Accessibility Applications

Many of Pacific’s approved AI tools have features that can enhance the accessibility of educational resources for our students. Some of these suggestions answer particular accommodations students may have, but many of them can also make educational materials more accessible across the board by offering multiple modalities and means of engaging to suit particular student needs and abilities.

The upside of AI is that it provides an embarrassment-free resource for study support that is available without limits, from any location, 24 hours a day. If students are properly trained and supported, they will have access to a range of powerful study support tools with their Pacific login.

The danger is that a gap in access or training could itself exacerbate inequalities, and that AI by its nature reflects the most common or “average” data, potentially underrepresenting marginalized groups. To address these concerns, you can support students as they learn how to use the tools provided by Pacific, and educate them about the limitations and biases of AI.

This guide is organized in terms of the features of each tool, followed by some exploration of effective usage.

Table of Contents
Class Recordings, Summaries and Transcripts
Creating Accessible Materials
Study Tutoring
Tools
Prompting for Learning
Promoting Beneficial Usage
Limitations

For more on the features of each tool and how to enable them, see AI Resources.

Class Recordings, Summaries and Transcripts

It can be beneficial to provide recordings of your classes to students for easy revision and access, and if you do this via Zoom, you will have access to additional resources provided by Zoom AI companion. While a student may sometimes have an accommodation for producing their own recordings, it can be desirable to produce these recordings yourself for three reasons: one, because the in-room audio-visual equipment is often well set up to capture your voice and slides, two, because you would then retain control of the muting and camera direction, and have the ability to edit the video if needed, to promote the privacy of all students, and three, because then you can provide those recordings to all students for revision.

Some students have concerns about being recorded. Where an accommodation is in place, we have an obligation to fulfil it; in many cases, the recording can be focused on you and your slides and voice, and student contributions or sensitive discussions excluded by pausing or muting. Often, an educator can have a conversation with a student about their specific concerns and reach an agreement about what will and will not be recorded and how it will be shared.

Most of our classrooms have cameras and microphones installed. These are either mounted on the ceiling, or are wired on the podium. Often, the most reliable option is to run Zoom from the podium computer, since cameras and microphones almost always have a connection to the podium computer. (They can sometimes also be routed to laptops, but this is not always the case.) For more detailed information and instructions for all of the different podium types at Pacific, see Podium Setup Instructions.

Zoom is capable of producing full transcripts of classes, live and recorded. This may help any student who could benefit from a written version of the class content, to access content in a different modality, to easily revise materials, and to search through transcripts to see where a particular topic is covered. This can be enabled in a side panel for live meetings, and will be available whenever you access a cloud recording from the Zoom Recordings and Transcripts tab.

Zoom summaries can similarly offer all students the ability to quickly recap what was covered in a class, as well as offering an easy summary of their next tasks. Once enabled, summaries can be sent to you automatically by email, accessed from the Zoom Summaries tab, or will be available whenever you access a cloud recording from the Zoom Recordings and Transcripts tab.

See Zoom AI Companion for full instructions on how to access and enable each feature.

Creating Accessible Materials

A principle of Universal Design for Learning is to offer multiple means of engagement, representation, and action and expression to craft learning experiences that anticipate diverse needs from the beginning. AI can help you to fulfil this goal by:

• Tailoring your course materials to the people you have in class, such as by creating examples that engage their interests and offering choice
• Presenting course materials in multiple formats
• Helping to suggest alternative formats for assignments that fulfil the rubric and learning outcomes

The ability to quickly reformat materials according to different requirements can allow educators to offer more options and flexibility to their students.

Educators can also ask an AI to critique their study materials from an accessibility standpoint, and suggest improvement. It may be helpful to prompt the AI to look for common issues, such as use of color and descriptive links, to write image descriptions for alt text, and to suggest other areas for improvement. An example of a prompt for this like of task is the Enhancing Accessibility prompt from AI for Education.

