AI Tools & Tips
This page introduces several commonly used AI tools, as well as information on writing a helpful prompt (prompt engineering), and some handy tips and resources for how to use tools effectively.
Before using an AI tool, be aware that it isn't always going to be a time-saver. Tools and their output must be verified for quality and accuracy, which means you'll need to do some research and double-check the content it has generated for you. Additionally, it can take some time to hone your prompt engineering skills so you aren't going back and forth with an AI tool for a while just to get the content you really want. AI tools are also not substitutes for your actual abilities -- and if you don't use them, you'll lose them.
If you're looking for individualized assistance beyond the limitations of a screen, come to the library! Librarians are available to provide all kinds of research help and guidance for every step of the process, from choosing a search strategy to finding the right resources. Using the library ensures you're getting real, high quality sources for your assignments, not hallucinations. Plus, the librarians are here to work side-by-side with you in a way that enhances your critical thinking skills and creativity. Stop in or contact a librarian.
Generative AI Tools
Below are some commonly used AI tools, what they are, and what you can do with them. While some of the general purpose tools might be familiar to you already, research-based tools may provide additional assistance with specific aspects of the research process. But please be aware, you must get permission from your instructor before using any AI tool on any assignments. Also, this is a very basic overview of these tools -- make sure to do your own research into a particular AI tool before using it so you're fully informed.
| Name | Cost | Description | Uses/Features |
|---|---|---|---|
| ChatGPT | Free + paid tiers (info here) | Large Language Model (LLM) -powered chat | General purpose; generates text, code, and images. |
| Microsoft Copilot | Free + paid tiers (info here & here) | LLM-powered chat & integration for Microsoft 365 apps (Teams, Word, Outlook, OneDrive, etc.) | General purpose; conversational search, summarize answers from web, ask follow up questions, use as a “creative tool” to generate content; text to image generation. |
| Google Gemini | Free + paid tier (Gemini Advanced) | AI "assistant." Three multimodal models: Pro, Ultra, and Nano (latter for mobile phones). | General purpose/free-flowing voice conversation; help with writing, planning, learning, generating images, and more; connects to multiple Google apps (Maps, etc.). |
| DeepSeek | Free | LLM-powered chat. AI "assistant" available in app version. | General purpose; specializes in reasoning capabilities like solving math problems, tackling coding challenges, handling logical reasoning tasks. |
| Claude | Free + paid tiers (info here) | AI "assistant." LLM-powered chat. Additional AI models available. | General purpose; complex reasoning, creativity, dialogue, coding, content creation, summary & analysis of text and data. |
| Semantic Scholar | Free | AI-driven search & discovery tools | Research; summary & analysis of journal articles, create individual libraries and get informed recommendations for articles, connect to open access academic resources. |
| Deep Research | Available to OpenAI Pro users ($200/month) | Research "agent" conducts multi-step research on the internet for complex tasks | Research; "find, analyze, and synthesize hundreds of online sources to create a comprehensive report at the level of a research analyst...leverages reasoning to search, interpret, and analyze massive amounts of text, images, and PDFs on the internet, pivoting as needed in reaction to information it encounters." |
| Elicit | Free | Research "assistant" using LLMs to automate literature reviews | Research; search with semantic similarity (not keywords), generate custom summaries, auto-search for flaws & assess reliability of sources. Elicit only shows papers/articles that actually exist and makes it easier than other AI tools to verify generated content against the original source. |
Curious about other tools available to you? Check out the More AI Tools box to the right.
Want to use GenAI? Ask yourself...
When permitted to use GenAI Ask, by Helena Marvin (adapted from Aleksandr Tiulkanov) is licensed under a Creative Commons Attribution 4.0 International License.
Prompt Engineering Models
Designed by Sarah Hartman-Caverly, the PROMPT Design Framework provides a handy acronym you can use to create a better, more helpful prompt.
- Persona - assign a role
- Requirements - define parameters for output
- Organization - describe the structure of the output
- Medium - describe the format of the output
- Purpose - identify the rhetorical purpose and intended audience
- Tone - specify the tone of output (ex: academic)
This is just one example of a prompt engineering model you can use. Others can be found via web search for "prompt engineering" + "techniques," "models," or "examples."
More AI Tools
-
Generative AI Product TrackerThe 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 faculty or students for teaching, learning, or research activities. The Tracker is updated regularly as new products enter the market or new information about existing products becomes available. Provides descriptions, key features, pros, cons, limitations, and updates about AI tools.
Chatbot Arena
-
Chatbot ArenaAn AI testing ground that helps users and developers evaluate, improve, and probe the strengths and weaknesses of different AI models. Users input prompts and watch as the models compete, providing answers in real time.
Writing Prompts (Prompt Engineering)
When it comes to AI, a prompt is the set of instructions you give to an AI tool in order for it to do what you want. Prompts are generally given in natural language (like you'd use talking to a friend) instead of in keywords (like search engines) or in computer language (like code). Prompt engineering can be tricky sometimes because it may require you to try many different things in order to get the best possible results or answers. Below are a few tips to keep in mind when you're designing your own prompts:
- "Temperature" is a parameter that impacts how creative or precise Gen AI output is. Some chatbots make it easy to choose the temperature and give you options right up front. For example, Microsoft CoPilot has buttons near the text box for "more creative," "more balanced," and "more precise." If you aren't sure how to control the temperature in the chatbot you are using, just ask it.
- Iteration is important. Even with a well engineered prompt, you will probably have to ask the chatbot to make refinements. Different chatbots have different limits. You may go back and forth 30 times in one conversation.
- It is helpful to feed chatbots examples to get what you need. For example, if you are writing a letter of recommendation for someone for a fellowship, you may want to upload the applicant's letter of interest and provide a description of the fellowship as part of your prompt. Keep privacy concerns in mind if you choose to do this.
- Consider using "in the style of..." as part of your prompt. For example, you may ask it to write a poem about your topic in the style of Emily Dickinson or create an image of your topic in the style of Edward Hopper.
- Remember that Gen AI is designed to be plausible, not credible. Make sure to check the information it provides in reputable sources.
Tips from University of Texas Libraries Artificial Intelligence (AI) LibGuide, licensed under a Creative Commons Attribution-NonCommercial 4.0 Generic License.
Prompt Engineering Tutorial
-
Google's 9 Hour AI Prompt Engineering Course In 20 MinutesIf you don't have time (or money!) to take Google's prompt engineering course, watch this video that condenses it in 20 minutses.