Skip to Main Content

AI Literacy

Large Language Models (LLMs)

Website: https://copilot.microsoft.com/

Uses: generates text, code, and images using ChatGPT and DALL-E. Includes links to some web resources.

Licensing: Licensed by TXST

Access: Copilot is still in its pre-adoption phases. Information about MS Copilot chat is relevant for all faculty and staff members. The information related to MS 365 Copilot is only pertinent to advanced Copilot license holders at this time. Log in with your TXST Microsoft 365 account (@txstate.edu) and then your NetID to access the TXST licensed version of CoPilot. 

Company: Microsoft

Cost/Upgade Vesion: Free for TXST faculty and staff

User Privacy:  When using CoPilot licensed through TXST, your prompts and responses are not retained by Microsoft or used to train AI models, and your information is encrypted. It is not currently approved for use with confidential university data (e.g., FERPA, HIPAA, PCI, IRB).

Additional information: see the TXST Co-Pilot webpage IT and the TXST AI HUB

Learn: See the below help articles for step-by-step instructions on how to use Microsoft Copilot.

Copilot website resources:

What is Perplexity?

Perplexity is a tool created to help streamline the research process. When given a prompt perplexity will use AI Technology to search the internet for real time information to analyze and summarize into a concise natural language text. By doing this, Perplexity helps users find relevant scholarly articles, generate insights, and navigate complex research topics with ease. 

Its core features include a powerful search engine that retrieves academic literature and a context-aware citation tool that clarifies the impact and relevance of sources. Perplexity also provides a list of sources it has used to create its response 

Additionally, Perplexity AI offers a summarization feature that distills large volumes of information into concise, comprehensible summaries, making it easier to grasp key concepts and findings. Ideal for both initial explorations and in-depth research. 

Perplexity Deep Research

In February 2025, Perplexity added a new search mode: Deep Research.  It is based on a similar chain-of-thought based agent as other tools offered by Google's Gemini, OpenAI's Deep Research, and DeepSeek Deep Research.  For researchers, it differs from these products in two important ways:

  • First, one can access it with a free-tier account (with a limited number of searches per day).
  • Second, one can use Perplexity's "Focus" feature to prioritize academic sources (taken from Semantic Scholar and PubMed, primarily).

Searches take about five minutes, and go through a long chain of intermediate searches before an LLM integrates the results into one three-page report.  The report usually draws on text from fewer than a dozen sources, but the final output will return all the websites and documents Perplexity Deep Research discovered along the way, which can sometimes be the most relevant to the user's needs.

The report will be broken down into numerous sections and subsections, and clicking on the title of such sections and subsections will start a new Deep Research search on that particular topic.  One can also ask follow-up questions, and otherwise use it like a chatbot.

Like most such tools, one should expect the report to prioritize the "consensus" rather than innovative, possibly untested new research that might overturn the consensus.  These reports are probably most useful at the outset of researching a particular topic, and discovering seed papers to read and discover subsequent work from.

Resources

Website: https://gemini.google.com/

Uses: Generates text, code and images. Includes links to some web sources.

Licensing: Proprietary; licensed by TXST

Access:  Google Gemini website and through Google app integrations. (Formerly known as Bard.)

Company: Google

Privacy:  Gemini Apps Privacy Hub; Uses location, past conversation data to provide responses. Will save and share data with other Google products if linked. 

What is NotebookLM?

NotebookLM is a tool from Google, using its Gemini engine, that allows users to create "notebooks" of text files, PDFs, websites, notes, and more, and "chat" with them to draw insight from all these sources at once. 

It uses a principle called Resource Augmented Generation, or RAG, which basically means that, instead of the chatbot trying to draw on its training data for its response to your query, it sticks as closely as possible to the source material you provide it. This dramatically cuts down on "hallucinations," but if the sources you give it are unclear, contradictory, or contrary to reality NotebookLM's replies may be as well!

Users can upload PDFs, text files, web pages, Google Docs and Sheets, YouTube videos (from which it extracts the transcript), and more. NotebookLM will extract the text and work from that; it will not update itself automatically if a website or Google Doc changes.

Files you put in a notebook stay within your Google account and are not made public or added to training data; however, as always one should avoid putting sensitive information on the internet if one can.  You can share a notebook with other Google account holders, but they cannot be made truly public.

One feature of NotebookLM that has received a lot of attention is its Deep Dive Conversation feature, where one can create an audio file that simulates two hosts discussing a topic based on your sources.  One can even have a live conversation with the "hosts."

How-Tos