Agavi

Educational technology (edtech) is overly complex, too expensive, and uncreative.  During the COVID-19 pandemic, the transition to digital education left disabled, rural, and impoverished students behind because existing edtech systems are targeted towards privileged customers.

Agavi is a system designed for use by teachers and students everywhere else in the world, where bandwidth and electricity are often unreliable or unavailable.  In addition to low resource demands, the system is also designed to make science learning experiential.  Rather than being yet another system for showing videos and quizzes, Agavi allows teachers to utilize phone sensors and GPS location in their activities, making the smartphone an agent in its environment rather than a mere portal to passive content.  Additionally, the system is being designed with artificial intelligence capabilities, using activity performance data from around the world to help a teacher adjust content to be locally relevant and effective.

Education technology (edtech) comes in two flavors:  show-and-tell builders and choose-your-own-adventure builders.  Show-and-tell builders are by far the most common, allowing teachers to remix text, images, videos, and sometimes simulators, and display it for students, perhaps coupled with quizzes and exams.  They tend to replicate the unengaging passive learning modalities of the 20th century.  Choose-your-own-adventure builders are much better suited for teaching the skills necessary to succeed in the 21st century, as they allow for active learning experiences.  However, they tend to be overly complex and expensive, often requiring dedicated learning design staff and custom solutions.  Essentially, privileged classrooms can buy their way into virtual reality, augmented reality, and always-on cloud computing, while everyone else is left with technology that has changed little since 1999.  "Everyone else" often includes the most disadvantaged populations in the world, including rural, impoverished, and disabled students, resulting in extremely inequitable educational outcomes simply because edtech has spent too much time chasing the 22nd century instead of addressing the existing 21st century digital divide (patchy internet connectivity, lack of accessible options, outdated smartphones and laptops).

Agavi is a web-based adaptive learning system that I am developing with my team that will allow the development of interactive choose-your-own adventure activities regardless of internet connectivity or newness of a teacher's phone, via local instances.  Rather than showing students a wall of questions, the system allows a teacher to split an activity into tasks that students complete one-by-one, providing feedback and alternative pathways when students make a mistake.  Tasks can include reading and answering questions, sure, but Agavi will also be context aware, allowing teachers to integrate phone sensors, bluetooth-connected sensors, and GPS location to create digital-analog tasks that simply aren't possible in current learning environments.  Imagine having a learning system that checks a student's experimental setup using low-cost sensors and gives them feedback before they even collect their first bit of data!

As teachers create, share, adopt, and adapt each others' content globally, Agavi will keep track of how activities are "mutating" to adapt to their local environments, allowing the construction of an AI recommendation engine that helps teachers rapidly adapt content to better serve their local students.  It will finally allow teachers to stand on the shoulders of giants, instead of constantly reinventing the wheel.

The solution targets the science teaching and public outreach system from top to bottom.  With a simple-to-use interface that contains no more complexity than absolutely necessary and one that is built to be accessible for all abilities, teachers of all levels of comfort with technology and physical abilities will be able to quickly build and deploy activities to their students, review how the activities have performed, and identify students' skillsets based on their performance in the activities.  Teachers will no longer need to attend lengthy seminars to understand how the new edtech flavor-of-the-week works ... it will be intuitively obvious.  By keeping the system simple and innovative, the system will be easier to deploy in regions that are currently underserved, especially places with unreliable internet connectivity, such as rural regions, refugee camps, and Indigenous reservations.

Students at all levels will benefit as well.  The COVID-19 pandemic forced a rapid switchover to edtech that was not prepared for the scale of challenge.  The go-to solution was Zoom classrooms, but they required high-bandwidth, reliable internet connections which for many students is not affordable or sometimes even possible.  And research has shown that interactive activities that challenge students are far more effective than passive videos and slides.  With a choose-your-own-adventure builder that is cheap and easy for teachers to use, students will benefit from new activities that will progress them through concepts one at a time, get them physically moving on scavenger and treasure hunts around their local environments, and engaging with their environments using their phones and low-cost sensor kits.  Their smartphones will become learning partners, rather than learning portals.

