Conference 2023 Conference 2023

“Charting the Path Forward for Tutoring Based in Evidence and Practice” was the first time hosted an in-person gathering.  Held April 26-27th in Arlington, Virginia, this invite-only event was extended to 31 grantees and provided valuable insights, fresh ideas, and networking prospects within the tutoring community and K-12 Education System.

Investing in the K-12 Education System

John Failla, Founder and CEO at Pearl, and Nate Casey, Chief Strategy Officer at Pearl, spent the day with the Community of Practice listening to panel discussions, participating in breakout sessions, and connecting with fellow grantees. The dedication to incorporating tutoring as a fundamental component of the K-12 education system in the upcoming years has never been more apparent.

Attendees were a wonderful blend of K-12 Education professionals ranging from classroom educators, researchers, policy experts, to EdTech innovators. As panel discussions unfolded and workshops began, everyone contributed their unique knowledge and valuable experiences, making this a truly inspirational event. Conference Key Takeaways

Accelerate’s CEP, Kevin Huffman initiated the conference with an optimistic, yet grounded, perspective on the past two years and the challenges ahead. The room was pervaded by a palpable sense of urgency to demonstrate the efficacy of our approach before the ARP ESSER funding expires in September 2024.

The opening panel featured district leaders from Baltimore and Washington DC, who shared intriguing insights into the complexities of implementing tutoring programs within the K-12 education system. In particular, Arthur Mola, Principal of the Cardoza Education Campus captivated the audience through his discussion on the importance of having a dedicated tutoring lead and the necessary steps to foster genuine collaboration with external support. 

Implementing Tutoring Programs
    1. Having a dedicated tutoring coordinator on your campus greatly streamlines the integration of tutoring into the scheduling framework
    2. Engaging kids in the data that shows their personal academic growth can be a powerful motivating factor.
    3. Rolling out MTSS anew is hard, but can become a strong catalyst for weaving tutoring more thoughtfully into the K-12 experience.
Future of Tech
    1. ChatGPT and AI writing software is not just a clear game changer, it has the opportunity to impact education in many ways, including professional development, assessment, and driving deeper individualized learning pathways.
    2. Although new technologies have a tremendous amount of promise, the “relationship” between student and tutor is still a critical aspect to learning.
    3. New technology is focused on driving down the cost of individualized learning which may soon allow for a single teacher to teach a classroom of students with individual learning gap data feeding “in real time” to the teacher. 
Ensuring Outcomes Through Policy
  • Every case study examined (Arkansas, Tennessee, and Texas) took a different approach to leveraging policy as a way to move quickly on tutoring.
  • In many instances, the most meaningful policies are the ones that unblock heavy barriers to entry, like streamlining criminal background checks or incentivizing tutors with better pay.

There is a great opportunity to incentivize programs that adhere to strict evidence-based approaches to delivering tutoring (i.e. – TQIS as defined by the NSSA)

Sustainability and The Future
    1. Increased emphasis on personalized learning: With advances in educational technology and the availability of data-driven insights, more school districts are likely to adopt personalized learning models that cater to the unique needs and preferences of individual students. This may include a greater use of adaptive learning platforms, virtual tutors, and other tools that enable students to learn at their own pace and according to their own learning styles.
    2. Greater collaboration between schools and external stakeholders: To address the increasing demand for high-quality tutoring services, K-12 education systems and school districts may partner with external stakeholders such as community organizations, non-profits, and private companies to provide additional resources and support. This may involve the development of public-private partnerships, grant programs, and other initiatives that bring together various stakeholders to improve access and equity in education.
    3. Enhanced infrastructure to support remote learning: In light of the COVID-19 pandemic, many school districts have already invested in upgrading their infrastructure to support remote learning. This trend is likely to continue in the next five years, with more schools adopting blended learning models that combine traditional classroom instruction with online and remote learning opportunities. This may require investments in new hardware and software, as well as training and professional development for teachers and staff to support effective remote instruction.

Accelerate actively builds the country’s knowledge of tools and practices that significantly advance student learning. [They] do this by bridging the gaps between research, communities, and systems to ensure the rapid and widespread adoption of proven strategies.

