Built on the science of how we learn

Bloom is built on decades of research in learning science, digital learning, and cognitive psychology.

Our Approach

Core principles

We've built Bloom using what scientists know about how people learn best. These are some of the principles guiding us today, and we adapt as new research emerges.

Start from what the learner already believes

New knowledge is built on prior knowledge — including misconceptions.

Source: National Research Council, How People Learn (2000)

How Bloom applies this

•Elicits first. Bloom prompts an attempt or explanation before teaching, so support targets the learner's current thinking.

•Diagnoses misconceptions. Bloom uses errors and explanations to distinguish gaps in knowledge from incorrect underlying ideas.

•Adapts over time. Bloom maintains a running profile of what a student has demonstrated (e.g., recurring errors, successful strategies) to adjust scaffolding and review.

Understanding over answers

Getting the answer right is only part of the story. To develop competence, students must have a deep foundation of factual knowledge, plus an understanding of the concepts and principles that connect them.

Source: Chi, Feltovich, & Glaser (1981); National Research Council (2000)

How Bloom applies this

•Probes principles, not just outputs. Asks "why does this work?" and "when would this apply?" to connect facts to underlying principles.

•Checks for transfer. When a student succeeds, Bloom may vary the surface details or ask a "what changes if..." question to test whether learning transfers.

Productive struggle & scaffolding

Learning improves when students do effortful thinking in their zone of proximal development. Bloom is designed to preserve productive struggle while preventing frustration.

Source: Wood, Bruner, & Ross (1976); Bjork & Bjork (2011)

How Bloom applies this

•Defaults to hints over solutions. Bloom typically starts with prompts and hinting that keeps the student doing the thinking, rather than jumping straight to a full worked answer.

•Increases support when stuck. When responses and time-on-step suggest genuine impasse, Bloom increases scaffolding (more specific hints, step decomposition, targeted explanation) so difficulty stays manageable.

Metacognitive skills & self-regulation

Learning improves when students monitor what they understand, notice uncertainty, and adjust strategy

Source: Chi et al. (1994); Koriat & Bjork (2005); Zimmerman (2002)

How Bloom applies this

•Prompts self-explanation. Bloom asks students to explain their reasoning, which reveals gaps and solidifies understanding.

•Checks confidence. By asking students to assess their own certainty, Bloom helps them detect the "illusion of competence."

Manage cognitive load

Working memory is limited. Design should protect attention and allocate effort toward the learning goal.

Source: Sweller (1988)

How Bloom applies this

•Chunks information. Bloom breaks complex topics into manageable steps.

•Keeps explanations targeted. Bloom avoids long, multi-topic explanations and instead gives short feedback tied to the learner’s current step or misconception.

Selected References

Bjork, E. L., & Bjork, R. A. (2011). Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning. In M. A. Gernsbacher, R. W. Pew, L. M. Hough, & J. R. Pomerantz (Eds.), Psychology and the real world: Essays illustrating fundamental contributions to society (pp. 56-64). Worth Publishers.

Chi, M. T. H., Feltovich, P. J., & Glaser, R. (1981). Categorization and representation of physics problems by experts and novices. Cognitive Science, 5(2), 121-152.

Chi, M. T. H., de Leeuw, N., Chiu, M. H., & LaVancher, C. (1994). Eliciting self-explanations improves understanding. Cognitive Science, 18(3), 439-477.

Koriat, A., & Bjork, R. A. (2005). Illusions of competence in monitoring one's knowledge during study. Journal of Experimental Psychology: Learning, Memory, and Cognition, 31(2), 187-194.

Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory Into Practice, 41(2), 64-70.

National Research Council. (2000). How people learn: Brain, mind, experience, and school: Expanded edition (J. D. Bransford, A. L. Brown, & R. R. Cocking, Eds.). National Academy Press.

Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257-285.

Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes (M. Cole, V. John-Steiner, S. Scribner, & E. Souberman, Eds.). Harvard University Press.

Featured Research Partnership

SPARK: Sovereign Pedagogical AI for Reinforcing Knowledge

In partnership with UNSW Sydney, we've secured a $480,000 Ignite grant from Australia's Economic Accelerator to develop AI that genuinely helps students learn.

Read the full announcement

A$480,000 Grant

Learn more about our research