the samples, check out the [GitHub repository](https://github.com/a2aproject/A2A).\n\nWhat's next\n-----------\n\n- [Develop a custom agent](/vertex-ai/generative-ai/docs/agent-engine/develop/custom).\n- [Evaluate an agent](/vertex-ai/generative-ai/docs/agent-engine/evaluate).\n- [Deploy an agent](/vertex-ai/generative-ai/docs/agent-engine/deploy).\n- [Get support](/vertex-ai/generative-ai/docs/agent-engine/support)."]]