Pearl Convenes Inaugural Community Tutoring Partnerships Summit Attended by State, University and District Leaders Across 18 States

Pearl Convenes Inaugural Community Tutoring Partnerships Summit Attended by State, University and District Leaders Across 18 States

Participants curated best practices that underscore the importance of diversifying tutor supply, establishing training and professional development pathways, and using evidence to validate programs

RICHMOND, Va. — Pearl, the leading research-based tutor management platform, announced today insights from its inaugural Community Tutoring Partnerships Summit focused on the rise of community tutoring partnerships. Community tutoring partnerships bring together states, districts and higher education institutions to leverage existing community resources with the goal of developing sustainable tutoring programs designed to solve each community’s greatest needs. 

The first-of-its-kind day-long virtual summit was attended by leaders spanning 18 states and 39 higher education institutions serving hundreds of districts nationwide.  The event highlighted evidence-based strategies and lessons from the nation’s leading community-tutoring experts including Dr. Christy Borders E.d.D, Director of the Illinois Tutoring Initiative at Illinois State University, Faith Freeman P.h.D, Co-Director of Institute for Partnerships in Education at University North Carolina GreensboroSusanna Loeb P.h.D, Director of the Annenberg Institute of School Reform at Brown University, and Patrick Steck, Senior Director of Policy for Deans for Impact. 

“Community-designed partnerships as a segment are showing significant promise in the fight against learning loss,” said John Failla, CEO and co-founder of Pearl. “These partnerships enable local school systems to build sustainable innovation right into their model. The result is a meaningful, measurable impact to lead to academic outcomes.”

During the summit, the National Student Support Accelerator also launched its inaugural Higher Education Toolkit, a playbook aimed to support Higher Education Institutions in partnering with school districts to offer high-impact tutoring services. The biggest takeaway from the convening was a unanimous consensus among key stakeholders that understanding how to retain, recruit, manage and support tutors is the most pressing issue to ensure tutoring is sustainable and effective in driving student outcomes.

With the Biden administration calling for an additional 250,000 tutors and mentors to help students make up for lost instruction time due to the pandemic, tutoring has emerged as an essential component of K-12 education. Researchers, across multiple studies, find that high-impact tutoring can dramatically accelerate student achievement. 

However, creating an evidence-based tutoring program can be daunting, especially during unprecedented education staffing shortages and uncertainty on resources post ARP-ESSER funding. Schools and districts have significant questions about recruiting, training and coaching tutors, choosing the most efficacious compensation model and how to ensure sustained funding in the future, and how to structure and measure the performance of a wide variety of critical interventions. 

Having partnered with multiple state, university and district-led community-tutoring programs since 2020, Pearl is developing the nation’s most diverse dataset in the tutoring industry. The platform is foundational for managing and scaling hybrid tutoring through evidence-based best practices in collaboration with the Annenberg Institute at Brown University and its National Student Support Accelerator (NSSA) to safely gather data to continuously improve program design and measurably accelerate student outcomes. In March, Pearl announced that it had joined the innovative community-based tutoring program endorsed by Virginia Governor Glenn Youngkin in partnership with the Urban Leagues of Hampton Roads and Greater Richmond and four historically black colleges and universities (HBCUs).

Failla concludes, “Certain geographies and specialties are in deeper need today, and they’re seeking guidance and evidence to stand as clear examples for how to build high-impact tutoring programs based on efficacy. These best practices curated by our participants at state and district levels can serve as that north star.”

To read more about the ten key takeaways from the Community Tutoring Partner Summit, visit 

About Pearl

Based in Richmond, VA, Pearl is the leading research-based tutor management platform that streamlines operations, reports actionable data, and improves outcomes for districts, state agencies and organizations tutoring tomorrow’s workforce, today. The platform’s fully integrated classroom and administrative tools allow its partners to launch, scale and sustain evidence-based tutoring to support measurable outcomes for all communities. The Pearl ecosystem provides access to the nation’s largest and most respected industry partners including the Annenberg Institute at Brown University and the National Student Support Accelerator at Stanford University.  For more information visit

Why is it so challenging to conduct research in K-12 education?

Why is it so challenging to conduct research in K-12 education?

The Intricacies of Conducting Research in K-12 Education: An In-Depth Analysis

Our country desperately needs an overhaul in K-12 education. In order to make this a reality, the quality of supporting research is essential. Research in K-12 education is often hampered by a number of challenges, making it difficult to conduct rigorous studies. This blog explores the challenges our K-12 researchers face today as well as possible solutions. 

