Phase 1: ADK Onboarding journey revision

docs/get-started/index.md

@@ -1,58 +1,23 @@
-# Get Started
+# Get started
 
-Agent Development Kit (ADK) is designed to empower developers
-to build, manage, evaluate and deploy AI-powered agents. It provides a robust
-and flexible environment for creating both conversational and non-conversational
-agents, capable of handling complex tasks and workflows.
+Agent Development Kit (ADK) is designed to empower developers to quickly build,
+manage, evaluate and deploy AI-powered agents. These quick start guides get you
+set up and running a simple agent in less than 20 minutes.
 
 <div class="grid cards" markdown>
 
--   :material-console-line: **Installation**
+-   :fontawesome-brands-python:{ .lg .middle } **Python Quickstart**
 
     ---
+    Create your first Python ADK agent in minutes.
 
-    Install `google-adk` for Python or Java and get up and running in minutes.
+    [:octicons-arrow-right-24: Start with Python](/adk-docs/get-started/python) <br>
 
-    [:octicons-arrow-right-24: More information](installation.md)
-
--   :material-console-line: **Quickstart**
-
-    ---
-
-    Create your first ADK agent with tools in minutes.
-
-    [:octicons-arrow-right-24: More information](quickstart.md)
-
--   :material-console-line: **Quickstart (streaming)**
-
-    ---
-
-    Create your first streaming ADK agent.
-
-    [:octicons-arrow-right-24: More information](streaming/quickstart-streaming.md)
-
--   :material-console-line: **Tutorial**
+-   :fontawesome-brands-java:{ .lg .middle } **Java Quickstart**
 
     ---
+    Create your first Java ADK agent in minutes.
 
-    Create your first ADK multi-agent.
-
-    [:octicons-arrow-right-24: More information](../tutorials/index.md)
-
--   :material-rocket-launch-outline: **Discover sample agents**
-
-    ---
-
-    Discover sample agents for retail, travel, customer service, and more!
-
-    [:octicons-arrow-right-24: Discover adk-samples](https://github.com/google/adk-samples){:target="_blank"}
-
--   :material-graph: **About**
-
-    ---
-
-    Learn about the key components of building and deploying ADK agents.
-
-    [:octicons-arrow-right-24: More information](about.md)
+    [:octicons-arrow-right-24: Start with Java](/adk-docs/get-started/java.md) <br>
 
 </div>

docs/get-started/java.md

@@ -0,0 +1,131 @@
+# Java Quickstart for ADK
+
+This guide shows you how to get up and running with the Agent Development Kit
+for Java. Before you start, make sure you have the following installed:
+
+*   Java 17 or later
+*   Maven 3.9 or later
+
+## Installation
+
+Add the following dependency to your `pom.xml` file:
+
+```xml
+<dependencies>
+    <dependency>
+        <groupId>com.google.adk</groupId>
+        <artifactId>adk-core</artifactId>
+        <version>0.0.1-SNAPSHOT</version>
+    </dependency>
+</dependencies>
+```
+
+## Set up your API key
+
+This starter project uses the Gemini API, which requires an API key. If you
+don't already have Gemini API key, create a key in Google AI Studio on the 
+[API Keys](https://aistudio.google.com/app/apikey) page.
+
+In a terminal window, write your API key into an `.env` file as an environment variable:
+
+=== "Windows"
+
+    ```shell
+    echo 'GOOGLE_API_KEY="YOUR_API_KEY"' > .env
+    ```
+
+=== "MacOS / Linux"
+
+    ```shell
+    echo 'export GOOGLE_API_KEY="YOUR_API_KEY"' > .env
+    ```
+
+## Create an agent project
+
+Run the `adk create` command to start a new agent project.
+
+```shell
+adk create my_agent --language java
+```
+
+
+### Explore the agent project
+
+The created agent project has the following structure, with the `MyAgent.java`
+file containing the main control code for the agent.
+
+```shell
+my_agent/
+    src/main/java/com/example/MyAgent.java  # main agent code.
+    pom.xml                                # project configuration.
+    .env                                   # API keys or project IDs
+```
+
+The `MyAgent.java` file contains a `main` method which is the entry point for
+the agent. You can also define tools for the agent to use. The following
+example includes an additional `getCurrentTime` tool for use by the agent:
+
+```java
+import com.google.adk.agents.Agent;
+import com.google.adk.tools.FunctionTool;
+
+import java.util.Map;
+
+public class MyAgent {
+
+    public static void main(String[] args) {
+        var timeTool = new FunctionTool(
+                "get_current_time",
+                "Returns the current time in a specified city.",
+                MyAgent.class,
+                "getCurrentTime"
+        );
+
+        var agent = Agent.builder()
+                .setName("time_teller_agent")
+                .setModel("gemini-1.5-flash")
+                .setInstruction("You are a helpful assistant that tells the current time in cities. Use the 'get_current_time' tool for this purpose.")
+                .setDescription("Tells the current time in a specified city.")
+                .setTools(java.util.List.of(timeTool))
+                .build();
+
+        // TODO: Run the agent
+    }
+
+    public static Map<String, Object> getCurrentTime(String city) {
+        if (city.equalsIgnoreCase("new york")) {
+            return Map.of("status", "success", "time", "10:30 AM EST");
+        }
+        return Map.of("status", "error", "message", "Time for " + city + " not available.");
+    }
+}
+```
+
+## Run your agent
+
+Run your agent using the `adk run` command-line tool.
+
+```shell
+adk run my_agent
+```
+
+![adk-run.png](../assets/adk-run.png)
+
+### Run agent with web interface
+
+The ADK framework provides web interface you can use to test and interact with
+your agent. You can start the web interface using the following terminal
+
+```shell
+adk web my_agent
+```
+This command starts a web server with a chat interface for your agent:
+
+![adk-web-dev-ui-chat.png](../assets/adk-web-dev-ui-chat.png)
+
+## Next: build your agent
+
+Now that you have ADK installed and your first agent running, try building
+your own agent with our intermediate build guides:
+
+*  [Build your agent](/adk-docs/tutorials/)

docs/get-started/python.md

@@ -0,0 +1,121 @@
+# Python Quickstart for ADK
+
+This guide shows you how to get up and running with the Agent Development Kit
+(ADK) for Python. Before you start, make sure you have the following installed:
+
+*   Python 3.9 or later
+*   `pip` for installing packages   
+
+## Installation
+
+Install ADK by running the following command:
+
+```shell
+pip install google-adk
+```
+
+??? tip "Recommended: create and activate a Python virtual environment"
+
+    Create a Python virtual environment:
+
+    ```shell
+    python -m venv .venv
+    ```
+
+    Activate the Python virtual environment:
+
+    === "Windows CMD"
+
+        ```shell
+        .venv\Scripts\activate.bat
+        ```
+
+    === "Windows Powershell"
+
+        ```shell
+        .venv\Scripts\Activate.ps1
+        ```
+
+    === "MacOS / Linux"
+
+        ```shell
+        source .venv/bin/activate
+        ```
+
+## Create an agent project
+
+Run the `adk create` command to start a new agent project. 
+
+```shell
+adk create my_agent
+```
+
+??? tip "Note: API key required"
+    The created project uses Gemini, which requires an API key. Create a key in
+    Google AI Studio on the [API Keys](https://aistudio.google.com/app/apikey) page.
+    You can also use a Google Cloud project ID with access to the Vertex AI.
+
+### Explore the agent project
+
+The created agent project has the following structure, with the `agent.py`
+file containing the main control code for the agent.
+
+```shell
+my_agent/
+    agent.py      # main agent code.
+    .env          # API keys or project IDs
+    __init__.py
+```
+
+The `agent.py` file contains a `root_agent` definition which is the only
+required element of an ADK agent. You can also define tools for the agent to
+use. The following example includes an additional `get_current_time` tool for
+use by the agent:
+
+```python
+from google.adk.agents.llm_agent import Agent
+
+# Mock tool implementation
+def get_current_time(city: str) -> dict:
+    """Returns the current time in a specified city."""
+    if city.lower() == "new york":
+        return {"status": "success", "time": "10:30 AM EST"}
+    return {"status": "error", "message": f"Time for {city} not available."}
+
+root_agent = Agent(
+    model='gemini-2.5-flash',
+    name='root_agent',
+    description="Tells the current time in a specified city.",
+    instruction="You are a helpful assistant that tells the current time in cities. Use the 'get_current_time' tool for this purpose.",
+    tools=[get_current_time]
+)
+```
+
+## Run your agent
+
+Run your agent using the `adk run` command-line tool.
+
+```shell
+adk run my_agent
+```
+
+![adk-run.png](../assets/adk-run.png)
+
+### Run agent with web interface
+
+The ADK framework provides web interface you can use to test and interact with
+your agent. You can start the web interface using the following terminal
+
+```shell
+adk web my_agent
+```
+This command starts a web server with a chat interface for your agent:
+
+![adk-web-dev-ui-chat.png](../assets/adk-web-dev-ui-chat.png)
+
+## Next: build your agent
+
+Now that you have ADK installed and your first agent running, try building
+your own agent with our intermediate build guides:
+
+*  [Build your agent](/adk-docs/tutorials/)