Equitable classrooms start with empowered teachers.  Too many teachers feel disempowered by edtech due to cost, complexity, and access.  Agavi directly addresses these issues with a cheap and simple system with full offline functionality.  Additionally, by linking with sensors and GPS location, Agavi allows for the development of activities that are unique and experiential, resulting in more engaging digital-analog experiences for students.  Finally, through the AI system that will observe how activities change as they move from teacher to teacher, teachers will receive customized support for localizing content they receive from others, building on global experiences.

We are currently building our first prototype and will have it ready for testing at the end of June.  We expect to move to Pilot stage in July.  We will be testing with teachers in the US, Ukraine, Brazil, and Indonesia (approximately 25 teachers and public outreach specialists working in a variety of settings, including Indigenous reservations, low-income countries, and middle-income countries).

Agavi is innovative because it is being built to solve the problems of the most difficult learning environments first (this was driven by my teaching experience in eastern Indonesia prior to the COVID-19 outbreak).  Most edtech starts its life in high-bandwidth, high-tech environments, which results in design choices and architectures that are impossible to later modify for low-bandwidth environments.

Agavi is also innovative because it will treat the phone as an agent in its environment, rather than a portal to videos, text, and other passive content.  With the ability to access phone sensors (compass, barometric pressure, accelerometers, thermometers), wi-fi/bluetooth sensors, and GPS location, Agavi will allow teachers to build custom activities that have students using their phones like Star Trek's tricorders, something that is not currently done.

Finally, through the unique data architecture surrounding the tasks, Agavi will be able to identify and track "mutations" in content as it is shared and modified by other teachers.  This will allow research into how teachers adapt content that has never before been possible.  By identifying and harnessing these unique insights, Agavi will be able to identify common modifications and changes associated with specific learning environments, allowing other teachers to benefit from these insights as they prep content they find in Agavi's library for their unique classroom challenges.  Imagine having a system that automatically swaps continental examples for island examples if it knows that you live and work on an island.  Currently, that all needs to be done manually by every island teacher.

We are currently working with early adopter teachers in the US, US Virgin Islands, Ukraine, Brazil, and Indonesia (~10 teachers).  We anticipate working with several dozen teachers a year from now and impacting hundreds of students.  Within five years, we anticipate impacting thousands of teachers and millions of students globally.

Because Agavi is still in development, we are monitoring progress according to the functionality of the system.  We are also monitoring community interest in the project through Google analytics on Agavi's website, contributions to crowdfunding campaigns, conversations with strategic partners, and the number of new partners who approach us about the project.

We have four people working on our team on a volunteer basis.  The lead is located in the US Virgin Islands, the back-end developer is located in Arizona, and the front-end developers are located in Romania.

The team lead has been working in the education sector for 20 years, and with edtech for 10 years, including design, development, distribution, teaching, and education research.  He has experience living and teaching in the US mainland, US territories, and eastern Indonesia, and will be adding Ukraine and Brazil in the next year.  He is trained in astrobiology research and education at the PhD level, and as a result, excels in making unique linkages between people, concepts, and cultures.  Currently, he is living and working in challenging teaching and learning environments to gain first-hand experience in the challenges these communities face, in order to better inform the design of the nonprofit's programs and endeavors, including Agavi.

Our back-end developer has 20 years of coding experience and hails from an Indigenous background and community.  He has firsthand experience with the challenges of education in Indigenous community settings, which informs the design of the Agavi's back-end functionality and user experience.

The front-end developers are enthusiastic Romanian students and recent graduates.  Growing up in post-Soviet Romania has given them deep insight into educational inequities and the patchiness of current edtech solutions.  Their recent experiences in education inform the design of Agavi's front-end functionality and user experience.

