“`html

Build Your First AI Agent: A Step-by-Step Tutorial for Beginners

1. What Is an AI Agent & Why Build One?

• Define an AI agent vs. a simple chatbot – autonomy, tools, memory, and goal-oriented behaviour.
• Real-world use cases: customer support triage, personal research assistant, content summariser.
• What you’ll build in this tutorial: a lightweight agent that can search the web, run code, and answer questions.

2. Prerequisites & Tools You’ll Need

• Python 3.10+ installed, plus a free OpenAI or Anthropic API key (list exact links to sign up).
• Core libraries: `openai`, `python-dotenv`, `requests`, and `duckduckgo-search` – include pip install commands.
• A code editor (VS Code recommended) and a basic understanding of functions and API calls.

3. Setting Up Your Project Structure

• Create a project folder, virtual environment, and `.env` file to store your API key securely.
• Write a simple `config.py` to load environment variables and initialise the AI client.
• Build a `tools.py` module with two stub functions: `web_search()` and `run_python_code()`.

4. Building the Agent Core – The ReAct Loop

• Implement the Thought–Action–Observation loop: prompt the LLM to decide which tool to call.
• Parse the LLM’s output to extract tool name and arguments (use regex or JSON parsing).