Zelma, a GPT‑4 powered research assistant, is making education data accessible to parents, teachers, school administrators, and policymakers across the United States.
The problem they’re solving? While standardized tests are issued to every student in grades 3–8 in the U.S., data about how students perform remains largely untapped and underutilized, scattered across different sources and formats. Test data offers powerful insights into how well students are learning in English language arts (ELA) and math, across district and demographic group levels. But crucial insights that could shape the future of education are effectively beyond the reach of most parents, journalists, educators, and policymakers.
Recognizing this gap, Dr. Emily Oster, a Brown economist and author, set out to change the narrative. “Zelma makes it possible for parents and policymakers alike to use plain language to get instant, tailored educational insights on what matters most to them,” Dr. Oster explained. How did Zelma accomplish this? Dr. Oster’s team of student researchers at Brown University spent a year gathering the data and meticulously cleaning it into one uniform format. Zelma then worked with Novy(opens in a new window) to bring the data to life using OpenAI’s API.
Novy leveraged function calling(opens in a new window) to tell GPT‑4 which visuals and fields to choose from in displaying the data. For Zelma’s "Ask a Question" view, they fine-tuned(opens in a new window) a model to create a data-aware type-ahead that suggests questions with available data. And they embedded and stored known-good example graphs in a vector database to improve accuracy on difficult edge cases.
The biggest challenge was trying to predict how people would phrase their questions, and keeping the prompts within Zelma’s scope of knowledge. “We addressed this through intentional design choices in Zelma’s user experience that nudge people to ask questions Zelma can answer,” Dr. Oster explained. Key features include:
Now, you can instantly shortlist the top 5 highest performing non-charter school districts in math in Minnesota,(opens in a new window) and find that they all score around a 77 percent proficiency rate. And a simple prompt can surface racial disparities in ELA achievement in California over time,(opens in a new window) while also pointing out an assessment change in 2015 that makes test results from 2015 onward not comparable with prior years.
Top 5 Math Proficiency Rates in Non-Charter Districts in Minnesota (2023)
ELA Scores Over Time in California by Race/Ethnicity
This means that school board members can use Zelma to quickly generate data visualizations during meetings, enabling data-informed decision-making. Parents can compare historical test performances of nearby school districts to make educated decisions on where to raise their children. A Governor’s Chief of Staff can reference Zelma to identify the best performing schools in their state and see how much test scores have changed over time.
> “Zelma offers K-12 superintendents an intuitive, conversational platform to instantly visualize student learning data—views that have historically taken district leadership teams hours or even days to generate. By democratizing this data, Zelma is making it easier for adults in the system to have concrete conversations about student outcomes and direct public attention to student well-being.”
Caitlin Sullivan, Co-founder & Executive Director of Leading Now
From scattered data portals and spreadsheets to a user-friendly website, Zelma transforms disparate data into meaningful analyses. Zelma joins other use cases supporting teachers in the classroom and helping students learn at their own pace in showing ways that generative AI can enhance our education system. Zelma also provides a powerful example of how OpenAI’s tools and products can be used to make data more useful and accessible to all.
## Interested in learning more about ChatGPT for business?
## Related customer stories
Klarna's AI assistant does the work of 700 full-time agents ChatGPT Apr 5, 2024
Customizing models for legal professionals API Apr 2, 2024
Reducing health insurance costs and improving care API Apr 1, 2024
Our Research * Research Index * Research Overview * Research Residency * OpenAI for Science * Economic Research
Latest Advancements * GPT-5.3 Instant * GPT-5.3-Codex * GPT-5 * Codex
Safety * Safety Approach * Security & Privacy * Trust & Transparency
ChatGPT * Explore ChatGPT(opens in a new window) * Business * Enterprise * Education * Pricing(opens in a new window) * Download(opens in a new window)
Sora * Sora Overview * Features * Pricing * Sora log in(opens in a new window)
API Platform * Platform Overview * Pricing * API log in(opens in a new window) * Documentation(opens in a new window) * Developer Forum(opens in a new window)
For Business * Business Overview * Solutions * Contact Sales
Company * About Us * Our Charter * Foundation * Careers * Brand
Support * Help Center(opens in a new window)
More * News * Stories * Livestreams * Podcast * RSS
Terms & Policies * Terms of Use * Privacy Policy * Other Policies
(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)
OpenAI © 2015–2026 Manage Cookies
English United States