docs/get-started/quickstart.md

@@ -1,4 +1,4 @@
-# Quickstart
+# Build a multi-tool agent
 
 This quickstart guides you through installing the Agent Development Kit (ADK),
 setting up a basic agent with multiple tools, and running it locally either in the terminal or in the interactive, browser-based dev UI.

docs/get-started/streaming/index.md

@@ -1,12 +1,12 @@
-# Streaming Quickstarts
+# Build a streaming agent
 
 The Agent Development Kit (ADK) enables real-time, interactive experiences with your AI agents through streaming. This allows for features like live voice conversations, real-time tool use, and continuous updates from your agent.
 
 This page provides quickstart examples to get you up and running with streaming capabilities in both Python and Java ADK.
 
 <div class.="grid cards" markdown>
 
--   :fontawesome-brands-python:{ .lg .middle } **Python ADK: Streaming Quickstart**
+-   :fontawesome-brands-python:{ .lg .middle } **Python ADK: Streaming agent**
 
     ---
     This example demonstrates how to set up a basic streaming interaction with an agent using Python ADK. It typically involves using the `Runner.run_live()` method and handling asynchronous events.
@@ -16,7 +16,7 @@ This page provides quickstart examples to get you up and running with streaming
 
 <!-- This comment forces a block separation -->
 
--   :fontawesome-brands-java:{ .lg .middle } **Java ADK: Streaming Quickstart**
+-   :fontawesome-brands-java:{ .lg .middle } **Java ADK: Streaming agent**
 
     ---
     This example demonstrates how to set up a basic streaming interaction with an agent using Java ADK. It involves using the `Runner.runLive()` method, a `LiveRequestQueue`, and handling the `Flowable<Event>` stream.

docs/get-started/streaming/quickstart-streaming-java.md

@@ -1,4 +1,4 @@
-# Quickstart (Streaming / Java) {#adk-streaming-quickstart-java}
+# Build a streaming agent with Java
 
 This quickstart guide will walk you through the process of creating a basic agent and leveraging ADK Streaming with Java to facilitate low-latency, bidirectional voice interactions.
 

docs/get-started/streaming/quickstart-streaming.md

@@ -1,4 +1,4 @@
-# Quickstart (Streaming / Python) {#adk-streaming-quickstart}
+# Build a streaming agent with Python
 
 With this quickstart, you'll learn to create a simple agent and use ADK Streaming to enable voice and video communication with it that is low-latency and bidirectional. We will install ADK, set up a basic "Google Search" agent, try running the agent with Streaming with `adk web` tool, and then explain how to build a simple asynchronous web app by yourself using ADK Streaming and [FastAPI](https://fastapi.tiangolo.com/).