AI for customer support automation in AI for Everyone - Mini Project: Build & Apply

AI for Customer Support Automation

📖 Scenario: You work in a company that wants to improve its customer support. The company plans to use AI to help answer common questions automatically, so customers get faster help.

🎯 Goal: Build a simple step-by-step plan showing how AI can be set up to automate customer support tasks.

📋 What You'll Learn

Create a list of common customer questions

Add a threshold for question similarity to decide when AI should answer

Write a simple matching logic to find if a customer's question matches a common question

Add a final step to confirm when AI will respond automatically

💡 Why This Matters

🌍 Real World

Companies use AI to quickly answer common customer questions, reducing wait times and freeing human agents for complex issues.

💼 Career

Understanding how AI can automate customer support is valuable for roles in customer service management, AI product development, and technical support.

1

Create a list of common customer questions

Create a list called common_questions with these exact questions as strings: 'What are your business hours?', 'How can I reset my password?', 'Where is my order?', 'Do you offer refunds?'.

AI for Everyone

# Create the list common_questions with the exact questions
# Your code here

Need a hint?

Use square brackets [] to create a list and include each question as a string inside quotes.

2

Add a similarity threshold for AI response

Create a variable called similarity_threshold and set it to 0.7. This will help decide when AI should answer a question automatically.

AI for Everyone

common_questions = [
    'What are your business hours?',
    'How can I reset my password?',
    'Where is my order?',
    'Do you offer refunds?'
]
# Create similarity_threshold variable and set it to 0.7
# Your code here

Need a hint?

Just assign the number 0.7 to the variable similarity_threshold.

3

Write matching logic for customer questions

Write a function called is_similar_question that takes two strings: customer_question and common_question. Inside, return True if the two questions are exactly the same, otherwise return False. Then, create a list called matches that uses a list comprehension to check each question in common_questions against a variable customer_input using is_similar_question.

AI for Everyone

common_questions = [
    'What are your business hours?',
    'How can I reset my password?',
    'Where is my order?',
    'Do you offer refunds?'
]
similarity_threshold = 0.7
customer_input = 'How can I reset my password?'
# Define is_similar_question function
# Create matches list using list comprehension
# Your code here

Need a hint?

Use a simple function that compares two strings with ==. Then use a list comprehension to apply this function to each question.

4

Add final decision for AI response

Create a variable called ai_should_respond and set it to True if any value in matches is True, otherwise False. Use the any() function.

AI for Everyone

common_questions = [
    'What are your business hours?',
    'How can I reset my password?',
    'Where is my order?',
    'Do you offer refunds?'
]
similarity_threshold = 0.7
customer_input = 'How can I reset my password?'

def is_similar_question(customer_question, common_question):
    return customer_question == common_question

matches = [is_similar_question(customer_input, question) for question in common_questions]
# Set ai_should_respond to True if any match is True, else False
# Your code here

Need a hint?

Use the built-in any() function to check if any item in the list is True.