Ethical Considerations

Human subjects research is governed by ethical considerations, especially when involving children. Any legitimate research that includes humans must go through an Internal Review Board (IRB). This process can vary from institution to institution as well as the nature of the research being proposed. Generally the steps include determining if the IRB is necessary, developing a research plan, completing an application to the IRB, submitting the application, responding to follow up requests and questions form the board, IRB edits and/or potential research design improvements, then receiving approval or “sigh” more required  changes prior to approval. This is a lengthy process and further complexity is introduced by funding and the needed consent from participants.  

The well-being and privacy of students will always be prioritized by parents, educators, and researchers alike. Therefore, obtaining informed consent from parents or guardians can be arduous and time-consuming. Study designs must respect students’ rights and protect their welfare while also remaining scientifically valid. Balancing all of the components of privacy, consent, and meeting the expectations of your institution and/or funders is not for the faint of heart.

Diverse Settings

From public to private institutions and from rural to urban environments, K-12 education encompasses a wide range of school types. The diversity of these populations can make it difficult for researchers to generalize their findings to broader populations or to draw conclusions that can be applied to a variety of contexts. There may also be unique policies, procedures, and curricula within each school and district that may affect research results.  It is also important to consider the intent of any study performed within the K-12 setting. There is some precedent for data being misused in ways that offset equity in the US.

“If we are imposing measures of success on communities, we are essentially also then imposing our values and agenda on them. Communities have been burned and harmed by the ways that measurement has been weaponized in past education reform efforts without their involvement.”

Confounding variables

It can be difficult to isolate the effects of a particular intervention or practice in educational research because of the complex interplay of factors that influence student learning. Among these factors are classroom dynamics, socioeconomic status, student motivation, parental engagement and teacher quality. Accounting for these different variables is often complex and time-consuming. The teacher shortage is also causing inconsistencies in resources that exacerbate the teacher quality and can strain new strategy implementation.

Resource constraints

K-12 education research often requires significant time, money, and human resources. In order to understand the long-term effects of educational interventions, longitudinal studies can span several years and require ongoing funding. Schools and teachers are often reluctant to participate in research projects having concerns about disrupting their daily routines and time away from instruction. Many teachers are also very much focused on raising state test scores and often fear variation from prepping towards their teaching goals. Lastly, even with district buy-in for a study, researchers also end up having to coordinate directly with individual schools for execution. 

Messy Data Issues

The arduous process of accessing K-12 education data can be extremely frustrating. This is especially true when the data is messy and almost impossible to aggregate for research purposes.  In spite of the fact that schools and districts have enormous amounts of valuable data, that data is often siloed, difficult to aggregate, or disorganized. Researchers are often unable to extract useful insights from school data due to its disorganization and disaggregation.

Additionally, because centralized school data is already difficult to parse, bringing in outside systems (such as disparate assessment providers) or giving them access to school insights from outside tutoring companies or professional development providers can also hinder or slow down progress.

Political and policy pressures

Changing policy priorities and a heated political climate also affect education, creating more challenges for researchers. It is possible for political agendas and policy changes to dictate which research areas receive support or funding, hindering the exploration of innovative ideas. Policy makers are focused on ROI in the final year of ESSER due to high expectations for reporting. State tests and NAEP scores in 2024 will remain the primary focus of governors’ offices. 

The level of focus on ROI may make it challenging to try new things or implement research that goes beyond basic third-party evaluations.  It is also possible for researchers to be pressured to produce results that support a particular policy or program. Their objectivity and integrity can be compromised by this kind of pressure. 


Educating children is a complex endeavor, involving ethical considerations, diverse learning environments, confounding variables, and  resource constraints. In order to overcome these challenges and contribute to the improvement of education, researchers, educators, policymakers, and other stakeholders must collaborate and be willing to adapt and innovate.

A number of solutions are possible, including simplifying the informed consent process, creating standardized research methodologies across multiple educational contexts, and advocating for increased funding and support for long-term, objective research.

