Author: Celena Kusch

How Blackboard’s AVA Supports Learning Without Replacing You

We’ve all done it. We know the answer is in the user guide or instruction manual, but we don’t want to skim the whole document. Students feel the same way about the course syllabus. They know the answer is in the syllabus, but they don’t know where it is or what to look for.

Blackboard’s AI Virtual Assistant (AVA) is designed to provide just-in-time automated answers about your course and syllabus information, so you don’t have to. You write your syllabus and course instructions into your Blackboard course, and AVA looks up the answers to students’ logistical questions based on your materials.

What Is AVA?

Blackboard’s AVA is a built-in AI agent designed to work only within the closed system of your Blackboard course. It answers objective questions posed in natural language by referring students to specific content you have added to your course. It does not share the information outside your course to train AI models, and it does not search beyond your content to make up answers that sound right.

AVA acts like a self-writing FAQ that students can access anytime, any place.

How Do Students Use AVA?

If you opt to enable AVA in your course, students access AVA when they send you a message through Blackboard. After they click Send on a new message or Reply to an existing message thread, AVA introduces herself.

When students ask about due dates, course policies, assignment instructions, and other objective questions, AVA provides answers and direct links to the source of your course information. The complete record of this interaction is saved for your review within the Message thread in your Blackboard course.

For example, a student could ask if any assignments are due tomorrow. Or they could ask for a list of assignment due dates. AVA searches your assignment due dates and compiles a list of course links.

AVA will intuit some answers, but only if the link to course materials is very clear. For instance, I asked whether Respondus monitoring was required for tests, and AVA concluded it was based on the number of references to Respondus within the course.

AVA did not, however, offer answers that were not directly available within the course materials provided by the instructor. My test course did not include a syllabus with a grading breakdown, so when I asked how much an assignment counted toward the Overall Grade, AVA directed me to wait for the instructor’s response.

As you can see from the sample interactions, AVA is not “chatty” or personal. She does not make judgment calls nor offer a personality that may clash with your instructor presence in your course. She’s simply a clear, formal, automated messenger who directs students to the answers you have already posted in your course. Even at 2 a.m.

Getting Started with AVA in Your Course

AVA is disabled in your class by default. Instructors have the option to enable AVA directly from the Details and Actions area of the Course Content page.

Under the Virtual Assistant heading on the main Course Content page, instructors may click “Edit Settings” to enable or disable AVA messaging.

The Edit Settings button will take you to the Course Settings options, where you may toggle the switch labeled “Allow AVA to reply to messages from students.”

Instructors who wish to use AVA must opt in to using this feature in each course by editing those settings.

Final Thoughts

AVA is a new student-facing AI feature in Blackboard. Its prompting is cautious and careful.

It effectively answers very straightforward questions about course logistics 24/7, and it provides a record of interactions for you to expand upon later.

In her most recent newsletter, “From Crutch to Coach?” Dr. Philippa Hardman, a scholar at the University of Cambridge, asks, does generative artificial intelligence (GenAI) “actually make us more capable, or just faster at outsourcing our thinking?“

As we race to keep pace with AI-driven change, it can be hard to keep up with the latest developments in Learning Science, critical thinking, and AI. Hardman’s Learning Science Newsletter offers an incredibly thorough, up-to-date digest of research, tools, and strategies for using GenAI to improve learning.

If you are looking for one go-to source to stay informed on using AI to implement lessons from learning science, Hardman’s newsletter will serve you well.

Hardman’s free weekly newsletter offers an in-depth look at the links between learning science and instructional design. While some weeks’ posts are more useful for professional instructional designers, others offer a refreshing, research-informed take on productive and innovative uses of GenAI to foster critical thinking and promote metacognition.

Below are some highlights from the past few months:

• “From Crutch to Coach?” offers in-depth analysis of a large-scale research study into the use of GenAI for skill development in professional writing.
• “ChatGPT: The World’s Most Influential Teacher” includes a list of The Ten Principles of Substantive Learning and associated chat prompts learners can use while learning with GenAI.
• “Your Learners Are Using AI to Redesign Your Courses” shares recent survey data about the ways learners reach out to AI to fill gaps in scaffolding of course assignment, integrate emotional support into the learning process, expand opportunities to practice course concepts, and restate course content in ways that are more accessible to them.
• “How to Build an AI Tutor from a Document in 10 Minutes” provides a detailed guide to building your own AI tutor, including a prompt template and suggestions for supplementary materials to upload to improve your tutor’s performance.

When students see the relevance of course content in their own lives, they are often more motivated to study, strive for excellence, and succeed. Introducing practical applications can help students connect abstract disciplinary concepts to the kinds of questions they are already asking in real world contexts.

Specialized Generative Artificial Intelligence (GenAI) tools, like the Khanmigo Real World Text Generator or NotebookLM’s podcast-style audio overview, offer inspiration for instructors to integrate examples and cases that increase relevance and motivation.

