Building Your First AI Chatbot

What You'll Build

By the end of this guide, you'll have a working chatbot that holds conversations and remembers context. We use Python, but concepts apply to any language.

Step 1: Install the SDK

pip install openai

Step 2: Basic Conversation

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is machine learning?"}
    ]
)
print(response.choices[0].message.content)

Step 3: Add Memory

Keep conversation history so the AI "remembers":

messages = [{"role": "system", "content": "You are helpful."}]
while True:
    user_input = input("You: ")
    if user_input.lower() == "quit": break
    messages.append({"role": "user", "content": user_input})
    response = client.chat.completions.create(
        model="gpt-4o-mini", messages=messages)
    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    print(f"Bot: {reply}")

Step 4: Customise

The system message is where the magic happens. For customer support: "You are a support agent for [Company]. Be friendly, concise, and offer to escalate to a human." For writing: "You are a professional editor. Suggest changes and explain why."

Using GPT-4o mini at $0.15/$0.60 per million tokens, a chatbot handling 1,000 conversations/day (~500 tokens each) costs roughly $15/month.