Some additional solutions might include:

  1. Creating Collaborative Research Networks that establish long term research relationships with key K-12 stakeholders.  
  2. Interdisciplinary Approaches: Researchers can collaborate with experts from other fields to bring a multidisciplinary perspective to their research. This can help to address the complex and multifaceted nature of the challenges facing K-12 education, and can lead to more innovative and effective solutions.  This approach may also help with LEA and school level buy-in. 
  3. Technology-Based Solutions: It may be possible to set up more robust data aggregation that are inherently part of native school data systems.  This could streamline the research process and make it more efficient. For example, online survey tools, data management software, and educational data analytics platforms could help researchers identify possible research and better collect, manage, and analyze data already collected. 

Our goal at Pearl is to unlock educational research’s potential to improve K-12 education in the US. We are always looking for creative ideas and partners to help bridge the research to practice gap.  Please reach out anytime to schedule a discussion.

To Access Great Education Research with a focus on tutoring – NSSA Research Repository

Unsure of how to tackle the challenges of your large online tutoring program? Schedule time to speak to a Pearl expert and learn best practices for evidence-based tutoring with Pearl.

Pearl Joins Urban Leagues of Hampton Roads, Greater Richmond, Four HBCUs to Launch Tutoring Programs

Pearl Joins Urban Leagues of Hampton Roads, Greater Richmond, Four HBCUs to Launch Tutoring Programs

Tutor management and efficacy provider Pearl will manage and measurably scale tutoring to thousands of underserved middle and high school students

Richmond, VA (March 7, 2023) Pearl, the leading tutor intelligence and efficacy platform, today announced it has joined the innovative community-based tutoring program endorsed by Virginia Governor Glenn Youngkin in partnership with the Urban Leagues of Hampton Roads and Greater Richmond and four historically black colleges and universities (HBCUs). In an effort to address critical learning gaps, the program will employ hundreds of HBCU students as tutors and mentors to middle and high school students throughout their communities.

As part of the initiative, Pearl will initially support the Urban Leagues of Hampton Roads and Greater Richmond to launch and manage tutoring for nearly 1500 students in Hampton City School District and Petersburg City Public Schools over the next two years with plans to expand the program to Richmond City and other districts in underserved communities. Participating HBCUs include Norfolk State University, Hampton University, Virginia State University, and Virginia Union University. 

“I’m thrilled that Pearl’s all-in-one tutor management and efficacy platform is partnering with our treasured Historically Black Colleges and Universities. This partnership is a testament to the commitment we have made to help high and middle schoolers in their communities get caught up in school,” said Governor Glenn Youngkin. “Pearl is the perfect example of the kind of collaborative, inventive partnership we want to see across the Commonwealth to support our students.”

“Faced with enormous learning loss and displacements, we are honored to join these outstanding partners in this first-of-its-kind, governor-endorsed tutoring program to launch and scale measurable tutoring support,” said John Failla, CEO and co-founder of Pearl. “Community-based tutoring is proving to be a sustainable modality to support both social-emotional learning and academic outcomes. We are especially excited about being able to serve the students across our home state of Virginia.”

In announcing the partnerships, Governor Youngkin described it as a “breakthrough initiative” focused on learning loss recovery by recruiting HBCU college students in “transformational tutoring partnerships.” Gill Bland, President and CEO of the Urban League of Hampton Roads, said the undertaking would “provide academic enrichment options through enhanced opportunities for tutoring and mentorship.” Interim CEO of Urban League of Greater Richmond, Larry Murphy added that the partnership is a “great opportunity to connect resources and services for the most ‘at promise’ students in Virginia.”

“Virginia 4th graders had the largest decline in math and reading scores as reported on the Nation’s Report Card; we are on the cusp of losing a generation of our children due to historic learning loss,” said Aimee Guilderia, Secretary of Education for the Commonwealth of Virginia.  “This inspiring partnership will change this trajectory and ensure that our children get back on track for academic and lifelong success.”

Having partnered with multiple state, university and district-led community-tutoring programs, Pearl is developing the nation’s most diverse dataset in the tutoring industry. The platform is foundational for managing and scaling hybrid tutoring through evidence-based best practices and collaborates with the Annenberg Institute at Brown University and its National Student Support Accelerator (NSSA) to safely gather data to continuously improve program design and measurably accelerate student outcomes.

