Scribd
Upload
21 views5 pages

AI Prompt Engineering

This document from San José State University discusses the use of AI, particularly Large Language Models (LLMs), as supplementary tools in the writing process. It emphasizes the importance of prompt engineering, providing five strategies for creating effective prompts to elicit useful responses from AI. The document also encourages students to engage with their instructors regarding AI usage policies in the classroom.

Uploaded by

Md. Saddam Hossain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views5 pages

AI Prompt Engineering

This document from San José State University discusses the use of AI, particularly Large Language Models (LLMs), as supplementary tools in the writing process. It emphasizes the importance of prompt engineering, providing five strategies for creating effective prompts to elicit useful responses from AI. The document also encourages students to engage with their instructors regarding AI usage policies in the classroom.

Uploaded by

Md. Saddam Hossain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

San José State University Writing Center

www.sjsu.edu/writingcenter
Written by Michaela Ota

AI Prompt Engineering

AI platforms can be useful when used as supplementary tools during the writing process. This
handout will cover when and how AI can be incorporated into different stages of the writing
process, from planning to drafting, with a focus on strategies for engineering prompts and getting
effective results.

Note that AI should never be used to generate writing from scratch; that's not what learning
writing skills is about. It is never acceptable to have an AI chatbot write your papers for you.
Instead, we will look at ways that AI can help you enhance your writing process, while making
sure that you're still doing the bulk of the work.

While this handout can help you learn more about applications of AI in writing, it's important to
remember that faculty will have different policies about the use of AI in the classroom. If you
are ever in doubt about acceptable applications of AI tools in a specific class, the best thing
to do is ask your instructor.

What is AI?
Broadly defined, Artificial Intelligence (AI) is a branch of computer science research focused on
technology that enables machines to utilize learning, intelligence, and environmental context.
Some examples of current AI applications are provided below, but be aware that there are many
more, and they can (and will) change over time.

Examples of AI Applications
● Web Search Engines
○ Google, Yahoo, DuckDuckGo
● Algorithms
○ YouTube, Instagram, TikTok
● Large Language Models (LLMs)
○ ChatGPT, ClaudeAI, Gemini

Large Language Models (LLMs)


This handout will focus on the Large Language Model (LLM) application of AI. LLMs are
Natural Language Processing (NLP) models that are trained on large amounts of text data and
complete tasks like language generation. ChatGPT was one of the earliest LLMs available
widely for public usage.

AI Prompt Engineering, Fall 2024. 1 of 5


What is Prompt Engineering?
Prompt engineering involves designing effective prompts to elicit desired responses from AI.

In this context, a prompt is the text that we input into language-generating AI platforms, like
ChatGPT, to generate responses that are relevant, coherent, informational, and useful. The more
that you engage repeatedly with the AI—by doing things like submitting follow-up prompts—the
more effective your responses will be.

Five Strategies for Effective Prompt Engineering

1. Be Clear and Specific

It's essential to make your prompts as clear and specific as possible. Ambiguous or vague
prompts can lead to irrelevant or confusing AI-generated responses. Ensure that your
prompts explicitly state the desired outcome or response format.

2. Provide Contextual Information

Providing context in your prompts is crucial for the generation of accurate responses. By
including relevant background information or defining specific terms, you can guide the
AI model toward a more informed and appropriate response.

3. Limit Response Length

When designing a prompt, consider specifying the desired length of the response. For
instance, if you require a brief, concise answer, you may include a phrase like “in one
sentence” or “summarize in 100 words.” This step ensures that the AI model generates
responses that meet your expectations.

4. Iterate and Refine

The process of prompt engineering often involves trial and error. Test your prompts with
the AI system and observe the responses. If the generated output is not satisfactory, refine
your prompt by making it more specific, adding context, or adjusting the response length.
You will likely have to iterate on your initial prompts in the AI system.

5. Chain Your Prompts

Sometimes a single prompt may not be enough to obtain the desired response. In such
cases, you can use “prompt chaining,” which involves breaking down a complex prompt
into simpler, interconnected prompts. This strategy helps guide the AI model step-by-step
toward the desired outcome.

AI Prompt Engineering, Fall 2024. 2 of 5


Example of Prompt Engineering (with ChatGPT)

1. The Beginning: We prompt ChatGPT to “list three primary causes of climate change.”

2. The Follow-Up: We follow-up and utilize the information from the initial response to
gain more in-depth and nuanced information on the subject by asking ChatGPT to
“discuss the impact of each cause on global temperatures and weather patterns.”

3. The Result: The result is a detailed and lengthy explanation on how each of the three
causes of climate change impacts global temperatures and weather patterns (shown on the
next pages). This information can be used to help you outline a paper on this topic by
helping organize and break down your thought process.

AI Prompt Engineering, Fall 2024. 3 of 5


AI Prompt Engineering, Fall 2024. 4 of 5
Activity: Practice Prompt Engineering
Now it’s your turn to practice prompt engineering. Consider the strategies listed above, the
provided example, and the activity steps below while you write and submit your own prompts
into a language-generating AI platform (like ChatGPT).

1. Consider the topic: Think of a topic that you’re interested in knowing more about. It
could be something that you’re actively working on or just something that you want to
learn more about.

2. Formulate a question: Once you’ve determined what subject matter you’re interested in
exploring, choose a specific question that you want to ask. Submit that question into the
language-generating AI platform of your choice.

3. Submit a follow-up prompt: Utilize the information provided in the AI’s response to
your first question to write and submit a follow-up question in order to obtain more
detailed and specific information.

References
“The Art of Prompt Engineering Simplified | Explained in 10 mins | Prompt Examples |

ChatGPT 4 | AI.” YouTube, uploaded by AI Insights & Innovations, 26 April 2023,

https://www.youtube.com/watch?v=PJxHKny4qrw.

AI Prompt Engineering, Fall 2024. 5 of 5

You might also like