{"id":7062992,"date":"2026-09-21T11:01:46","date_gmt":"2026-09-21T11:01:46","guid":{"rendered":"https:\/\/peraltafinancing.com\/uncategorized\/build-and-run-your-simple-fact-checker-ai-agent\/"},"modified":"2026-09-21T11:01:46","modified_gmt":"2026-09-21T11:01:46","slug":"build-and-run-your-simple-fact-checker-ai-agent","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=7062992","title":{"rendered":"Build and Run Your Simple Fact-Checker AI Agent"},"content":{"rendered":"


\n<\/p>\n

\n

Have you ever tried building an AI agent, only to get bogged down in massive, complex frameworks just to get a basic output? If you want a clean, code-first way to build and debug agents without the boilerplate, Google\u2019s open-source Agent Development Kit (ADK) is what you need. In this post, you will learn how to set up the Python SDK, code your first Gemini-powered agent that checks facts, and test it locally using ADK\u2019s built-in web playground. Let’s get started!<\/p>\n

\"Getting<\/p>\n

Table of contents #<\/a><\/h2>\n

Prerequisites #<\/a><\/h2>\n

Before you get your hands dirty with the code, let\u2019s get the following prerequisites mentioned:<\/p>\n

    \n
  1. As you will be using Python with Google ADK, you must have Python and uv<\/a> installed and working. For the demo, we will use uv version 0.11.7 and Python version 3.12<\/li>\n
  2. You will need basic knowledge of how Python, pip, and virtualenv<\/a> work.<\/li>\n
  3. Knowledge of Google ADK<\/a> will be beneficial<\/li>\n
  4. You will need a working API key on Google AI Studio, for which you might need a working Google Cloud Platform (GCP) project and a valid GCP account with payment enabled or GCP credit.<\/li>\n<\/ol>\n

    In the next section, you will learn about the Google Agent Development Kit (ADK).<\/p>\n

    Google Agent Development Kit (ADK) #<\/a><\/h2>\n

    Google ADK is an open-source agent development framework that enables you to build, debug, and deploy AI Agents at enterprise scale. It is available in multiple languages, including Python, TypeScript, Go, Java, and Kotlin. Based on the ADK samples<\/a> and examples, Python is the most popular language for building an AI agent with ADK at this point. ADK version 2.0<\/a> has been recently released.<\/p>\n

    In my experience, it is a good framework to build AI Agents. With less than 100 lines of code, you can build something useful and meaningful. For the example used in the tutorial, you will build a simple conversational single-agent tool that can verify facts.<\/p>\n

    Fact checker agent #<\/a><\/h2>\n

    As a demo for this blog post (a tutorial), you will build a fact-checker agent using the Google Agent Development Kit (ADK). The aim is simple: you see a news post, or someone makes a statement, but you are not sure whether it is a fact or a false opinion (even worse, fake news). You can pass that statement to this AI agent, and it will tell you whether it is a fact.<\/p>\n

    In the next section, get ready to roll up your sleeves and code a simple fact-checker AI agent, then run it locally on your machine.<\/p>\n

    Build the agent #<\/a><\/h3>\n

    To build the fact-checker agent, you can start by running the following commands:<\/p>\n

    mkdir<\/span> fact-checker-agent-adkcd<\/span> fact-checker-agent-adk<\/code><\/pre>\n
    Then you can run:<\/p>\n
    uv inituv add<\/span> google-adk<\/code><\/pre>\n
    It will initialize the project with uv, and add the Google ADK package to the project with its CLI.<\/p>\n
    \"Adding<\/p>\n
    Now you have google adk<\/code> installed. At the time of writing, the version is 2.1. You can check it by running uv run adk --version<\/code>.<\/p>\n
    To create the fact checker agent with the adk<\/code> CLI, run the command below and answer the questions about the model, whether to use Vertex AI or an API key from Google AI Studio. You will need to execute the following command:<\/p>\n
    uv run adk create fact_checker<\/code><\/pre>\n
    Then answer the questions, which will look like:<\/p>\n
    \"Creating<\/p>\n
    For this tutorial, you will use Google AI Studio, and you will need to create an API key on Google AI Studio to continue building the AI Agent.<\/p>\n
    It will create a .\/fact_checker\/agent.py<\/code> file with the following contents:<\/p>\n
    from<\/span> google.<\/span>adk.<\/span>agents.<\/span>llm_agent import<\/span> Agent
    root_agent =<\/span> Agent(<\/span>model=<\/span>'gemini-2.5-flash'<\/span>,<\/span>name=<\/span>'root_agent'<\/span>,<\/span>description=<\/span>'A helpful assistant for user questions.'<\/span>,<\/span>instruction=<\/span>'Answer user questions to the best of your knowledge'<\/span>,<\/span>)<\/span><\/p><\/code><\/pre>\n
    Replace it with the following contents to create your fact checker<\/code> agent:<\/p>\n
    from<\/span> dotenv import<\/span> load_dotenvfrom<\/span> google.<\/span>adk.<\/span>agents import<\/span> Agentfrom<\/span> google.<\/span>adk.<\/span>apps.<\/span>app import<\/span> Appfrom<\/span> google.<\/span>adk.<\/span>tools import<\/span> google_searchfrom<\/span> google.<\/span>genai import<\/span> types
    load_dotenv(<\/span>override=<\/span>True<\/span>)<\/span><\/p>
    root_agent =<\/span> Agent(<\/span>name=<\/span>\"Facts\"<\/span>,<\/span>model=<\/span>\"gemini-flash-latest\"<\/span>,<\/span> instruction=<\/span>\"\"\"You are a fact checker. You will be skeptical about anything that is said to you. You will search the web and verify the given information; if it does not match, you will respond with the latest and factual information.\"\"\"<\/span>,<\/span>description=<\/span>\"An Agent to provide only facts about a given topic using Google Search.\"<\/span>,<\/span>generate_content_config=<\/span>types.<\/span>GenerateContentConfig(<\/span>temperature=<\/span>0.1<\/span> )<\/span>,<\/span>tools=<\/span>[<\/span>google_search]<\/span>,<\/span>)<\/span><\/p>
    app =<\/span> App(<\/span>name=<\/span>\"fact_checker\"<\/span>,<\/span> root_agent=<\/span>root_agent)<\/span><\/p><\/code><\/pre>\n
    The code above does the following:<\/p>\n