Teacher educators are perpetual experimenters. We build, test, revise, and build again, not because we seek novelty, but because the students in our classrooms demand it. Mathematics is the language of the universe. It underlies the structures of nature, the logic of systems, and the foundations upon which societies organize, govern, and flourish. When young learners develop mathematical reasoning, they are not merely acquiring a skill; they are gaining access to a way of understanding the world that is essential to informed citizenship, equitable participation, and human dignity. It is this conviction that mathematical understanding is inseparable from societal well-being that connects our work to broader inquiry into how artificial intelligence can serve, rather than diminish, the conditions for human flourishing. Our students will inherit tools we cannot yet imagine, so our work is to model what thoughtful experimentation looks like: trying things, observing what happens, and learning from what emerges.
Estella AI: A Purpose-Built Custom AI
A little less than two years ago we built Estella AI, a purpose-built custom math bot, a specialized tutor bot designed to help elementary school teachers and learners understand math word problems’ procedures and concepts in easy-to-read, student-accessible language (Gattupalli, Maloy, & Edwards, 2024). Estella AI is based on one of four virtual characters in Usable Math, a free online math and reading tutoring platform we had built earlier using Google Slides.
Estella AI is designed to respond to prompts and queries with language at the “very easy” readability level (a 90 to 100 score range) on the Flesch-Kincaid Reading Scale (Flesch, 1948). As a conversational partner for teachers and students, Estella AI can keep refining sentence structure, tone, and language to support understanding for young readers and expand its capabilities as a reading coach in Usable Math. Estella’s role as a coach centers on math readability, helping students decode the language of word problems, because every math word problem is fundamentally a reading problem. To build Estella AI, we employed a 10-shot learning technique, using carefully crafted, human-created hints for math word problems as learning material. These original hints were developed by experienced math teachers with more than 30 years of classroom practice, helping ensure that the bot’s responses reflect pedagogical judgment rather than generic machine output.
Since its inception as part of Usable Math, Estella AI has been tried by elementary and high school teachers, math tutors, and college students enrolled in our courses at the University of Massachusetts Amherst. Estella AI also assisted in building an open online A to Z alphabet book for young readers explaining AI-related words becoming widely used in everyday language and media (Maloy, Xu, & Edwards, 2025a; Maloy, Xu, & Edwards, 2025b).
Currently we are using our curiosity about Estella AI to generate ideas beyond its initial focus on understanding the language of math word problems. This article reports emerging new directions as our AI continues responding to and learning from prompts. These experiences may provide ways for teachers and other educators to use this tool to address their own curiosity or design their own AI to support student learning.
Example: Interdisciplinary Curriculum Connector
We wondered whether Estella AI, designed originally as a tutor for math word problems, could generate ideas for interdisciplinary or cross-disciplinary curriculum learning. We chose an important history/social studies event, the Montgomery Bus Boycott of 1955-1956, when African American citizens in Montgomery, Alabama refused to ride segregated city buses for 381 days following the December 5, 1955 arrest of civil rights activist Rosa Parks. The bus boycott led to a landmark Supreme Court decision declaring segregated public transportation unconstitutional in the United States.
We prompted Estella AI to write a fourth grade math problem about the Montgomery Bus Boycott. Here is the chatbot’s response:
Montgomery Bus Boycott Math Problem
During the Montgomery Bus Boycott, about 40,000 Black residents stopped riding the buses. Before the boycott, each person rode the bus twice a day (once to work and once home). How many bus rides were lost each day because of the boycott? If the boycott lasted 381 days, how many total bus rides were lost?
Bonus question: If each bus ride cost 10 cents, how much money did the bus company lose in total?
Answer: The bus company lost $3,048,000 in total (approximately $36,856,000 in 2026).
