Message roles (system, user, assistant) in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding the role of the system message

In a chat-based AI model, what is the primary purpose of the system message role?

A To provide instructions and set the behavior of the AI assistant

B To generate the AI's responses to the user

C To ask questions and provide user input to the AI

D To store conversation history for later analysis

💡 Hint

Think about who controls the AI's style and rules.

The system message sets the context and rules for the AI assistant, guiding how it should respond throughout the conversation.

❓ Predict Output

intermediate

Output of a chat message sequence

Given the following chat messages, what will the AI assistant reply? Messages: 1. System: "You are a helpful assistant." 2. User: "What is 2 + 2?" Assuming the AI correctly follows instructions, what is the assistant's reply?

A "I don't know."

B "2 + 2 equals 22."

C "Please provide more details."

D "4"

💡 Hint

The system message says the AI is helpful.

The AI assistant follows the system instruction to be helpful and answers the math question correctly with "4".

❓ Model Choice

advanced

Choosing the correct message role for user input

When sending a message to a chat AI model, which message role should be used to represent the human asking questions or giving commands?

A user

B system

C assistant

D moderator

💡 Hint

Think about who is talking to the AI.

The 'user' role represents the human interacting with the AI by asking questions or giving commands.

❓ Metrics

advanced

Evaluating assistant message quality

Which metric best measures how well the assistant messages follow the instructions given in the system message?

A Perplexity on training data

B Number of tokens generated

C Instruction adherence score from human evaluation

D Model size in parameters

💡 Hint

Think about measuring if the AI listens to the system message.

Instruction adherence score from human evaluation directly measures how well the assistant follows system instructions.

🔧 Debug

expert

Identifying the cause of incorrect assistant behavior

A developer notices the AI assistant ignores the system message instructions and gives unrelated answers. Which is the most likely cause?

A The user message was too short

B The system message was not included in the chat messages sent to the model

C The assistant message role was used for user input

D The model size is too large

💡 Hint

Check if the AI received the instructions at all.

If the system message is missing, the AI has no instructions to follow and may respond incorrectly.

Practice

1. What is the main purpose of the system role in AI chat messages?

easy

A. To store conversation history

B. To provide user input or questions

C. To set instructions and guide the AI's behavior

D. To display the AI's answers

Solution

1. Step 1: Understand the roles in AI chat

   The system role is designed to give the AI instructions or context on how to respond.

2. Step 2: Differentiate from other roles

   The user role is for input, and the assistant role is for AI output, so setting instructions fits the system role.

3. Final Answer:

   To set instructions and guide the AI's behavior -> Option C

4. Quick Check:

   System role = instructions [OK]

Hint: System role sets AI instructions, user inputs, assistant replies [OK]

Common Mistakes:

• Confusing system role with user input
• Thinking assistant role sets instructions
• Assuming system role stores chat history

2. Which of the following is the correct way to represent a user message in a chat API call?

easy

A. {"role": "assistant", "content": "Hello!"}

B. {"role": "user", "content": "What is AI?"}

C. {"role": "system", "content": "You are helpful."}

D. {"role": "bot", "content": "I can help."}

Solution

1. Step 1: Identify the role for user input

   The user messages must have the role set to "user" to indicate input from the person.

2. Step 2: Check each option's role field

   {"role": "user", "content": "What is AI?"} uses "user" correctly, while others use "assistant", "system", or invalid "bot".

3. Final Answer:

   {"role": "user", "content": "What is AI?"} -> Option B

4. Quick Check:

   User role = "user" [OK]

Hint: User messages always have role "user" in JSON [OK]

Common Mistakes:

• Using "bot" instead of "assistant" or "user"
• Mixing system role with user messages
• Forgetting to set the role field

3. Given this message list sent to an AI model:

[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"}]

What role will the AI use to respond?

medium

A. system

B. user

C. moderator

D. assistant

Solution

1. Step 1: Understand message roles in conversation

   The AI responds with messages having the role "assistant" to show its output.

2. Step 2: Identify the role for AI replies

   Since the input messages include system and user roles, the AI's reply will be labeled as "assistant".

3. Final Answer:

   assistant -> Option D

4. Quick Check:

   AI replies use role "assistant" [OK]

Hint: AI responses always have role "assistant" [OK]

Common Mistakes:

• Thinking AI replies use "system" role
• Confusing user input role with AI output
• Assuming unknown roles like "moderator"

4. You wrote this message list for an AI chat:

[{"role": "system", "content": "Be concise."}, {"role": "user", "content": "Explain AI."}, {"role": "user", "content": "Tell me more."}]

Why might the AI ignore the second user message?

medium

A. Because there are two user messages without an assistant reply in between

B. Because the system role is missing

C. Because the assistant role is used twice

D. Because the user messages are empty

Solution

1. Step 1: Check message sequence rules

   AI expects alternating user and assistant messages; two user messages in a row can cause confusion.

2. Step 2: Identify the problem in the message list

   Here, two user messages come one after another without an assistant reply, so the AI may ignore the second user message.

3. Final Answer:

   Because there are two user messages without an assistant reply in between -> Option A

4. Quick Check:

   Messages alternate user-assistant-user [OK]

Hint: User and assistant messages must alternate to avoid ignored inputs [OK]

Common Mistakes:

• Thinking system role is missing
• Assuming assistant role used twice
• Believing empty messages cause ignoring

5. You want the AI to act as a friendly tutor and answer questions clearly. Which message list correctly sets this up before the user asks a question?

hard

A. [{"role": "system", "content": "You are a friendly tutor. Answer clearly."}, {"role": "user", "content": "Explain math."}]

B. [{"role": "user", "content": "Explain math."}, {"role": "system", "content": "Be friendly and clear."}]

C. [{"role": "assistant", "content": "I will be friendly."}, {"role": "user", "content": "Explain math."}]

D. [{"role": "user", "content": "Explain math."}, {"role": "assistant", "content": "I will be friendly."}]

Solution

1. Step 1: Place instructions in the system role

   Instructions for AI behavior must be in the system message before user input.

2. Step 2: Check message order and roles

   [{"role": "system", "content": "You are a friendly tutor. Answer clearly."}, {"role": "user", "content": "Explain math."}] correctly puts the system message first with instructions, then the user question.

3. Final Answer:

   [{"role": "system", "content": "You are a friendly tutor. Answer clearly."}, {"role": "user", "content": "Explain math."}] -> Option A

4. Quick Check:

   System message first with instructions [OK]

Hint: Put AI instructions in system role before user messages [OK]

Common Mistakes:

• Putting system message after user input
• Using assistant role for instructions
• Starting with user message without system context