iMATE Lesson Planner: Instructional Design and AI-Assisted Lesson Planning

Project Type: AI-Enhanced Instructional Design | Learning Experience Design | Educational Software Development

Project Status: Completed Standalone Assignment Prototype — Further Integration and Evaluation Planned

iMATE Lesson Planner: Instructional Design and AI-Assisted Lesson Planning

iMATE Lesson Planner is an AI-assisted instructional planning application designed to help educators develop structured, evidence-informed lesson materials while retaining control over instructional decisions.

The project demonstrates how established instructional design frameworks and generative artificial intelligence can be integrated into a working educational technology prototype.

Rather than treating AI-generated lesson plans as finished instructional products, the application positions the teacher as the primary decision-maker responsible for reviewing, adapting, and implementing generated materials.

Effective lesson planning requires teachers to coordinate multiple instructional elements, including curriculum expectations, learner characteristics, prior knowledge, learning objectives, teaching activities, assessment strategies, available resources, and instructional time.

Maintaining alignment across these elements can be challenging, particularly when teachers must prepare differentiated materials, develop assessment activities, or adapt instruction to different lesson durations.

Although generative AI can produce lesson plans and instructional materials, the quality and usefulness of those outputs depend on how instructional requirements are specified, organized, and evaluated.

An automatically generated lesson plan may contain appropriate activities without adequately aligning them with learning objectives, available instructional time, or assessment expectations. AI-generated resources may also contain conceptual or numerical inaccuracies that require professional review.

The central design challenge was therefore to develop an AI-assisted planning tool that organizes essential instructional requirements into coherent lesson drafts without replacing teachers’ professional judgment.

I developed iMATE Lesson Planner in response to this challenge, drawing on my experience in classroom teaching, instructional design, and educational technology development.

The project also extends ideas from my earlier learning theories virtual library developed for preservice teachers, translating instructional design guidance into a functional planning application.

iMATE Lesson Planner is a web-based application that assists educators in creating organized instructional resources through a teacher-directed AI generation process.

Teachers provide planning information, specify instructional preferences, and determine whether generated content should rely on AI-generated material, uploaded instructional sources, or a combination of both.

The application generates three complementary instructional resources:

Teacher Lesson Plan

A structured instructional plan containing lesson objectives, instructional sequences, activities, and assessment considerations.

Student Notes

Learner-facing materials intended to support conceptual understanding, guided practice, and engagement with the selected topic.

Teacher Answer Key

Supporting materials for educators, including answers and worked solutions where appropriate.

Core Functionalities

  • AI-assisted generation of lesson materials based on teacher-provided requirements.

  • Selection between focused lessons and broader topic overviews.

  • Support for different instructional durations.

  • Upload of existing instructional resources to inform generated content.

  • Three source-generation options: independent AI generation, uploaded-source use, or combined source use.

  • Separate teacher lesson plans, student notes, and teacher answer keys.

  • Editable lesson materials and browser-based printing or export.

  • Access-code protection for demonstration users.

These functionalities are intended to reduce the need for teachers to begin every planning task from an empty document while preserving opportunities for reviewing and revising the instructional materials.

The standalone application is also intended for future integration into the broader iMATE educational platform.

The overarching objective was to design and develop an AI-assisted lesson-planning prototype that applies established instructional design principles to the generation of teacher-reviewed instructional resources.

The specific objectives were to:

  1. Integrate instructional design principles: Apply ADDIE, motivational design, instructional sequencing, and objective-writing guidance to the planning workflow.

  2. Support instructional alignment: Encourage coherent relationships among learning objectives, instructional activities, assessment strategies, and available time.

  3. Preserve teacher agency: Allow educators to specify instructional preferences, provide original materials, and review generated outputs before classroom implementation.

  4. Generate complementary learning resources: Produce separate teacher lesson plans, student notes, and teacher answer keys.

  5. Support source-informed planning: Enable the use of uploaded instructional documents alongside AI-generated content.

  6. Develop and refine a functional prototype: Implement an accessible web-based workflow through iterative design, functional testing, and revision.

  7. Investigate practical usability: Examine whether the prototype can generate materials suitable for further adaptation to authentic lesson-planning needs.

These were design and development objectives. The project did not seek to establish causal effects on student achievement or quantitatively measure changes in teacher workload.

The development process combined instructional design frameworks, AI-assisted programming, iterative prototyping, and reflective evaluation.

5.1 Instructional Design Framework

I used the ADDIE framework—Analysis, Design, Development, Implementation, and Evaluation—to organize the project.

During analysis, I considered the instructional requirements teachers routinely coordinate when preparing lessons, including learning objectives, content, activities, assessment, learner support, and time constraints.

During design, I translated these requirements into application inputs, generation instructions, and expected output structures.

Development involved constructing the application, integrating AI functionality, and refining the presentation of generated instructional materials.