The approach for building the Agavi leaderships team is to deliberately recruit from the communities we are seeking to serve to ensure that their perspectives and priorities are reflected in the final product.  The team lead comes from a dual-culture household (American and Ukrainian) and actively seeks out lived experiences that help him understand the groups he is working with (hence living and teaching in Indonesia, US Virgin Islands, Ukraine, and Brazil).  The co-lead is a young woman from Romania well-integrated in the Romanian start-up tech sector.  The back-end developer is US Indigenous with connections to many Indigenous groups in Arizona and North Dakota.  As the team expands, we plan on continuing to draw leaders from the communities with whom we are working most closely.

More than funding, we need experienced guidance as we start on our business journey.  Most of us are trained teachers and programmers with little business experience.  We are learning as we are growing, but the challenges of growing and scaling call out for expert guidance, especially in navigating the international market.  In my previous job, I watched our intelligent tutoring system provider mismanage their business and eventually be forced to sell their technology to their competitor.  After the sale, teachers were cut off from the system.  I want to plot a more successful trajectory and implement the change we promise.

We are currently a small group of volunteers, whose previous experience has been teaching, scientific research, and programming.  We are confident that we can build an excellent solution.  We are less confident that we will be able to build a successful business around it.

We would be most interested in partnering with groups focused on development and education.  Partnership priorities are to develop a diverse set of teachers working in diverse settings to implement, test, and provide feedback on Agavi to ensure it is meeting teacher needs globally and advocating for Agavi once it does so.

The Agavi system is designed to help teachers build experiential learning activities for students, as well as utilize AI to assist teachers in improving their teaching by drawing on the experiences of others who have worked in similar settings.  Agavi will be experimenting with a novel evaluation system.  Rather than giving students "points" for the tasks they complete, each task will contribute data (number of attempts, time on question, answers tried, etc.) to a behavioral algorithm that will evaluate whether the behavior demonstrates competence in a skill or learning outcome that a teacher has identified as important.  Students will be able to view their proficiencies in the various skills that the teacher has identified and could potentially use them to find other courses or public outreach experiences that can help them specialize in favored skills or practice weak ones.

Our team would use the ASA Prize for Equitable Education to build and refine the behavioral algorithms for identifying and tracking student proficiencies with a course as well as across various courses, allowing students to create a "skill portfolio" that they can use for college applications, job applications, and for lifelong learning.

The original motivation for developing the Agavi system was the Syrian refugee crisis, specifically a news article about how online learning could help Syrian refugees but that it often didn't because of existing edtech limitations.  It was at that point that I started thinking about how to conduct online education in such an environment.  Although we do not specifically work with refugees yet, Agavi is being built to work in the kinds of environments in which refugee children often live and go to school.  Developing a partnership with the SolarSPELL project (which has expressed interest in Agavi) would allow us to begin serving the refugee community relatively quickly through the SolarSPELL architecture.

Our team would utilize The Andan Prize for Innovation in Refugee Inclusion to optimize the Agavi system to minimize its bandwidth and electricity usage, as well as adapt it to operate out of a solar-powered Raspberry Pi.  We would also utilize the funds to assist the SolarSPELL solar-powered digital library project in construction and distribution of new SolarSPELL units to refugee communities.

The Agavi system is being built as a response to the poor digital tools available for science education.  Science education remains mired in passive learning, often teaching the facts that science has discovered rather than engaging students in and teaching them the skills of the process itself (observing, hypothesizing, model building, evaluation, analysis, etc.).  Engaging students in the discovery and exploration process in the classroom is often impossible because existing edtech solutions simply don't support those kinds of activities.  Technology that is engaging often is very expensive and difficult to use, giving the impression that science learning is a time-idle rich-person's endeavor.  Agavi will demonstrate that science learning can be cheap, easy, fun, and done by anyone anywhere.