Next we asked the chatbot to write a story about the Montgomery Bus Boycott using the words of participants that students could read, illustrate, and perform in class. The chatbot’s response included quotes from Dr. Martin Luther King Jr., Rosa Parks, and unnamed bus boycott participants:
Walking for Justice: A Story of the Montgomery Bus Boycott
The morning was cold, but Sarah Johnson didn’t mind. She wrapped her scarf tighter around her neck and started walking. It had been weeks since she had ridden the bus, but she would not give in now.
Down the street, she saw her neighbor, Mr. Fred Daniels, stepping carefully on the sidewalk. “Morning, Mr. Daniels!” she called. He smiled. “Morning, Miss Johnson. Another day on these feet.”
Sarah nodded. They had all agreed they would not ride the buses until they were treated fairly. Ever since Rosa Parks had been arrested, Black people in Montgomery had decided: enough was enough.
The boycott had started on December 5, 1955, the day of Mrs. Parks’ trial. That morning, Dr. Martin Luther King Jr. had stood in front of a crowd at Holt Street Baptist Church and said: “There comes a time when people get tired of being trampled over by the iron feet of oppression.”
The church had erupted in applause. Sarah had been there that night, standing in the back. She remembered how she had clapped so hard that her hands hurt.
Now, weeks later, she still was not riding the bus. Most Black people in Montgomery were not. They walked. They carpooled. Some even rode mules and horses. The bus company was losing money every day.
One afternoon, Sarah stopped by the home of an elderly woman from her church. “Would you like a ride, Miss Emma?” she asked. Miss Emma shook her head with a determined smile. “My feets is tired, but my soul is rested.”
Sarah smiled and kept walking.
The boycott lasted 381 days. It was not easy. People lost their jobs. Some were arrested. But they kept walking. They kept fighting.
Finally, on December 20, 1956, the Supreme Court ruled that segregation on buses was illegal. The boycott had worked. The next day, Dr. King rode the bus with other Black citizens. They sat wherever they wanted.
As Sarah climbed aboard a bus for the first time in over a year, she thought of Rosa Parks’ quiet bravery, of Dr. King’s powerful words, and of Miss Emma’s tired but determined feet. She smiled as she took a seat in the front.
Example: Learning Game Designer
We wanted to see if Estella AI would design a learning game to teach an important, but potentially difficult economics concept: exponential growth. We gave the chatbot this prompt: Design a game for 4th, 5th, and 6th grade elementary school students to learn about exponential growth. Make the game interesting for students so they are challenged but not discouraged by the game play. Make the game open-ended so students can play multiple times and not experience game play in the same way every time.
Here is the bot’s response for a game it called Growth Quest: The Power of Multiply:
Core Game Loop (Each Round)
Each round represents one time step (day, week, or year).
Step 1: Start with a Small Amount Each player begins with one seed, creature, robot, or energy unit.
Step 2: Choose a Growth Path Players choose one option each round:
- Steady Grow: Add +2 units
- Power Grow: Multiply by 2
- Risk Grow: Draw a Growth Card
- Protect: No growth, but safe from loss
Step 3: Growth Event (Random and Open-Ended) Draw a Growth Card. Examples: “Your population doubles again,” “Only half of your units survive,” “Your growth repeats twice this round,” “Switch growth paths with another player,” “Choose: double or triple.”
Step 4: Record and Represent Students record results by drawing groups, using counters, writing numbers, or making bar models and arrays.
Winning (Multiple Ways to Win) There is no single winner. Possible win conditions include reaching a target number, growing most efficiently, predicting growth accurately, explaining growth over time, or surviving the longest without losses.
Surprisingly, without explicit prompting, Estella AI also included how the game addressed upper levels of Bloom’s Taxonomy (analyze, evaluate, create) and Universal Design for Learning (UDL).
Example: Primary Source Summarizer
One of the most challenging features of history/social studies teaching is having students read primary source materials. Primary sources matter because they present history as participants experienced it, but the language can be difficult, leading students to give up on meaning-making. We wondered whether Estella AI would generate accessible summaries that teachers could use to guide reading and support understanding.
