From plug-and-play to custom agents: The Complete Path to Building Agents with Google’s AI Stack

Over the past few months, Google has been shaping an entirely new way to build intelligent systems: agents that can reason, act, and connect deeply with enterprise data.

With Gemini Enterprise (formerly Agentspace), and the Agent Development Kit (ADK), google now offers a complete gradient of control: from quick, no-code agents and connectors to fully customized, autonomous applications.

Here’s what that journey looks like.

1. Native connectors in Gemini Enterprise (formerly called AgentSpace)

Native connectors on gemini enterprise

Here, you can launch an agent in minutes by connecting built-in integrations such as Gmail, Drive, Jira, Confluence, ServiceNow, Zendesk, etc.

No code, no setup. The connectors handle authentication, data access, and response generation automatically.

Jira Native connector — gemini enterprise

It’s a powerful way to make enterprise data conversational, your agent can fetch tasks, search documents, or analyze tickets out of the box. But this simplicity also means limited flexibility. The agent can only operate within the scope of those prebuilt connectors.

2. Connect custom data sources to AgentSpace (Gemini Enterprise)

The next step is to bring your own data into the ecosystem. With Vertex AI Search (built on Discovery Engine), you can ingest PDFs, manuals, reports, or support content into a custom datastore and connect that datastore to your Agentspace agent. ACLs can also be respected while doing this. Refer to: https://medium.com/@aashna-kunk/agentspace-searches-on-custom-data-sources-respecting-acls-6b1a03fbc833

This setup allows you to extend the agent’s knowledge far beyond Google’s standard connectors. Instead of relying solely on Gmail or Drive, your agent can now search your own corpus and ground responses in context-specific material.

It’s the bridge between a general assistant and a domain expert, a tailored RAG (retrieval-augmented generation) system that speaks your organization’s language.

3. Build custom agents built in ADK and deployed to Agentspace

Once you need more than retrieval, when your agent has to reason, plan, or orchestrate multiple tools: that’s where the Agent Development Kit (ADK) comes in.

ADK allows you to define a complete multi-agent system in code.You can specify its reasoning model, the tools it can call (for instance, Snowflake, custom data, or Vertex Search), and the logic behind its responses.

When you deploy it to Gemini Enterprise (formerly AgentSpace), your organization gets a managed, observable agent that can handle complex workflows while still integrating into Google’s ecosystem.

ADK agent — local testing

A custom snowflake agent built using ADK, deployed on Gemini Enterprise (AgentSpace)

This is the sweet spot for most enterprise teams: enough customization to build meaningful logic, but still within a governed, deployable environment.

4. Fully custom agents: ADK with your own UI

The final level of customization removes the limits altogether. Here, you still use ADK as the reasoning and orchestration engine, but you build your own frontend: perhaps a Streamlit dashboard, a React chat interface, or even an internal web app.

For instance, I built an interior design assistant using Google’s ADK: it combines BigQuery embeddings with data scraped from the store’s website to generate style-based recommendations.

Fully Custom Interface built on ADK

In this design, the agent lives entirely on your infrastructure. It can call Vertex AI Search directly, integrate with your existing APIs, manage access control, and surface insights in your own branded experience. This is what powers bespoke copilots: systems that not only talk but act on your behalf, tightly integrated with your data and workflows.

Google’s Gemini Enterprise and Agent Development stack turns what used to be a maze of APIs into a canvas for real intelligence. It’s where agents stop being demos, and start running your business.