Study Tutoring

A wonderful thing about AI is that it provides an embarrassment-free resource for study support that is available without limits, from any location, 24 hours a day. If students are properly trained and supported, they will have access to a range of powerful study support tools with their Pacific login. This can represent a powerful tool to level the playing field for students with different backgrounds, educational histories, and access to support, as well as different preferred learning methods.

A great strength of AI-supported study is that the same material can very rapidly be presented in different formats. Students can ask for materials to be summarized in a paragraph, bullet-points, a table, or any other format that works well for them (although AI is still not especially successful at creating infographics).

An informal survey conducted at the University of Waterloo (reported at the session on Unsurfaced Educational Practices & Practical Tips in Graduate Supervision and Undergraduate Learning Skills Support at the 2025 Teaching with AI conference hosted by the University of Guelph) revealed that their students often use AI to help them to represent materials in ways that are more memorable or understandable to them. Examples were: ‘explain it like I’m 5 years old,’ mnemonics, and explanations in terms of personal interests (e.g. ‘relate this chemistry material to cats so I can remember it better.’).

Tools

If you are storing class materials in Box, the built-in Box AI can answer questions, provide concept summaries and even generate study guides based on the materials provided. This means that you can provide study materials to students in a secure folder, and with proper support with prompting, students have access to an in-application personal tutor to help them with key questions, define terms, and explain concepts, all drawing upon the material you have provided. For more information on how to find and use Box AI, see Box AI.

With proper prompting, Google Gemini can offer all students on-demand, tailored tutoring and study support in multiple modalities. Google Gemini is a very versatile tool, and this means that students may need support to develop the right prompts to get the best out of it. It is possible to simply upload study materials into the Google Gemini chat window, and ask the AI to use those as its primary source. This will often lead to more reliable outcomes and also allow students to easily check the source to confirm the interpretation offered by the AI. For instructions on how to access Gemini, see Google Gemini.

Google Gemini offers the ability to create your own ‘Gems:’ custom-built, user-created chatbots that can be set up by providing specified source materials and instructions, and saved for future use. This means that students can set up their own Gems for different purposes:

• Retrieval practice: A bot to be used for daily practice recalling a list of medications and their contraindications
• Conceptual tester: A bot that will prompt the user to write their own definitions of key terms, and give them feedback on the answers based on pre-provided documents
• Exam questions: Working from specified materials, a bot that can provide questions according to specifications and assess the answers.

It could be beneficial in some cases to work with individual students to set up chatbots to help them with specific skills. You can read more about applications in Student-Made Bots: An Educator’s Toolkit from CUNY Academic Works. For instructions on how to set up a new Gem, see Google Gemini/Gems.

NotebookLM, from Google, is a virtual research assistant that can work across up to 300 documents, and provide study materials in multiple modalities. It provides a structured interface that is user-friendly and cues study-apt interactions. NotebookLM can produce study guides, concept summaries, and even an audio ‘podcast,’ which can be very beneficial for students who prefer working with audio content. An experimental feature even allows a user to interact with the audio summary in real time, by speaking aloud. For instructions on how to access NotebookLM, see NotebookLM.

Prompting for learning

The key to working effectively with AI is to write a prompt for the AI that sets up the behaviors you are looking for.

For example, in a study-tutoring setting, it can be beneficial to set up the prompt such that the bot proceeds by Socratic questioning rather than generating answers itself. As students experiment with prompting chatbots for their own learning, they may discover things about their own learning preferences (for example, that they understand things better with lots of examples, or a table). To read more about prompt structures, see Introduction to Prompting.

It is also very important to go in with an expectation that you will need to iterate. If you do not get useful results the first time, consider why. Adjust your prompt, try again, and observe the results. An AI will often not be employing all of the contextual assumptions being used by its human interlocutor. A human questioner will often find that their original prompt takes an AI in a slightly different direction than they were hoping, and the process of refining and adjusting prompts can itself clarify a student’s understanding of the material.

It is possible to ask a chatbot like Gemini or Box AI to work with specific provided materials, and to provide full referencing for all of the claims it makes. This can be beneficial for promoting reliability.