To explore this function, we chose the Mayflower Compact of 1620, signed by 41 Pilgrims as they journeyed by ship to North America from Europe. It is considered one of the founding documents of U.S. government in setting forth a framework for democratic self-government. We asked Estella AI to summarize the text in student-accessible language:
The Pilgrims wrote it when they landed at Cape Cod in 1620. In it, they say:
- They are loyal to King James of England.
- They are traveling for God, for their faith, and for their country.
- They agree to form a group that will make rules and laws to help the colony survive.
- Everyone in the group promises to follow these rules, even if they are hard.
- They signed their names to show they meant it.
In very simple words: The Pilgrims promised to work together, follow fair rules, and build their colony in an organized way.
Example: Story Generator
Stories are powerful learning experiences for students across grade levels, especially when they are free to write, draw, and perform their own stories (Edwards, Maloy, & Trust, 2019). As story creators, students stretch their imagination and develop their identities as learners. We wondered how Estella AI might support children’s story writing, not by writing entire stories, but by offering a beginning framework that students could extend in multiple directions. We used this prompt: Start a detective mystery story about classifying two-dimensional figures that students can continue to write and draw. Include at least two characters and include dialogue and description as part of the story beginning.
The Case of the Mysterious Shape Mix-Up
It was a rainy morning in Geometryville Elementary, and Detective Raya Rightangle sat at her desk, staring at a pile of shape cards scattered everywhere. Circles, triangles, trapezoids, and rectangles were all mixed up in one big mess.
Raya sighed. “Something strange happened here,” she muttered, picking up a triangle card. “These shapes used to be sorted perfectly!”
Just then, her partner, Agent Leo Line, burst into the room holding a magnifying glass. “Detective Raya! I found this clue near the math board,” he said, holding up a sticky note. It read: “You’ll never sort these shapes again! Signed, The Shape Scrambler.”
Raya gasped. “The Shape Scrambler? That’s the sneakiest math trickster in the whole school!”
Leo nodded. “We have to figure out how to classify these shapes before the big Geometry Fair tomorrow, or the students won’t have their display.”
Raya began sorting the cards on the table. “Look at this one, Leo. Four sides, opposite sides equal… could it be a parallelogram?”
Leo leaned closer. “Maybe, but this one has four equal sides and four right angles, that’s a square!”
Raya smiled. “Good eye, partner. The key is in their properties, the sides, the angles, and the lines that stay parallel or meet.”
They both looked at the jumbled pile. Circles rolled across the desk, and triangles leaned on top of rectangles. It was going to take teamwork and sharp eyes to crack the case.
Raya grabbed her notebook. “Let’s write down what we know about each suspect… I mean, shape. Once we understand their properties, we’ll know exactly where each one belongs.”
Leo nodded eagerly. “And maybe, just maybe, we’ll find out who The Shape Scrambler really is.”
In each example, Estella AI generated content beyond the scope and purpose of our initial programming as a reading tutor for elementary math learners.
Methodological Note
This work follows an exploratory design inquiry approach. We did not begin with hypotheses to test; we began with a tool we had built and questions about what else it might do. Our method was iterative prompting: we posed challenges to Estella AI outside its original parameters, observed responses, and reflected on what those responses revealed about possibilities and limits of purpose-built AI in educational contexts. The examples above are representative, not exhaustive. They are offered as generative provocations for educators who may wish to experiment with their own AI configurations.
What We Learned
Several patterns emerged across our experiments:
- Specificity of prompt matters. The more precisely we articulated what we wanted (grade level, constraints, pedagogical goals), the more useful outputs became.
- AI can surprise within constraints. Estella AI introducing Bloom’s Taxonomy and UDL frameworks without prompting suggests that well-trained models can draw on pedagogical knowledge in generative ways.
- Output requires human judgment. Every response needed review. Historical accuracy had to be checked. Language had to be examined for appropriateness. AI proposes; educators decide.