Implementation involved deploying the prototype and using it for demonstration and testing. It did not constitute implementation of the generated lessons in a classroom study.

Evaluation focused on reviewing generated materials, identifying functional and instructional limitations, and making revisions informed by testing.

I also used a design-thinking approach, emphasizing iterative problem-solving, testing, and refinement based on identified user needs.

5.2 Integration of Learning Theories and Instructional Principles

The application was informed by established learning design principles.

Keller’s ARCS Motivational Design Model

The dimensions of attention, relevance, confidence, and satisfaction informed the instructional guidance used to structure engaging lesson experiences.

Gagné’s Instructional Events

Gagné’s instructional events informed lesson sequencing, including attention, activation of prior knowledge, guided learning, practice, feedback, and assessment.

ABCD and SMART Learning Objectives

The application incorporated guidance for writing instructional objectives using the ABCD framework:

  • Audience: Who is expected to learn?

  • Behavior: What observable performance is expected?

  • Condition: Under what circumstances will the performance occur?

  • Degree: What standard of performance is required?

SMART criteria—specific, measurable, achievable, relevant, and time-bound—provided additional guidance for objective clarity and practical implementation.

Additional Learning Design Principles

Drawing on my earlier learning theories virtual library, the planner incorporated guidance related to prior knowledge, content chunking, modeling, scaffolding, practice, feedback, and reflection.

Together, these principles informed the instructions used to generate coherent instructional sequences rather than unrelated lists of classroom activities.

5.3 Iterative Prototype Development

Four main development versions document the project’s progression.

Version 0.1 — Initial Structure and Interface

Established the application’s initial interface, planning workflow, and expected response structure.

This version did not include live AI integration.

Version 0.2 — AI Integration

Connected the application to the OpenAI API, enabling substantive AI-generated instructional content.

This represented the transition from a structural prototype to a functional AI-assisted lesson-planning application.

Version 0.3 — Instructional Resource Differentiation

Introduced separate outputs for teacher lesson plans, student notes, and teacher answer keys.

This version also strengthened guidance for instructional objectives, assessment alignment, and the organization of learning materials.

Version 0.4 — Source Integration and Teacher Choice

Introduced document uploads and additional teacher-directed planning options.

Teachers could select focused lessons or broader overviews and choose among independent AI generation, uploaded-source use, or a combined approach.

This refinement provided greater control over the source and scope of generated instructional content.

5.4 Technical Development and Deployment

I developed the standalone prototype using AI-assisted coding and iterative troubleshooting.

I provided the application requirements, instructional resources, test scenarios, design feedback, and revision priorities. ChatGPT supported coding, troubleshooting, and development refinement.

The application connects to the OpenAI API through a server hosted on Render, while its source code is maintained in a private GitHub repository.

An application access code allows reviewers to explore the prototype without being given the OpenAI API secret.

Subsequent refinements strengthened the application’s instructions to check calculations and mathematical responses before presenting generated material.

This verification-oriented design step is intended to reduce errors, but it does not guarantee numerical or conceptual accuracy.

5.5 Functional Testing and Refinement

Functional testing involved generating and reviewing instructional materials for Heat and Simple Machines, using lesson durations of 50 and 120 minutes.

The Heat tests used AI-generated content without uploaded instructional sources. The Simple Machines tests incorporated an existing reference document.

These scenarios allowed me to examine content organization, instructional alignment, the handling of different lesson durations, and the influence of uploaded instructional resources.

One useful design finding was the importance of distinguishing lessons emphasizing conceptual understanding from those emphasizing numerical problem-solving. This distinction informed refinements to teacher-controlled lesson focus.

I also demonstrated the application to a professional colleague who used it to generate and download a mathematics lesson plan.

This provided an additional example of use beyond my physics testing. It was not a formal usability evaluation or independent validation of instructional quality.

5.6 Observations, Challenges, and Lessons Learned

The prototype generated lesson-planning resources that I found useful for my immediate instructional planning needs.

However, the review process also highlighted the importance of verifying both AI-generated content and uploaded instructional sources.

In particular, testing identified occasional numerical inconsistencies in an uploaded reference document.

This observation reinforced a critical design principle: Providing an AI application with instructional source materials does not eliminate the possibility of inaccuracies, because the sources themselves may contain errors.

Consequently, the application is designed to support teacher decision-making rather than replace professional review.

The testing activities did not measure student learning outcomes, actual classroom pacing, or reductions in teacher preparation time.

The development process integrated instructional design methods, generative AI, web application development, and cloud deployment.

