What about AI? - Ranger College Library at Ranger College

June 10, 2025

Ok, I have settled on Consensus as the library AI. Pending discovery of something better, this is the tool I am going to use when I create examples for this site. At the pace of change on the topic, I imagine there will be something better every week.

Today’s real topic is prompting. This will probably be the topic of several posts. As I learn more about it, it seems that prompting is the most important part of the AI process. If you want to get everything you can out of AI, the prompt is what matters.

First, let me recommend a video called Generative AI in a Nutshell. It is 18 minutes long, but well worth your time. It has a lot of information, but I think the most important part is the way it explains how the right prompt can make all the difference in your results.

This screenshot from the video helps a lot. Notice the last ‘good’ prompt. You can tell AI to ask you clarifying questions. This is probably the single most important thing to know about AI. You can ask AI how to frame your questions to get the best results.

Recent Posts

Prompt engineering: Few-shot prompting

Few-shot prompting is a technique in artificial intelligence where a model is given a few examples of a task to improve its performance on similar tasks. This can be used after a zero-shot prompt to increase specificity about your topic or generated right from the beginning.For example:“Regular exercise improves cardiovascular health by strengthening the heart and increasing circulation. It also enhances mental well-being by reducing stress and boosting mood through endorphin release. Now, describe another benefit of regular exercise.”It is also an excellent way to find points of comparison or contrast in two or more items.Enter the prompt statement and include the items to be analyzed in quotation marks.Classify the sentiment of the third movie review. Use the information from the first two examples: Review: "This movie was a waste of time." Sentiment: NegativeReview: "I couldn't stop laughing throughout the film!" Sentiment: PositiveReview: "The special effects were amazing, but the plot was confusing. "Sentiment:```?WARNING: This example does not work well with Consensus which looks at journal articles to find real data. It did work well with Google Gemini, a more generic tool, which provided this response:The sentiment of the third movie review is: Neutral.Another example is:Write a funny limerick about a boy named Sue This contains two ‘shots’ of information, boy and Sue.A young boy named Sue, quite unique, Had a name that made everyone shriek. He'd say with a grin, "It's not where I've been, But the stories I've got, so to speak!"You can try again, over and over until you get something you likeA tough boy named Sue, quite perplexed, When folks thought his gender was vexed. He'd just spit on the ground, "That's a man's name, profound! Don't you know Johnny Cash? Read the text!"...

Prompt engineering: Zero-shot prompting

I am going to spend a lot of time in this blog discussing prompt engineering. The prompt is probably the most important aspect of using generative AI. If you are not asking the right question, you will not get an effective answer. There are three categories of prompt engineering. We are going to take a closer look at each over the next three weeks. Your goal is to create the most effective prompt you can.1. Zero-shot prompting2. Few-shot prompting3. Chain-of-thought promptingFirst, Zero-shot prompting. This is your most basic form of prompting and the style you are probably used to.Why is…Summarize…Create an outline for…These kinds of prompts create responses based on existing knowledge. This is useful when you are looking for general information on a topic. Very often, as students trying to avoid plagiarism issues, this will be the type of prompt you are looking for....

The iterative nature of AI

The next big thing I want to get out here is the iterative nature of AI. You have probably heard the word in relation to AI before, but have you ever contemplated what it really means? Ask AI something. Rephrase the prompt. Follow up the prompt. Keep tightening the focus until you are getting the results you are looking for. Here is an example.What kind of vision insurance should I get? This is a pretty generic question but it gave a really good overview of types of insurance and why different types of people would need each. But what I really wanted to know was what kind I needed. Me. Personally. I added a follow-up.What kind of insurance would be good for macular degeneration?In addition to some specific features to look for, it provided this handy table. Its bottom line was that this person would not need vision insurance at all. It is a health insurance issue.It can go deeper. What kind of insurance would be good for a person with macular degeneration and posterior vitreous detachment?Here is even more detailed information, including links to studies about various types of medications that can be used in persons with both conditions. It is still in the realm of health insurance rather than vision insurance. “These studies suggest insurance policies for managing posterior vitreous detachment and macular degeneration should cover regular specialist visits, advanced imaging like OCT, and ongoing treatments such as anti-VEGF injections, as these are key for monitoring and treating both conditions." Keep asking until you are getting the results that you need. Don't forget you can ask the AI to interrogate you or ask it what would be good prompt. We will get examples of those next time....

Generative AI in a Nutshell

June 10, 2025Ok, I have settled on Consensus as the library AI. Pending discovery of something better, this is the tool I am going to use when I create examples for this site. At the pace of change on the topic, I imagine there will be something better every week.Today’s real topic is prompting. This will probably be the topic of several posts. As I learn more about it, it seems that prompting is the most important part of the AI process. If you want to get everything you can out of AI, the prompt is what matters.First, let me recommend a video called Generative AI in a Nutshell. It is 18 minutes long, but well worth your time. It has a lot of information, but I think the most important part is the way it explains how the right prompt can make all the difference in your results.This screenshot from the video helps a lot. Notice the last ‘good’ prompt. You can tell AI to ask you clarifying questions. This is probably the single most important thing to know about AI. You can ask AI how to frame your questions to get the best results....

Generative AI in a Nutshell

Leave a comment