id: course-design
framework_id: 4d-framework
version: "1.0.0"
contributor: "Rick Dakan & Joseph Feller / Anthropic"
title: "AI-Augmented Course Design"
domain: education
dimensions:
  delegation:
    description: "AI can accelerate the scaffolding work of course design: generating draft learning objectives from a topic brief, suggesting module sequencing options, proposing assessment formats, brainstorming reading list candidates, and drafting rubric language. The instructor must own: the pedagogical strategy, the theoretical framework underlying the course, the sequencing rationale, and all decisions about what students will actually experience. Pedagogical authority cannot be delegated."
    example: A professor designing a new undergraduate ethics course asks AI to generate a draft list of possible weekly topics aligned with her stated course arc (from foundational theory to applied cases). She uses this list as a stimulus to compare against her own planned sequence, adopting two AI-suggested topics she had overlooked and discarding three that don't serve her theoretical framework.
    antipattern: Asking AI to design the full course — objectives, module structure, readings, assignments, assessments — and adopting the output with cosmetic changes, without grounding the design in a coherent pedagogical theory or ensuring it reflects the instructor's scholarly expertise.
  description:
    description: "Provide AI with detailed instructional design context: course level and credit hours, student profile and prerequisite knowledge, program-level learning outcomes the course must serve, your pedagogical philosophy, assessment philosophy, any accreditation or institutional constraints, and the thematic arc you want the course to trace. Precision in the brief yields useful scaffolding."
    example: "Prompt: 'Help me draft learning objectives for a 3-credit upper-division course on algorithmic bias. Students are CS seniors with strong technical backgrounds but limited social science exposure. Program outcome: graduates can evaluate the societal impact of technology systems. I want the course to move from conceptual foundations (weeks 1-4) to case analysis (weeks 5-10) to policy and design response (weeks 11-14). Use Bloom's Taxonomy verbs appropriate to the upper-division level.'"
    antipattern: "Prompting: 'Write learning objectives for a course on AI ethics.' Without specifying student level, program context, Bloom's taxonomy tier, or the course's theoretical arc, AI produces generic objectives that could apply to any course at any level and serve no specific program outcome."
  discernment:
    description: Evaluate AI-generated course design elements against pedagogical soundness, alignment to Bloom's Taxonomy, internal coherence, and fit with your students' actual preparation. Check that assessment types genuinely measure the stated learning objectives, that the workload is realistic, and that reading suggestions are current, credible, and accessible to your student population.
    example: An instructor reviews AI-generated weekly learning objectives and notices three of them are knowledge-level objectives (define, identify, list) in weeks designed for upper-division analysis. She revises them upward to analysis and evaluation verbs to match the cognitive demand appropriate for the course level.
    antipattern: Adopting AI-generated course syllabi and assessment designs without checking internal alignment — using multiple-choice exams to assess objectives that require critical analysis, or setting a reading workload that AI estimated without accounting for the actual length and density of the suggested texts.
  diligence:
    description: Verify the accuracy of all factual content AI contributes to course materials. Document the AI's role in course design per your institution's academic integrity and transparency policies. Ensure the final course design meets accreditation requirements, reflects current disciplinary knowledge, and embodies your own scholarly judgment and professional responsibility as the instructor of record.
    example: A faculty member building a new public health law course uses AI to draft a draft syllabus framework, then spends three hours reviewing it against her institution's course approval criteria, the program's accreditation standards, and current public health law scholarship — revising heavily before submission for curricular approval.
    antipattern: Submitting an AI-generated course proposal to a curriculum committee without personally verifying that the proposed learning objectives meet accreditation standards, that the reading list contains accurate and current citations, or that the assessment strategy is pedagogically defensible under institutional review.
score_hints:
  delegation: 0.20
  description: 0.30
  discernment: 0.25
  diligence: 0.25
tags:
  - course-design
  - curriculum
  - higher-education
  - instructional-design
reference: "https://aifluencyframework.org"

collaboration:
  pattern: linear_with_loops
  description: "Instructor delegates curriculum scaffolding, provides learning goals and constraints, evaluates AI-drafted structure, then approves — looping back to description if pedagogical alignment is off."
  sequence:
    - step: 1
      d: delegation
      label: "Agree on AI's curriculum design role"
      example_prompts:
        - speaker: human
          text: "Help me design a 10-week course on data literacy. You propose the weekly themes — I'll adjust."
        - speaker: ai
          text: "Should I sequence from concepts to tools, or mix both throughout?"
        - speaker: human
          text: "Concepts first, tools introduced in week 4 after foundations are set."
      triggers_next: "AI's design role and pedagogical sequencing approach agreed."
    - step: 2
      d: description
      label: "Provide learning outcomes and constraints"
      example_prompts:
        - speaker: human
          text: "Students are undergraduates with no statistics background. By week 10 they should be able to read and critique a published data study."
        - speaker: ai
          text: "Should I include assessment design or only the content structure?"
        - speaker: human
          text: "Include weekly assessments — short, formative, no exams."
      triggers_next: "AI has learner profile, outcomes, and assessment approach."
    - step: 3
      d: discernment
      label: "Evaluate curriculum structure"
      example_prompts:
        - speaker: human
          text: "Week 6 introduces regression too early — students won't have the algebra foundation yet."
        - speaker: ai
          text: "I can move regression to week 8 and use week 6 for data visualization instead."
        - speaker: human
          text: "Do that. Also add a prerequisite check activity in week 1."
      triggers_next: "Curriculum validated for pedagogical soundness."
      loop_back:
        to: description
        condition: "Curriculum consistently misaligns with stated learning outcomes or student level."
        reason: "Learning goals or student profile constraints need to be re-specified."
    - step: 4
      d: diligence
      label: "Approve and document"
      example_prompts:
        - speaker: human
          text: "Department curriculum committee reviews and approves the final structure."
        - speaker: human
          text: "Filing AI-assisted design notes in the course development record."
      triggers_next: "Curriculum approved. Cycle restarts when course is revised."
      can_restart: true
  transitions:
    - from: delegation
      to: description
      trigger: "Design role and sequencing approach agreed."
    - from: description
      to: discernment
      trigger: "AI delivers curriculum draft."
    - from: discernment
      to: diligence
      trigger: "Structure validated."
    - from: discernment
      to: description
      trigger: "Persistent misalignment — re-specify goals."
      is_loop_back: true
    - from: diligence
      to: delegation
      trigger: "Course revision cycle — restart."
      is_cycle_restart: true