- The tool reflects the questions we ask. Narrow questions generated narrow answers. Curiosity-oriented questions opened new directions and opportunities.
Implications for Practice and Questions for Further Inquiry
As we continued to experiment with Estella AI, a pattern quietly emerged: the most generative moments occurred not when the tool produced polished outputs, but when its responses prompted us to pause, question, and recalibrate our instructional assumptions. Because we understood the system’s design parameters, we could trace how prompt specificity shaped outcomes, how documentation transformed interaction into data, and how provisional outputs demanded professional judgment rather than compliance. This raised deeper questions alongside practical insights. What happens to teachers’ pedagogical knowledge when AI acts as a recurring curriculum co-designer? How might students experience learning differently when materials are co-created through human-AI collaboration rather than authored by a single source? If purpose-built educational AI can surface frameworks like Bloom’s Taxonomy (Krathwohl, 2002) or Universal Design for Learning (CAST, n.d.) without prompting, how might future systems make pedagogical reasoning more visible and contestable? These considerations suggest that experimentation with AI in education is not mainly about adoption or efficiency; it is about cultivating reflective practice, ethical awareness, and shared inquiry, where the most valuable outcomes emerge not from answers given, but from questions newly made possible.
References
CAST. (n.d.). UDL Guidelines. https://udlguidelines.cast.org/
Edwards, S. A., Maloy, R. W., & Trust, T. (2019). Kids have all the write stuff: Revised and updated for a digital age. University of Massachusetts Press.
Flesch, R. (1948). A new readability yardstick. Journal of Applied Psychology, 32(3), 221-233.
Gattupalli, S., Maloy, R. W., & Edwards, S. A. (2024, October). Fine-tuning a GenAI chatbot in the development of math modules for early elementary learners. ScholarWorks @ UMass Amherst. https://scholarworks.umass.edu/entities/publication/1160db5e-6948-4776-9448-e11ac79a5078
Krathwohl, D. R. (2002). A revision of Bloom’s taxonomy: An overview. Theory Into Practice, 41(4), 212-218.
Maloy, R. W., Xu, C., & Edwards, S. A. (2025a). An alphabet of AI words, from A to Z for elementary school teachers, students and families. ScholarWorks @ UMass Amherst. https://scholarworks.umass.edu/server/api/core/bitstreams/4717cd41-da6e-44e7-9c5f-cc801cf82566/content
Maloy, R. W., Xu, C., & Edwards, S. A. (2025b, Autumn). We used AI to build an alphabet of AI words: You can do this too! The Leaflet, 121(2), 13-24. NEATE (New England Association of Teachers of English).
OpenAI. (n.d.). Estella AI chatbot. https://chatgpt.com/g/g-zA144CUNe-estella-explainer-math-bot-2
About the Authors
Robert W. Maloy, Ed.D. is a Senior Lecturer in the UMass Amherst College of Education who coordinates history teacher education and co-directs the TEAMS Tutoring Project. His work focuses on interactive technologies and history education.
Sharon A. Edwards, Ed.D. is a Lecturer in the UMass Amherst College of Education with decades of classroom and teacher-education experience. Her work centers on inclusive, technology-supported learning.
Sai Gattupalli, Ph.D. is a learning scientist and Principal Scientist at the Society & AI Research Group. His work focuses on society-centered approaches to AI in education.
Cite this article
Maloy, R. W., Edwards, S. A., & Gattupalli, S. (2026). To boldly go where our purpose-built AI had not gone before. Society and AI. https://societyandai.org/research/to-boldly-go-where-our-purpose-built-ai-had-not-gone-before/
Write for Society & AI
We invite submissions from educators, researchers, policymakers, and practitioners exploring the intersection of artificial intelligence, education, and societal change. Society & AI publishes all work open access and free of cost in service of education and the public good. If you would like to contribute a guest article, send your proposal to the Editorial and Content Director at sai@societyandai.org.