For more information about Pearl’s tutor management and efficacy platform for states, districts and enterprise tutoring companies to launch, manage and measurably scale hybrid tutoring programs, please visit: 

About Pearl

Richmond-based Pearl is committed to scaling sustainable, evidence-based tutoring to support measurable academic outcomes for all students. The platform’s fully integrated classroom and administrative tools allow enterprise tutoring companies, academic organizations, districts, and states to launch and scale hybrid tutoring programs with ease. Whether instruction occurs online or in person, Pearl’s all-in-one tutor management system provides education decision-makers with the tools needed to improve student learning. Additionally, in collaboration with the Annenberg Institute at Brown University and its National Student Support Accelerator, Pearl safely collects and protects the necessary data to prove efficacy and improve program design to ensure all students thrive. To learn more about Pearl, visit


The Implications of Large Language Machine Learning Models in Tutoring

The Implications of Large Language Machine Learning Models in Tutoring

Since ChatGPT was released to the public via OpenAI the education community has been in constant chatter about its implications for learning. A large language model is a machine learning system that uses vast amounts of data to generate human-like language and perform natural language processing tasks such as text generation, translation, summarization, and sentiment analysis.

If you have not experienced ChatGPT you should. It’s definitely an exciting next generation in how we think about searching on the internet. For almost a quarter of a century Google has been the cornerstone of where we find information online. Google presents relevant links based on search. With ChatGPT information is presented in natural language and feels much more like a chat with someone very knowledgeable about the question you ask. 

Although the conversation feels fairly natural and the answers are cogent, they are not always correct. That being said, if you have a decent understanding of a subject you will probably find that the chat feels authentic and most of the time pretty accurate.  

When the AI was released everyone at Pearl was interested in jumping quickly and trying to understand the implications for tutoring. We spend a lot of time thinking about equity and imagine a world where anyone that needs a tutor could have a tutor. None of us is convinced that AI could replace a human, but I do think that AI has the capacity to make someone better at tutoring or give more opportunities for people to teach.

Here are some interesting implications for the tutoring industry:


Without compromising any person’s identity a tutor admin can give a list of characteristics of a learner and then ask to see corresponding characteristics of a tutor. Below is an example of a question and ChatGPT’s answer:


“Based on the research, what are 5 strong characteristics to look for in a tutor that would match well with a 9 year old Asian dyslexic child coming from a poor socioeconomic background learning in English whose first language was Chinese?”


“Great question! Here are five strong characteristics to look for in a tutor that could match with an Asian 9-year-old dyslexic child coming from a poor socioeconomic background learning in English whose first language was Chinese:

  1. Patience: A tutor who is patient can help the child feel comfortable and confident as they learn. Dyslexia can be frustrating and challenging for a child, especially when they are also trying to learn a new language. A patient tutor can help the child to feel supported and encouraged.
  1. Multisensory approach: Dyslexic children can benefit from a tutor who uses a multisensory approach to learning. This means that the tutor can use different senses, such as sight, sound, and touch, to help the child learn. For example, the tutor could use visual aids, like pictures or diagrams, or use physical activities to help the child understand the material.
  1. Experience working with dyslexic children: It’s important to find a tutor who has experience working with dyslexic children. This experience can help the tutor understand the unique challenges that dyslexic children face and how to tailor their teaching methods to meet the child’s needs.
  1. Cultural sensitivity: A tutor who is culturally sensitive can help the child feel understood and respected. It’s important to find a tutor who is familiar with the child’s cultural background and can be sensitive to their unique needs and experiences.
  1. Flexibility: Finally, it’s important to find a tutor who is flexible and can adapt to the child’s needs. Dyslexic children can learn at different paces and in different ways, so the tutor should be willing to adjust their teaching methods to meet the child’s individual needs. Additionally, the tutor should be flexible in terms of scheduling and availability to ensure that the child can receive consistent support.”


Once ChatGPT or some version of this type of AI is available, an admin could ask AI to construct a calendar based on the data for two tutors.  Here is an interesting example of ChatGPT’s response to a basic scheduling prompt.


I am a tutor that needs to meet with my student three times a week for 30 minutes each time.  I would like to know the dates I can meet with that student in school based on a typical school calendar.


The specific school calendar will depend on the school district and location. However, in general, most schools in the United States operate on a traditional academic calendar, with two semesters per year (fall and spring) and breaks for holidays and summer vacation.

To determine the possible meeting dates, you can start by looking up the school district’s academic calendar online or contacting the school directly to get a copy of the calendar.

