About INTERLAZA
Building evidence-based adaptive learning tools at the intersection of behavioral science and technology.
About us
Built on rigorous science, reviewed by practitioners
INTERLAZA was conceived at the intersection of behavioral science and software engineering, designed to bring decades of peer-reviewed research into a practical clinical tool. Every algorithm, training paradigm, and mastery criterion in the platform traces directly back to published literature.
The platform's foundations rest on the pioneering work of researchers who dedicated their careers to understanding how children learn symbolic relationships. The methodology is grounded in the peer-reviewed work of Julio Varela, Murray Sidman, and other foundational ABA researchers.
INTERLAZA is the first platform to combine match-to-sample training, Bayesian Knowledge Tracing, and Relational Frame Theory in a single adaptive tool — making 55 years of behavioral science accessible in a tablet-friendly interface that instructors can use in every session.
Murray Sidman
Stimulus Equivalence
The foundational framework for understanding how children form symbolic categories and derive new relations without explicit teaching.
Julio Varela
Transfer Theory
A 15-level paradigm for transferring stimulus control across identity, non-identical, symbolic, and auditory modalities.
Hayes, Barnes-Holmes & Roche
Relational Frame Theory
The theoretical basis for contextual control exercises, enabling training of coordination, distinction, opposition, and hierarchy relations.
Mission
Evidence-based adaptive learning tools for every learner
The most effective behavioral learning techniques have existed in the scientific literature for decades. The gap is not knowledge — it is access. Sophisticated methods like stimulus equivalence training, Varela transfer probes, and BKT-driven adaptive difficulty have been confined to research labs and specialist clinicians with rare expertise.
INTERLAZA's mission is to close that gap: making evidence-based learning tools accessible to instructors and families, regardless of resources, institution, or geography. Because the engine adapts to the learner, the platform serves children from 18 months and up — typically developing learners and children with learning disabilities alike. When the algorithm does the heavy lifting, the adult can focus on the child.
Access is also about ecosystem. The Community Store lets instructors publish the modules they build and clone those shared by other professionals, researchers, and parents — so a good training sequence designed in one clinic can reach dozens of children in another. Every shared module passes through a moderation queue and shows its author and clone count, so practitioners can judge trust before adopting it.