AI Resources

RWU IT offers a list of AI resources, tools, and training, including courses, guides, and product trackers related to AI use in higher education.

Note:  Although some vendors claim they won't save individual data as part of their learning model, it is generally considered safest and best practice to avoid inputting sensitive or protected data into generative AI platforms.  For a description of sensitive or protected data, visit RWU's Data Storage Policy.  The Acceptable Use Policy (AUP) is another good resource for information about data confidentiality.

AI Tools

There are many AI tools out there, with more coming on the market all the time.  Choosing an AI tool can be influenced by a number of factors including, but not limited to, ease of use, accuracy, data security, scalability, and cost.

 The Generative AI Product Tracker lists generative AI products that are either marketed specifically towards postsecondary faculty or students or appear to be actively in use by postsecondary faculty or students for teaching, learning, or research activities. The Tracker is a living document, which is updated regularly as new products enter the market or new information about existing products becomes available.

Training About AI

:  LinkedIn Learning has a wide variety of courses on AI, ranging from beginner to advanced.  The RWU community has access to all of these resources.

:  The Elements of AI is a series of free online courses created by MinnaLearn and the University of Helsinki.

AI Resources

:  This LibGuide from the ÐÓ°ÉÊÓƵ University Library includes a range of information for faculty and students, including a guide to citing AI in academic work.

:  The Microsoft Education AI Toolkit is intended  to equip educational leaders at various stages of their AI journey with knowledge, strategies, and tips to confidently advance their use of generative AI technologies. 

How to Write Effective Prompts 

Prompt engineering is the process of designing and optimizing prompts to guide artificial intelligence (AI) models to produce desired outputs.  Writing an effective prompt for AI models involves being clear, concise, and specific about what you're asking for. A well-crafted prompt helps the model understand your intent and deliver more relevant and accurate responses. Here are some tips on how to write a good prompt:

Be Clear and Specific

The more precise you are, the better the response will be. If you have a specific question, ask it directly. For example:

Vague: "Tell me about space."

Specific: "Can you explain how black holes form and what happens inside them?"

Provide Context (When Needed)

If your question requires background information or has a specific context, include that in your prompt. This will help the AI model tailor its response.

Without Context: "What's the best way to improve communication?"

With Context: "In a corporate setting, what are some strategies to improve team communication and reduce misunderstandings?"

Use Open-Ended Questions for Exploration

If you want a detailed or creative answer, open-ended questions work best. These allow the model to elaborate and explore multiple angles.

Open-Ended: "What are some innovative ways to use AI in education?"

Closed-Ended: "Is AI used in education?"

Set Expectations for the Type of Response 

If you need a specific kind of response—such as a list, summary, or explanation—state that upfront. This guides the model to format its answer accordingly.

Example: "Can you give me a list of the top five benefits of exercise?"

Example: "Please summarize the key points of this article in three sentences."

Be Concise but Provide Enough Detail

Try to balance brevity with enough detail. Too little information might lead to a general or off-target response, while too much can overwhelm the model.

Too Little: "How do I bake a cake?"

More Effective: "What are the steps to bake a simple chocolate cake from scratch?"

Ask for Clarification If Necessary 

If you want a deeper dive into a topic or further explanation, feel free to ask for clarification.

Example: "Can you explain that concept in simpler terms?" or "Can you give me more examples?"

Use "What," "How," and "Why" for Insightful Responses

Starting your prompt with questions like "What," "How," or "Why" can encourage the model to provide detailed explanations and insights.

Example: "How does photosynthesis work?" or "Why is the sky blue?"

Be Aware of Ambiguity

If your question could have multiple meanings or interpretations, try to clarify your intent to avoid confusion.

Ambiguous: "Tell me about the event."

Clarified: "Can you tell me about the event where humans first landed on the Moon?"

Avoid Overly Complex or Unclear Requests 

While AI models are powerful, it's best to avoid asking extremely complex, multi-faceted questions all at once, as it may lead to an incomplete or disorganized answer.

Complex: "Explain the history, politics, and economics of Europe."

Simplified: "Can you give me a brief history of Europe?" followed by specific questions about politics or economics as needed.

Example of an Effective Prompt:

Let's say you want to learn about the environmental impact of plastic waste:

Ineffective: "Tell me about plastic waste."

Effective: "What are the environmental impacts of plastic waste on oceans, and what solutions are being developed to reduce this problem?"

 

Ethical Considerations

Ethical considerations in the development and usage of AI models include:

  • Transparency:  Disclosure of AI usage
  • Fairness:  Being aware of and attempting to reduce the impact of biases in AI models
  • Data Privacy:  Protection of user privacy and data security
  • Accountability:  Establishing clear lines of responsibility

For more information about ethics in AI use and development, visit: