How do AI Prompts Differ from Search Engines?

• Uses complete sentences and natural language for AI prompts rather than relying on keywords
• Provides context such as describing the audience for the answer
• Views the prompts as conversations and continually ask for the information you need

Using AI and Library Databases to find Articles

Student research question:

• "Why does the satisfaction of buying a luxury product die down once we own it?"
• None of the keywords in the students' question yielded relevant articles

Copilot's Response when asked about relevant keywords for this topic:

When searching for scholarly articles on why satisfaction decreases after purchasing luxury products, you might use the following keywords:

• "hedonic adaption luxury goods"
• "consumer satisfaction luxury products"
• "Post-purchase dissonance luxury"

Searching an EBSCO database with the term "hedonic adaptation" produced several useful articles.

The CLEAR framework was developed to introduce students to prompt engineering in a concise and user-friendly way, while also nurturing necessary critical thinking skills for the AI era. (L. Lo, 2023) Below are key examples from his work.

Concise - emphasizes brevity & clarity in prompts

• Removes unnecessary information, enhances relevance and precision of responses
• Effective prompts are specific & targeted toward desired outcome

Example: Use "identify factors behind China's recent economic growth" instead of "Please provide me with an extensive discussion on the factors that contributed to the economic growth of China during the last few decades."

Logical - structured & coherent prompts

• use logical flow and order of ideas within a prompt
• allows AI to better understand the context and relationship between various concepts - results in more accurate outputs

Example: A logically structured prompt could be, "Describe the steps in the scientific method, starting with forming a hypothesis and ending with drawing conclusions."

Explicit - clear output specifications

• Clearly tells the AI what kind of response you want. Include details like format, content, or scope of the answer
• Being specific helps avoid off-topic replies, so include exactly what you need and how you want it presented.

Example: Instead of, "Tell me about the French Revolution," an explicit prompt would be, "Provide a concise overview of the French Revolution, emphasizing its causes, major events, and consequences."

Adaptive - flexibility and customization in prompts

• Adaptive prompts are all about flexibility. Try different wordings, styles, roles to find the right response
• Tailor your prompts to fit the task and don't be afraid to experiment based on how the AI responds

Example: If asking, "What are some ways to conserve water?" leads to generic responses, try a more targeted and adaptive prompt like, "List household practices for conserving water and their potential impact."

Reflective - continuous evaluation & improvement of prompts

• Reflective prompts help you improve by reviewing how the AI responds.
• Take time to assess output, gather feedback, and adjust prompts based on what works and what doesn't.

Examples: After acquiring AI generated list for effective time management, evaluate the relevance and applicability of each strategy. Consider the target audience needs and use this information to tailor future prompts.

RAFT

Role: Define the persona or role the AI should assume.

Audience: Specify who the content is intended for.

Format: Indicate the desired format of the output (e.g., essay, list, email).

Topic: Clearly state the subject matter or topic.

Example

Role - “Act as a professional career coach…”

Audience - “…speaking to recent college graduates…”

Format - “…in the form of a bullet-point checklist…”

Topic - “…about preparing for job interviews.”

1. When you want to change the subject, start a new chat.

2. It will remember what you've said in the course of a conversation, so you don't have to repeat everything again. Just continue like it's part of the same conversation.

Memory across conversations is optional. As of March 2025, there is a new feature in ChatGPT where you can let it reference previous conversations. If you want to activate this feature click on your name, then Settings, Personalization. Look for the button called "reference chat history" and turn it on. (Turn on "reference saved memories" first, to see the button.)

3. Don't ask ChatGPT for a list of sources. It will often make them up. Instead use library search, library databases, or Google Scholar. It can search the web now (as of mid 2025), but even with that feature activated, some of the sources may not exist.
See I can't find the citations that ChatGPT gave me. What should I do?

4. Choose an output format. In addition to paragraphs it can give you a table, a bulleted list, ascii art, multiple choice quiz questions, emojis, computer code, and more.

5. In ChatGPT you can see a history of your conversations. You can go back to a previous conversation and continue it. If you like, in the settings you can delete your history and turn off the saving of future history. You can also export your history and save it on your own computer.

6. Remember, don't enter any personal, private data in ChatGPT, because OpenAI may use your input to help improve the model. The free version is a research experiment. If you don't want your data used to help improve ChatGPT, you can turn it off in the settings. Go to your name, then Settings, then Data Controls and turn off, "Improve the model for everyone."