Assuming a typical school calendar, here is a general example of possible meeting dates for a tutor meeting three times a week for 30 minutes each time:

  • Fall Semester: September to December (approximately 16 weeks)
    • Possible meeting dates:
      • Monday, Wednesday, Friday: September 6th to December 16th (excluding holidays)
      • Tuesday, Thursday, Friday: September 7th to December 16th (excluding holidays)
  • Spring Semester: January to May (approximately 16 weeks)
    • Possible meeting dates:
      • Monday, Wednesday, Friday: January 10th to May 20th (excluding holidays)
      • Tuesday, Thursday, Friday: January 11th to May 20th (excluding holidays)

Keep in mind that these dates are approximate and may vary depending on the specific school calendar. It’s important to confirm the exact school calendar with the school or district to ensure that the meeting dates are accurate.”


We’re starting to get into the interesting part now. Obviously, it is imperative that the teacher’s knowledge confirms, in some way, whether the ChatGPT response is helpful. As an example, ChatGPT can help tutors contextualize or better consider a student’s learning style or interests in order to support their tutoring. Let’s see if ChatGPT builds some math problems based on two factors (age and affinity) based on my son’s interest in trucks and construction equipment.


My son is 12 years old and has a strong affinity for trucks and construction equipment.  Based on his age and interests please produce 3 great ways to teach him long division. 


If your son has a strong interest in trucks and construction equipment, incorporating these interests into his long division lessons may help him stay engaged and motivated. Here are three great ways to teach him long division:

  1. Use visual aids: Use pictures or diagrams of trucks and construction equipment to explain the steps of long division. For example, you could use a picture of a dump truck to represent the dividend and use smaller pictures of construction equipment, such as bulldozers or excavators, to represent the divisor and quotient. This can help your son visualize the process and make it more concrete and meaningful.
  1. Turn division into a game: Create a game that uses trucks and construction equipment to teach long division. For example, you could create a game where your son has to use a dump truck to carry a certain number of building materials and use excavators to divide the materials into equal groups. Each time he successfully divides the materials, he can move to the next level of the game. This can make the learning process more fun and interactive.
  1. Use real-life examples: Find examples of how trucks and construction equipment are used in real-life scenarios that involve division. For example, you could use examples of construction projects where trucks have to haul and divide large quantities of materials. This can help your son see the practical applications of division and make it more relevant to his interests.

Remember, every child learns differently, so it’s important to find an approach that works best for your son. Incorporating his interests and making learning fun can go a long way in helping him stay motivated and engaged in the learning process.


Assessment is the final interesting implication for tutoring.  At Pearl, we believe the key to tutoring is quick formative assessments that verify student learning and identify areas where knowledge or understanding might be lacking. Once again, this is a great way to leverage several variables in a question. The following are two examples that you may find interesting:


Please give me three formative assessment questions that will help me validate that my 9 year old student understands long division.


  1. Can you explain the steps involved in long division and how they relate to each other?
  1. Can you solve a long division problem independently and explain how you arrived at your answer?
  1. Can you apply long division to solve real-world problems and explain how you arrived at your answer?


Please provide me with 3 problems to solve that would assess my 9 year old’s understanding of the basics of long division.


  1. 84 ÷ 6 = ?
  1. 145 ÷ 5 = ?
  1. 232 ÷ 8 = ?

Note: These problems are designed to test the student’s understanding of the basic steps of long division. When assessing your student’s responses, make sure to check that they have correctly used the divisor, dividend, quotient, and remainder, and that their final answer is correct. It’s important to provide feedback on their work and address any areas where they may need additional support or practice.


When tutoring programs consider using ChatGPT or any of the other emerging large language model AI tools, they must validate the tools carefully.  It is possible to speed up certain processes, but there is a cost associated with it.  There is a possibility that AI is extrapolating biases that are not aligned with your ethics.  Additionally, tutors should cultivate value that reflects their approach to tutoring and not rely too heavily on computers.  Relationships are at the heart of tutoring, so it’s important to foster connections and care throughout the process. Nevertheless, keeping up with the changing world is essential.  There is no doubt that our students will benefit from this new tech; therefore, as educators to the next generation, we need to keep our eyes on the ball. 

Now, for kicks, let’s let ChatGPT have the final word ?