Tool or FrameworkApplication
ChatGPTAI-assisted coding, troubleshooting, prototyping, and revision
OpenAI APIAI-assisted lesson-content generation
RenderServer hosting and application deployment
GitHubPrivate source-code repository and development management
ADDIEOrganization of the instructional design and development process
Design ThinkingIterative refinement and problem-solving
Keller’s ARCS ModelMotivational design guidance
Gagné’s Instructional EventsInstructional sequencing
ABCD and SMARTInstructional objective-writing guidance

My responsibility was to define the educational requirements, direct the development process, review generated materials, identify problems, and determine the instructional and functional revisions required.

iMATE Lesson Planner is designed to help educators transform instructional requirements into organized, editable lesson resources while maintaining professional control over planning decisions.

Its value lies in combining the generative capabilities of AI with established instructional design guidance.

For Teachers

The application provides structured starting points for lesson planning, opportunities to reuse existing instructional materials, and separate resources for instructional delivery and student support.

For Preservice Teachers

The design offers a structured example of how learning objectives, instructional activities, motivational principles, and assessment considerations can be connected during lesson planning.

For Instructional Designers

The project illustrates how instructional design models and learning principles can be translated into the requirements and workflows of an AI-supported educational application.

For Educational Technology Development

The prototype demonstrates one approach to developing teacher-directed AI tools that preserve human review and integrate existing instructional resources into content generation.

Central Value Proposition

iMATE Lesson Planner combines AI-assisted content generation with evidence-informed instructional design to support the development of coherent, editable, and teacher-reviewed learning resources.

These are intended or observed design benefits. Broader claims about efficiency, effectiveness, or learning outcomes require additional evaluation.

The project’s main contribution is the integration of instructional design guidance and teacher-controlled AI generation within a single planning workflow.

Several design characteristics distinguish its approach.

Instructional Design Embedded in AI Generation

Rather than relying exclusively on open-ended prompts, the application incorporates structured guidance informed by ADDIE, ARCS, Gagné’s instructional events, and objective-writing frameworks.

Multiple Complementary Instructional Outputs

The system separates teacher lesson plans, student notes, and teacher answer keys, recognizing that different instructional audiences require different forms of information.

Teacher-Controlled Source Selection

Teachers can determine whether generated materials should draw on uploaded documents, independent AI generation, or a combination of the two.

Flexible Lesson Scope and Duration

The design supports different instructional durations and allows teachers to emphasize focused instruction or broader topical coverage.

Integration of Conceptual and Numerical Learning Needs

Testing with physics materials informed refinements intended to help teachers distinguish conceptual explanations from numerical problem-solving requirements.

Human Oversight and Verification

The application preserves opportunities for teachers to inspect, edit, and verify generated instructional resources.

These features describe the project’s design approach and should not be interpreted as evidence that it outperforms commercially available AI lesson-planning systems.

iMATE Lesson Planner demonstrates my ability to translate instructional design knowledge into a functioning AI-assisted educational technology prototype.

The project reflects several professional competencies.

Instructional Design and Learning Theory Application

Applying ADDIE, ARCS, Gagné’s instructional events, and objective-writing frameworks to an authentic instructional planning challenge.

Educational Problem Analysis

Identifying the relationships among curriculum requirements, instructional activities, available time, and assessment.

AI-Assisted Software Development

Using generative AI to support application development while retaining responsibility for requirements, design decisions, testing, and revisions.

Instructional Alignment

Designing generation workflows intended to connect objectives, learning activities, assessment, and supporting resources.

Iterative Design and Evaluation

Developing four prototype versions, testing instructional scenarios, and refining application functionality based on observations.

Technical Integration and Deployment

Integrating an external AI API, deploying a working web application, and maintaining source code through a private repository.

Critical Evaluation of AI-Generated Content

Reviewing generated materials for instructional and mathematical accuracy and identifying limitations associated with both AI outputs and uploaded reference materials.

My Contribution

I served as the individual instructional designer and AI-assisted developer.

I initiated the project, established its instructional and functional requirements, provided test scenarios and source materials, directed development revisions, evaluated generated content, and deployed the application for demonstration.

The project connects my background in classroom teaching and instructional design with my continuing development in AI systems and educational software.

It also provides a foundation for future integration with the broader iMATE learning platform.

Live Project Demonstration

iMATE Lesson Planner

https://imate-lesson-planner.onrender.com/

Reviewer access is available through a separately provided application access code.

Supporting Development

Scholarly and Technical References

The instructional design section draws on ADDIE, Keller’s ARCS motivational design model, Gagné’s instructional events, and ABCD and SMART approaches to objective writing.

Current Status and Limitations

The standalone assignment prototype is complete and available for demonstration.

Its current functionality includes AI-assisted lesson generation, teacher-directed source selection, differentiated instructional outputs, and browser-based export.

Further refinement and broader evaluation are planned as part of its intended integration into iMATE.

The testing completed to date supports a description of the application as a functional instructional planning prototype. It does not establish improvements in student achievement, teacher workload, lesson quality across subjects, or classroom implementation outcomes.