We would utilize The GM Prize to seed a "maker" community around the Agavi system, providing a virtual space for innovative teachers to gather to exchange ideas for developing low-cost equipment and science experiences that integrate with Agavi, as well as sensor kits for new teachers who want to get started on developing analog-digital science learning activities.

In many parts of the developing world, the teaching profession is dominated by women who are embedded in patriarchal systems, which can limit the kinds of classroom tools and training that are available to them.  Agavi's teacher-centric approach is designed to address this issue.  By creating a low-cost system that teachers can subscribe to and utilize quickly because of its simple interface, it allows women to bypass hierarchies that can prevent them from accessing overly complex edtech tools that their male colleagues are more likely to have time to learn and money to buy.

We would utilize the Innovation for Women Prize to partner with the SolarSPELL solar-powered digital library project to install the Agavi system on SolarSPELLs, and pay for construction and distribution of the units to impoverished women teachers in regions where SolarSPELL currently operates (Pacific Islands, South Sudan, and Rwanda).

Currently, there exist many digital repositories for science learning activities and content on the internet.  However, there is no data associated with these modules on whether or not they were effective, how they have been modified, and whether those modifications were effective.  Teachers are constantly reinventing the wheel because they can't learn from each others' experiences.

A primary goal of Agavi is to rectify this problem through the use of AI and machine learning to explore the "adaptive landscape" in which teaching resources change.  We are structuring the task architecture in Agavi to capture modification and relational information as teaching activities are copied, modified, and deployed so that we can develop a deep understanding of how activities are modified and what teaching environment characteristics are associated with successful versus unsuccessful modifications.  Using AI and machine learning to understand this "adaptive landscape", we plan on utilizing it to power a construction engine that will draw on the positive and negative experiences of teachers globally to help teachers customize their activities for their particular students and their particular challenges.

We would utilize The AI for Humanity Prize to develop and optimize this AI engine to meet this ambitious goal and create a teaching ecosystem that has never before been seen or attempted.

Currently, there exist many digital repositories for science learning activities and content on the internet.  However, there is no data associated with these modules on whether or not they were effective, how they have been modified, and whether those modifications were effective.  Teachers are constantly reinventing the wheel because they can't learn from each others' experiences.

A primary goal of Agavi is to rectify this problem through the use of AI and machine learning to explore the "adaptive landscape" in which teaching resources change.  We are structuring the task architecture in Agavi to capture modification and relational information as teaching activities are copied, modified, and deployed so that we can develop a deep understanding of how activities are modified and what teaching environment characteristics are associated with successful versus unsuccessful modifications.  Using AI and machine learning to understand this "adaptive landscape", we plan on utilizing it to power a construction engine that will draw on the positive and negative experiences of teachers globally to help teachers customize their activities for their particular students and their particular challenges.

We would utilize The AI for Humanity Prize to develop and optimize this AI engine to meet this ambitious goal and create a teaching ecosystem that has never before been seen or attempted.

Edtech solutions take a global, one-size-fits-all approach.  There is a prevailing attitude that once educational resources or technologies are out on the internet, they will work some kind of transformative magic and fix problems on their own.  The reality is that each educational setting has its own unique challenges.  Some students will have difficulty with math, others will have poor connectivity, still others may lack quiet study spaces at home.  Education is incredibly local and content and technology must be tailored to the unique challenges of each location.  But most edtech solutions aren't natively built to support this.  As a result, customizing content and technology for local challenges is painstaking and must often be completed by each teacher in isolation.

The Agavi system is being built to allow quick and easy customization, as well as the ability to share customization with other teachers working in the Agavi ecosystem.  The AI and machine learning algorithms operating in the background will further assist teachers with that customization.  For example, if Agavi detects that you are teaching in an island environment, it will find the most successful versions of the activity you are customizing that has previously been deployed in an island setting, and make modification recommendations drawn from those activities.

We would use The GSR Prize to enhance the AI and machine learning algorithms that will take Agavi from a system that allows you to build unique content to a system that helps you build the best content for your students.