What are the implications of Large Language Machine Learning Models in Tutoring


Large language machine learning models have several potential implications in tutoring, including:

  1. Personalized Learning: These models can help provide more personalized learning experiences for students by tailoring the content and pace of the instruction to their individual needs, interests, and learning styles.
  1. Immediate Feedback: The models can provide immediate feedback to students on their work and progress, helping them identify areas where they need additional practice or support. This can help students stay engaged and motivated and can also help teachers more effectively monitor student progress.
  1. Automated Scoring and Grading: These models can help automate the grading and scoring of student work, freeing up time for teachers to focus on providing individualized instruction and support to students.
  1. Improved Accessibility: These models can help make tutoring more accessible to a wider range of students, including those with disabilities or who speak different languages.
  1. Improved Instructional Design: These models can help identify patterns in student learning and suggest improvements to instructional design and content, helping teachers to more effectively support student learning and improve outcomes.

However, there are also some potential challenges and limitations to the use of large language machine learning models in tutoring, including issues of privacy and data security, the potential for bias in the algorithms used to analyze and evaluate student work, and the need for teachers to be trained in how to effectively use and interpret the results of these models.

The End…

Tutoring needs a standard approach to assessments

Tutoring needs a standard approach to assessments

The many variations across hundreds of tutoring RFPs

Each year our public school districts issue hundreds of requests for proposals (RFPs) for high-impact tutoring support, but there is no standard approach to collecting feedback and assessments of the tutoring. Many districts require their tutoring providers to administer academic assessments, while others do not. Here at Pearl, our partners typically follow one of these 4 approaches to assessments:

  1. The tutoring provider uses a specific assessment tool (like iReady or NWEA MAP) to assess students at all stages of a student’s tutoring experience.
  2. The tutoring provider assesses each student’s progress (choosing their preferred benchmark, formative, and other assessment types) with no specific assessment tool requirement other than the assessment questions used must meet the state’s ESSA standards.
  3. The tutoring provider supports students but is not required to administer the assessments. In this case, the district runs the assessments and advises the tutoring provider accordingly.
  4. A state-based program serving multiple districts is required to use different assessment tools depending on the requirements of each district they serve. In these cases, the state agency is also left with the complicated task of comparing district progress with varied types of outputs and insights from multiple assessment tools.

The Pearl platform provides the technical scaffolding for state and district tutoring programs, nonprofits, and enterprise-level tutoring companies. For each of these different client types, we take an agnostic approach to how academic progress is assessed. Sometimes our partners have their own assessments, like district-funded programs, and other times they simply follow the requirements defined in the contracts they serve, such as outside tutoring companies responding to RFPs. 

In a “best case” scenario tutoring providers would have: 

  1. A diagnostic or benchmark assessment from the student’s school (or district) to inform gaps in learning and insights into how that student learns most effectively
  2. A viable feedback loop with a student’s school teacher(s)
  3. A formative assessment tool that:
    1. Meets the applicable state ESSA standards
    2. Aligns with the school’s curriculum 
    3. Is agile enough to be used on the fly
    4. Provides a way to regularly measure student academic progress
    5. Informs clear opportunities for tutors to employ an individualized learning pathway for their students
  4. A final “end of tutoring” assessment to measure progress against the benchmark test

If more districts had the resources to increase their level of system interoperability, the above “best case” assessment pathway would be more widely viable. It is common for even sophisticated districts to lack an elegant method for merging assessment data from providers with SIS student records. In addition, tutors may be unable to access useful academic-related data because of security concerns and requirements.

In the absence of a standard assessment methodology, a host of problems arise. To determine learning gaps, tutors often need to conduct several sessions without a baseline. If a tutor does not use a formative assessment approach aligned with the student’s starting point, he or she may be left guessing about the student’s understanding gaps. Also with so many assessment approach variations, it is difficult to compare programs district-to-district or state-to-state. 

To develop a successful tutoring program, four key data categories are needed (attendance, dosage, academic progress measurement, and SEL insights). In the absence of academic progress that relates to individual students, tutor providers are unable to measure the true picture of progress or show clear ROI to stakeholders. With the final ESSER cliff fast approaching it is critical that programs robustly measure efficacy. Only programs that demonstrate evidence of effectiveness will be sustainably funded in the future.