References
This chapter provides curated references for readers who want to explore intelligent textbooks, MicroSims, and AI-assisted education in greater depth. References are organized by type: peer-reviewed papers, online textbooks, and blog articles.
Journal Papers and Preprints
Deploying AI for Signal Processing Education
Authors: Jarvis Haupt, Qin Lu, Yanning Shen, Jia Chen, Yue Dong, Dan McCreary, Mehmet Akçakaya, Georgios B. Giannakis
Date: September 10, 2025
URL: https://arxiv.org/abs/2509.08950
This paper examines the challenges and opportunities of deploying AI in signal processing education. The authors explore how generative AI can create personalized learning experiences, generate practice problems, and provide adaptive feedback. The paper addresses concerns about academic integrity while highlighting the potential for AI to democratize access to high-quality STEM education.
MicroSims: A Framework for AI-Generated Educational Simulations
Authors: Valerie Lockhart, Dan McCreary, Troy A. Peterson
Date: November 25, 2025
URL: https://arxiv.org/abs/2511.19864
This paper introduces the MicroSim framework for creating small, focused educational simulations using generative AI. The framework emphasizes simplicity, universal embedding via iframes, and adaptive learning support. The paper presents case studies demonstrating how MicroSims can be generated from natural language descriptions and embedded in learning management systems.
A Five-Level Classification Framework for Intelligent Textbooks
Author: Dan McCreary
Date: November 30, 2025
URL: https://osf.io/preprints/edarxiv/sh2yu_v1
This preprint proposes a classification framework for intelligent textbooks inspired by the SAE J3016 standard for autonomous vehicles. The five levels range from static content (Level 1) through interactive simulations (Level 2), adaptive learning (Level 3), chatbot integration (Level 4), to fully autonomous AI tutoring (Level 5). The framework helps educators and developers set appropriate goals for their projects.
Online Intelligent Textbooks
Intelligent Textbooks
URL: https://dmccreary.github.io/intelligent-textbooks/
The companion website to this book, containing interactive examples, MicroSim demonstrations, and supplementary materials. The site itself serves as a Level 2 intelligent textbook, demonstrating the concepts discussed in these chapters.
Intelligent Textbook Case Studies
URL: https://dmccreary.github.io/intelligent-textbooks/case-studies/
A catalog of intelligent textbooks generated using the methods described in this book. As of February 2026, the catalog contains 64 textbooks spanning subjects from geometry and electronics to economics and machine learning. Each case study includes metrics on content volume, MicroSim count, and feature implementation.
Claude Skills for Generating Intelligent Textbooks
URL: https://dmccreary.github.io/claude-skills/
Documentation for the AI skills (structured prompts and workflows) used to generate intelligent textbook components. Skills include learning graph generation, glossary creation, quiz generation, and MicroSim development. The site demonstrates how skills enable consistent, repeatable content generation.
MicroSim Faceted Search
MicroSim Search - there are about 830 MicroSims and we are getting about 30 new MicroSims each week.
MicroSim Similarity Map
MicroSim Similarity Map This is a 2-dimensional layout of 800+ MicroSims where each dot is a MicroSim you can hover over. When you hover over the dot you can see details about the MicroSim. The map is created using embeddings so that MicroSims that are similar are near each other in the layout. The color of the dot also categorizes the MicroSim by a subject. You can click the "Uncheck All" button on the right and then just turn on one or more subjects. Note that this is a semantic embedding, not a pedagogical or technical embedding. It just compares the entire metadata.json file as a block of text.
MicroSims for Education
URL: https://dmccreary.github.io/microsims/
A collection of educational MicroSims with source code and documentation. The site includes templates, design patterns, and best practices for creating effective simulations. MicroSims are organized by subject area and Bloom's Taxonomy level.
MicroSim Search
URL: https://dmccreary.github.io/search-microsims/
A faceted search interface for discovering MicroSims across multiple intelligent textbooks. Users can filter by subject area, concept, interaction type, and complexity level. The search demonstrates how proper metadata enables discoverability of educational resources.
Learning Graphs
URL: https://dmccreary.github.io/learning-graphs/
Documentation and tools for creating and visualizing learning graphs—the directed acyclic graphs that represent concept dependencies. The site includes interactive graph viewers, validation tools, and guidance on generating graphs from course descriptions.
Blog Articles
Keeping Intelligent Textbook Generation Agents Portable
Author: Dan McCreary
This article argues that the learning graph—not the language model—should be the source of truth for intelligent textbook generation. By keeping content generation agents portable across AI frameworks, authors avoid vendor lock-in and can take advantage of improving models over time.
Five Levels of Intelligent Textbooks
Author: Dan McCreary
Date: November 19, 2024
URL: https://medium.com/@dmccreary/five-levels-of-intelligent-textbooks-b81a4c1525a0
The original blog post introducing the five-level classification framework. This article clarifies the crucial distinction between Level 2 (interactive) and Level 3 (personalized) textbooks—the privacy threshold where individual learner tracking becomes necessary.
Using GenAI to Create Learning Graphs
Author: Dan McCreary
Date: October 16, 2024
URL: https://medium.com/@dmccreary/using-genai-to-create-learning-graphs-fbfe8bcf1eb1
A practical guide to generating learning graphs using generative AI. The article covers prompt engineering strategies, validation techniques, and how learning graphs enable hyper-personalized lesson plans.
GenAI is Hyper-Personalizing Education
Author: Dan McCreary
Date: November 22, 2023
URL: https://medium.com/the-modern-scientist/genai-is-hyper-personalizing-education-e28019027944
An exploration of how generative AI enables teachers to create customized lesson plans and MicroSims for individual students. The article discusses the shift from one-size-fits-all education to personalized learning at scale.
MicroSims for Education: An Interview
Author: Dan McCreary
Date: November 4, 2023
URL: https://medium.com/@dmccreary/micro-simulations-for-education-6989eae8d85d
An interview with Valerie Lockhart of Code Savvy discussing the educational philosophy behind MicroSims. The conversation covers why simplicity matters, how students learn through interaction, and the role of AI in simulation creation.
ChatGPT Brings Us Closer to the Diamond Age
Author: Dan McCreary
Date: January 30, 2023
URL: https://dmccreary.medium.com/chatgpt-brings-us-closer-to-the-diamond-age-b1469bee4949
A reflection on how ChatGPT and similar models bring us closer to the vision of personalized AI tutors described in Neal Stephenson's novel "The Diamond Age." The article considers what educational technology might look like as AI capabilities continue to improve.
Grading GPT-3 for STEM Lesson Plan Generation
Author: Dan McCreary
Date: January 25, 2021
URL: https://medium.com/data-science/grading-gpt-3-for-stem-lesson-plan-content-generation-c8d9d1f59806
An early evaluation of GPT-3's ability to generate STEM lesson plans. The article assesses strengths and weaknesses, providing a baseline for measuring how much AI content generation has improved since 2021.
Using AI to Generate Detailed Lesson Plans
Author: Dan McCreary
Date: September 12, 2020
URL: https://dmccreary.medium.com/using-al-to-generate-detailed-lesson-plans-29a5af200a6a
One of the earliest explorations of using AI for educational content generation. Written before the transformer revolution, this article documents initial experiments and sets context for how rapidly the field has evolved.
Lost in Knowledge Space
Author: Dan McCreary
Date: October 12, 2019
URL: https://dmccreary.medium.com/lost-in-knowledge-space-14be123ea083
An introduction to knowledge spaces—mathematical structures representing a learner's position in a graph of learning concepts. This foundational article explains the theory behind adaptive learning systems and how concept graphs enable personalized education.