Worksheet: Prompt Engineering with Chatbots
# Learning Objective
By the end of this activity, you should be able to:
distinguish between a prompt and prompt engineering
understand Zero-shot, One-shot and Few-shot prompting
understand what tokens are
identify possible AI hallucinations
improve an AI response by writing a more precise prompt.
# Instructions
Use and work with any chatbot of your likeness, such as, ChatGPT, Copilot, Claud, Gemini, Perplexity etc. Create a blogpost and write your answers in that, under the title of various activities. Do not simply copy its answers. Compare, observe, and analyse how your prompt affects the response.
Activity 1 — What is a Prompt?
A prompt is any question, instruction, statement, or command given to Chatbot.
Enter the following prompt:
What is symbolism in literature?
Now enter:
Explain symbolism in literature using examples from Shakespeare's Macbeth.
Observe
What changed between the two responses?
Question:
What does this tell you about the relationship between the specificity of a prompt and the quality/relevance of the response?
Activity 2 — Prompt Engineering
Prompt engineering means deliberately designing a prompt so that the AI produces a response suitable for your particular purpose.
Step 1: Start with a weak prompt
Enter:
Tell me about Hamlet.
Read the response.
Step 2: Engineer the prompt
Rewrite it by adding:
Role — Who should Chatbot act as?
Task — What exactly should it do?
Context — What do you need the information for?
Format — How should the answer be presented?
Level — Who is the intended reader?
Try your improved prompt:
Act as a university English Literature teacher. Explain __________ in Shakespeare's Hamlet for MA-level students. Focus on __________. Give three textual examples and present the answer under clear headings in approximately 300 words. (This is examples prompt, you may create your own prompt)
Now replace the blanks with your own requirements and enter the complete prompt into ChatGPT.
Compare
Which response was more useful? Why?
Remember:
Good prompt = Clear task + Context + Specific requirements + Desired format
Activity 3 — Zero-Shot, One-Shot & Few-Shot
These strategies differ mainly in how many examples you give to Chatbot before asking it to perform a task.
We will use literary tone as our task.
A. Zero-Shot Prompt
Give Chatbot no example.
Enter:
Identify the tone of this sentence: "The night was silent, but something seemed to be waiting beyond the window."
Chatbot's answer:
B. One-Shot Prompt
Now give ChatGPT one example before giving it a new sentence.
Enter:
Example: "The sun disappeared behind the hills, and the village slowly fell silent."
Tone: Melancholic
Now identify the tone of this sentence: "The night was silent, but something seemed to be waiting beyond the window."
Answer:
C. Few-Shot Prompt
Now provide multiple examples.
Enter:
Example 1: "The sun disappeared behind the hills, and the village slowly fell silent."
Tone: Melancholic
Example 2: "He laughed as he ran through the rain, completely unconcerned about what anyone thought."
Tone: Joyful
Example 3: "The locked door creaked open by itself, revealing nothing but darkness."
Tone: Suspenseful
Now identify the tone: "The night was silent, but something seemed to be waiting beyond the window."
Answer:
Compare
In your own words, explain the difference:
Zero-shot means ___________________________________________
One-shot means ___________________________________________
Few-shot means ___________________________________________
Activity 4 — Tokens: How Does Chatbot Read Text?
Chatbot does not process language exactly as humans do. Text is broken into smaller units called tokens.
Consider:
"I love reading Shakespeare."
Ask:
How many tokens are approximately in the sentence "I love reading Shakespeare"? Explain briefly.
Approximate number given by Chatbot: __________
Now try:
"The posthuman subject constantly negotiates memory, identity, technology, and embodiment."
Approximate number of tokens: __________
Think
Which sentence contains more tokens?
Why might longer prompts require more computational resources?
Activity 5 — Can Chatbots Be Wrong?
One of the most important limitations of LLMs is hallucination.
A hallucination occurs when an AI produces information that sounds convincing but is false, unsupported, or invented.
Step 1
Enter:
Give me five scholarly articles about the relationship between Shakespeare's Hamlet and artificial intelligence. Include the author's name, article title, journal, year, and DOI.
Look carefully at the references.
Step 2 — Verify
Choose one citation from the response.
Search for it independently using Google Scholar, your university library, or the journal's website.
Record your finding:
Citation given by Chatbot:
Your verification and what did you discover? Was it a correct citation or not? If not then what was the problem?
The Golden Rule
Never assume that a confident-sounding AI response is automatically a factual response.
Chatbot can generate invented citations, incorrect dates, nonexistent books/articles, false quotations, and misleading information.
Therefore:
AI-generated information → Verify → Then use
Final Challenge — Improve the Prompt
Suppose a student asks a Chatbot:
Tell me about symbolism in literature.
This is a relatively broad prompt.
Rewrite it into a better academic prompt by including at least four of the following:
☐ Role
☐ Context
☐ Specific literary text
☐ Theoretical focus
☐ Length
☐ Structure/format
☐ Examples
☐ Academic level
☐ Request for reliable sources
Your improved prompt:
Why is your prompt better?
Your Reflection
Complete this sentence:
The most important thing I learned about working with (Name of the AI/Chatbot you worked with) is that...
