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

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

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

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

Hint

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

Practice

1. What is one main benefit of using AI in customer support automation?

easy

A. It can answer common questions quickly and accurately.

B. It replaces all human support completely.

C. It only works during business hours.

D. It requires customers to wait longer for help.

Solution

1. Step 1: Understand AI's role in customer support

   AI is designed to handle common questions fast and accurately to improve service.

2. Step 2: Compare options with AI benefits

   Only It can answer common questions quickly and accurately. correctly states AI's benefit; others are false or misleading.

3. Final Answer:

   It can answer common questions quickly and accurately. -> Option A

4. Quick Check:

   AI benefit = quick, accurate answers [OK]

Hint: AI speeds up common question answers [OK]

Common Mistakes:

• Thinking AI replaces all human support
• Believing AI works only during business hours
• Assuming AI causes longer wait times

2. Which of the following is the correct way AI helps customer support?

easy

A. By deleting customer complaints automatically.

B. By answering complex legal questions without human help.

C. By ignoring customer messages until a human replies.

D. By providing 24/7 support for common issues.

Solution

1. Step 1: Identify AI's support capabilities

   AI can provide round-the-clock help for common problems but not complex legal advice alone.

2. Step 2: Evaluate each option

   By providing 24/7 support for common issues. correctly states AI provides 24/7 support; others describe incorrect or harmful actions.

3. Final Answer:

   By providing 24/7 support for common issues. -> Option D

4. Quick Check:

   AI support = 24/7 help [OK]

Hint: AI works anytime for common questions [OK]

Common Mistakes:

• Assuming AI handles all complex questions alone
• Thinking AI ignores customers
• Believing AI deletes complaints

3. Consider this scenario: An AI chatbot receives 100 customer questions, 80 are common and 20 are complex. How many questions can AI handle alone effectively?

medium

A. All 100 questions

B. Only the 80 common questions

C. Only the 20 complex questions

D. None, AI cannot handle questions alone

Solution

1. Step 1: Understand AI's strength in question types

   AI is best at handling common questions quickly and accurately, but complex questions need human help.

2. Step 2: Apply this to the scenario

   Out of 100 questions, AI can handle the 80 common ones alone effectively.

3. Final Answer:

   Only the 80 common questions -> Option B

4. Quick Check:

   AI handles common questions = 80 [OK]

Hint: AI handles common, humans handle complex [OK]

Common Mistakes:

• Thinking AI can handle all questions alone
• Confusing complex with common questions
• Assuming AI cannot handle any questions

4. A company uses AI to answer customer questions but notices many customers get wrong answers. What is the most likely problem?

medium

A. The AI is only trained on common questions, but customers ask complex ones.

B. The AI is working perfectly and no changes are needed.

C. The AI deletes all customer messages by mistake.

D. The AI only works during business hours.

Solution

1. Step 1: Identify why AI gives wrong answers

   AI trained only on common questions struggles with complex or new questions, causing errors.

2. Step 2: Evaluate options

   The AI is only trained on common questions, but customers ask complex ones. correctly explains the most likely cause of wrong answers; others deny the problem, suggest deletions, or time limitations.

3. Final Answer:

   The AI is only trained on common questions, but customers ask complex ones. -> Option A

4. Quick Check:

   Wrong answers = AI training mismatch [OK]

Hint: Mismatch training causes wrong AI answers [OK]

Common Mistakes:

• Assuming AI always works perfectly
• Thinking AI deletes messages randomly
• Believing AI only works limited hours

5. A company wants to improve customer support by combining AI and human agents. Which approach is best?

hard

A. Use AI to ignore customer complaints and humans to answer only positive feedback.

B. Use only AI and remove all human agents.

C. Use AI to handle common questions and route complex issues to humans.

D. Use only humans and avoid AI completely.

Solution

1. Step 1: Understand combined AI-human support benefits

   AI efficiently handles common questions, freeing humans to focus on complex issues.

2. Step 2: Evaluate options for best practice

   Use AI to handle common questions and route complex issues to humans. correctly combines AI and humans; others either remove humans or misuse AI.

3. Final Answer:

   Use AI to handle common questions and route complex issues to humans. -> Option C

4. Quick Check:

   Best support = AI + human teamwork [OK]

Hint: Combine AI for simple, humans for complex [OK]

Common Mistakes:

• Thinking AI can replace humans fully
• Ignoring AI benefits completely
• Misusing AI to ignore complaints