Khanmigo Real World Text Generator

Khanmigo is an AI Learning Tool offered free to educators by Khan Academy. It is trained on relevant course materials for a range of educational levels, include introductory college courses. Instructors can use the Real World Context Generator or the Make It Relevant lesson planner to introduce challenging course concepts or end each unit with a focus on career relevance.

NotebookLM Podcast-Style Audio Overview

Google’s NotebookLM tool offers a customized, multimedia AI chat for summarizing and asking questions about a collection of resources you select. One of its most exciting features, however, is the Audio Overview, which can synthesize your chosen materials into an engaging podcast-style discussion designed to link course content to real-world contexts.

Take this example podcast generated from a math problem about calculating speed at an instant in time. The math problem includes the formula for instantaneous speed, a word problem about a bicycle, several values for time and distance, and a question for students to solve.

First, I generated a text-based narration by uploading a sample handwritten math problem and solution into ChatGPT.edu and asking it to create a human-centered narration of the problem. Then, I loaded the narration text into NotebookLM and asked for a podcast-style overview focused on applying the source to a real-world context. Inspired by just the mention of the bicycle, NotebookLM created an animated discussion of the principles behind the problem and their real-world applications.

A student may study the problem-solving notes by passively reading for a few minutes, but they might listen to an engaging podcast for 10 minutes while working out the problem alongside the AI “hosts.”

Bonus Tip:

Increase the accessibility of your NotebookLM podcast by download the audio file from NotebookLM and uploading it to your YuJa or Panopto media management account. YuJa or Panopto will automatically transcribe the audio for you, and you can edit the transcript to ensure your podcast meets the accessibility standards for high-quality captions and transcription.

In recent months, a range of journal and news articles featuring Harvard’s AI Tutors have touted the effectiveness of AI tutorbots in fields like physics, accounting, and statistics. Harvard’s AI tutor studies have found that students achieve greater academic success and engagement with personal tutorbots that can generate practice problems and questions or coach students through cases and scenarios from disciplinary or real-world perspectives.

Instructors who would like to take advantage of the benefits of AI tutors (without the time-consuming work of building, training, and testing their own bots) can turn to a range of sources for ready-to-launch AI tutors for students.

General Tutors Students Can Access

• AI Tutor Pro by Contact Nord is our favorite tutorbot. It has three modes: grow knowledge, check knowledge, and discuss knowledge. Students can identify their subject and academic level and enjoy prompting and questioning from the AI tutor in one of eight common languages. At the end of the chat, students may opt to receive a summary of their strengths and areas for further study.
• ChatGPT.Edu has launched its Study Mode for a built-in tutoring support. Login to ChatGPT.Edu with your USC Upstate single sign on through the Spartan Hub to access your protected, full ChatGPT account. In the chat prompt type “Turn on Study Mode,” and ChatGPT Study Mode will coach students to work through problems step-by-step rather than giving out complete answers.

Custom Tutors Instructors Can Build

For instructors who make a free account, AI Faculty Assistant for AI Tutor Pro allows instructors to create their own custom AI tutor trained on OpenStax textbook materials or faculty materials you load into the AI on your own (See AI Faculty Assistant Privacy Policy). Instructors generate a private link to their custom tutor, which can be shared with students in their course.

The AI Conversation assignment tool in Blackboard can also be used to create focused tutoring or coaching experiences at key points in the term. Set up your AI Conversation with a tutoring role play scenario targeting a specific learning experience for your course.

• Design your AI persona as a peer tutor with experience in the detailed course topics you are covering. Or create an academic coach with expertise in study skills and metacognition or a supportive graduate teaching assistant in your discipline who challenges students to expand and develop their ideas.
• Although instructors cannot upload content into the AI at this time, they can encourage tutoring about the learning process needed to study the course content. Invite students to work with the AI persona to draft a paper thesis or outline, develop study skills for an upcoming test, plan a project, or strategize a group assignment.

Google’s NotebookLM now offers a Learning Guide mode that enables instructors to upload or link to relevant materials, create audio or video resources and mindmaps, then share their notebook link with students as a Learning Guide. Students can listen to a podcast-style discussion of course materials, explore flashcards and quizzes, or chat with a tutorbot designed to coach them through ideas step-by-step. NotebookLM has a free plan for individuals, but added features require premium subscriptions.

AI Tutors from Publishers and Library Databases

Many textbook publishers and research databases offer their own AI tutoring and guidance within ebook or database sites.

For textbooks, Pearson, McGraw Hill, Macmillan, and VitalSource all offer coaching or tutoring AI bots embedded in a growing list of their ebooks. Students can see an AI icon while reading their textbook to start a practice session or quiz themselves on what they read.

Library databases such as JSTOR and Proquest offer AI assistants to coach students through the research process. The AI research assistants can suggest additional search terms and offer lists of concepts in selected articles or chapters from ebooks in the library collection. In the coming months even more library platforms and databases will be integrating AI assistants to enable natural language searching and to help streamline research for students.

Bonus Tip

Listen to a Harvard University faculty member describe their AI Tutor prompts in the YouTube video below.