Below are some specific ideas for tasks that an AI can fulfil.

Conceptual tutoring

An AI can be prompted to ask the student questions about their current knowledge, identify gaps, provide explanations or further questioning to address them.

• Explain the process of x like I’m 15 years old. (Then ask follow-up questions).
• I’m confused about the difference between x and y. Can you provide examples of each and explain why they aren’t the same?
• Here is my summary of x. What key points am I missing or misunderstanding?
• Give me three different examples to help me to understand this concept.

Students can drop class documents into the Google Gemini text field, and use this as source material.

Practice questions

Chatbots can be used to generate case studies or practice questions from specific course content, give students feedback on their answers, and provide daily challenges to memorize content.

• Write me a set of exam questions to test my knowledge of . Have me answer them one by one, and give feedback on my answers.
• Help me to memorize this list of medications with a daily challenge: When I prompt you to, show me the list with one missing.
• Write me a case study following this example, and help me to role-play my interaction with the patient. Critique my questions and responses.

Assignment critique

A student can use an AI tool to compare an assignment against the description and rubric, and suggest areas for improvement. Specific tasks might include:

• Compare this assignment against the rubric. Write bullet-points telling me how well it fulfils each item on the rubric.
• Read a paragraph, provide feedback on clarity, and offer specific suggestions for improvement.
• Identify the main argument in a paragraph. Is it well-supported? Suggest ways to strengthen the support.
• Check a paragraph for passive voice and suggest active voice alternatives.
• Identify strengths and weaknesses of the writing style in a sample. Exemplify alternative styles.

Idea brainstorming

A chatbot can work from an assignment description, ask student about their interests and existing knowledge, help draft and critique ideas.

• Help me to come up with ideas for an upcoming project, based on my knowledge and interests.
• Help me to choose between these three ideas by asking me questions about the assignment and how well these ideas fulfil it.
• Help me to choose between some possible ideas by showing me their strengths and weaknesses, and anticipate counterarguments.
• I have chosen a topic. Show me three different angles I might want to cover in my discussion.
• I am stuck writing this essay. Suggest three possible directions to take in the next paragraph.

Promoting beneficial use

Many students are looking for guidance on which uses of AI are acceptable, and are hesitant to use it when they are unsure. By providing guidance on how to use AI in ways that are accepted and beneficial, you can provide students with a powerful resource that they can use in their independent learning–and one that can help to mitigate many differences in educational background and preferred learning methods. It could be beneficial in some cases to work with individual students to set up chatbots to help them with specific skills.

It is also important to provide guidance on which uses will not be beneficial or accepted. See General Considerations/Responsible use and our AI Course Policy Guidance page.

Limitations

Human educators often add significant interpretation, commentary and emphasis as they expand on written materials, conveyed by anything from sketches to speech to gesture; they also tend to pay attention to the reactions of their students, whether they look confused or confident, and which parts of the material elicit reactions. A human educator will often respond to those reactions and provide more guidance as needed; they will also often prompt students to test their understanding by modelling techniques covered or summarizing ideas.

An AI simply asked a question about a topic is likely to quickly summarize factual information, and give an answer. However, prompting an AI to behave like a teacher and ask questions can make for a more effective learning experience. Students hoping to work effectively with an AI as a tutor will need to consider how to craft their prompts and take an active role in feeding back their understanding of the material. Students can ask the AI to pose them follow-up questions to test their understanding, and consider whether explanations in different registers could be helpful (metaphorical explanations; step-by-step; commentary on the culture of a discipline or underlying assumptions; and so forth). Even so, it is important to be conscious that an AI will not provide everything that a human educator can.

It is important to caution students about the limitations of AI tools. AIs are known to manifest bias and to give outright incorrect information. For any application you discuss, spend some time considering where inaccuracy and bias could manifest, and what steps students can take to double-check or critique answers. If you do not see a good way to mitigate potential inaccuracies, do not recommend that application.