A teacher-first approach to test preparation
Dr. Mienie Roberts is a mathematics professor whose classroom practice sits at the intersection of advanced mathematics and the learning sciences. Her university teaching has focused on helping pre-service and early-career educators move from procedural fluency to conceptual mastery — the same transition the TExES Mathematics 7-12 (235) examination was designed to assess.
QuantegyAI grew out of that work. After watching capable, mathematically prepared candidates struggle with an exam that rewards adaptive diagnosis and misconception repair rather than rote review, Dr. Roberts set out to build a preparation platform that mirrors the way mathematics is actually learned: one targeted problem at a time, with immediate feedback, and with a deliberate loop back to the missing prerequisite whenever a gap is detected.
Pedagogy, not product marketing
Every design decision in the platform is anchored in the adaptive-learning and intelligent-tutoring literature. The engine uses a three-parameter logistic Item Response Theory model to estimate each learner's ability after every response, selecting the next item from the region of the test blueprint where growth is most likely. When a misconception is inferred, the system opens a short remediation loop on the missing prerequisite and then returns the learner to the original item to verify mastery — a structure supported by the tutoring-effectiveness literature.
A reviewer's perspective on instructional materials
Dr. Roberts currently serves as an active reviewer under the Texas Instructional Materials Review and Approval (IMRA) process, established by House Bill 1605. In that role she evaluates K–12 mathematics materials against the Texas Essential Knowledge and Skills (TEKS), the English Language Proficiency Standards (ELPS), and state-defined suitability and quality rubrics. That reviewer lens — alignment, quality, suitability, and factual accuracy — is applied to every item in the QuantegyAI bank.
Although QuantegyAI is a teacher-certification preparation product rather than a K–12 classroom resource (and therefore not itself an IMRA-eligible submission), the same standards of evidence, alignment, and pedagogical rigor inform its construction.
Adaptive by design
Difficulty, discrimination, and guessing parameters are calibrated per item; the next question is always chosen at the edge of the learner's current ability.
Misconception repair
When a wrong answer signals a specific prerequisite gap, a short remediation loop is triggered before the learner continues.
Evidence-aligned
Item design, review, and reporting draw on the intelligent-tutoring literature and the published TEA framework for the TExES Mathematics 7-12 (235).
Continuing Professional Education
Certificate of Continuing Professional Education issued through the Texas Instructional Materials Review and Approval (IMRA) reviewer training program.
Independence statement
QuantegyAI is an independent preparation platform and is not affiliated with, endorsed by, or sponsored by the Texas Education Agency (TEA) or the State Board of Education (SBOE). "TExES" is a trademark of the Texas Education Agency. Participation in the IMRA reviewer program does not confer any endorsement of products outside the reviewer's official duties.