What is this course about?
Most institutions already hold the material for a course in documents nobody has organized into one. This course shows how to have an AI agent draft outcomes, an outline and assessments from those documents, trace every module back to a source passage, clear the rights questions first, and keep a faculty review gate before anything publishes.
Who is this course for?
- Instructional designers and teaching and learning center staff
- Faculty converting existing material into online courses
- Continuing and professional education directors
- Academic technology staff who run the LMS
What do I need before starting?
- Bring a folder of real source documents for one course or training program
- Access to your institution's LMS or a sandbox course shell
What will I be able to do afterwards?
- Assess whether a document set is ready to become a course
- Identify the rights questions to clear with counsel before material reaches an AI
- Draft measurable outcomes and an aligned module outline from source documents
- Generate assessments that test each outcome rather than recall of the text
- Run a faculty review gate that keeps provenance for every generated passage
- Check the generated course against WCAG 2.2 and Universal Design for Learning
What does each module cover?
What makes a document set ready to become a course?
45 minInventory the material, find what is current, and name the gaps a generator will otherwise fill with invention.
Objectives
- Inventory source documents by type and date
- Flag superseded and contradictory material
- Identify the topics no document covers
Topics
Activity. Inventory your own folder and mark every document current, superseded or contested.
Who owns the material you are about to give an AI?
45 minCopyright, licences and third-party content in course material, framed as questions for counsel rather than answers.
Objectives
- Separate institution-owned from licensed and third-party material
- List the questions counsel must answer before ingestion
- Record the rights status of every source
Topics
Activity. Build a rights register for your folder and mark what needs counsel's review.
How do you turn documents into measurable learning outcomes?
45 minOutcomes come first; the generator drafts candidates, and faculty choose and sharpen them.
Objectives
- Write outcomes with observable verbs
- Align each outcome to source material
- Check alignment against a published course-design rubric
Topics
Activity. Have the agent propose outcomes from your sources, then rewrite the weakest three.
How should an agent draft a module outline from your sources?
45 minGrounded drafting: every module and every claim cites the passage it came from.
Objectives
- Configure retrieval over the source set
- Require a citation for every generated claim
- Detect claims with no supporting passage
Topics
Activity. Generate an eight-module outline and trace three claims back to their passages.
How do you generate assessments that test the outcomes?
45 minItems aligned to outcomes, not to sentences in the text, with distractors a subject expert would accept.
Objectives
- Map every item to an outcome
- Write items above recall level
- Review distractor quality
Topics
Activity. Generate ten items for one module and reject the ones that test recall alone.
How do you keep faculty as the author of record?
45 minThe review gate: what faculty must approve, how changes are tracked, and how provenance is kept.
Objectives
- Define what requires faculty approval
- Track every accepted and rejected change
- Keep provenance from source to published page
Topics
Activity. Run a review cycle on one module and produce its provenance record.
How do you make the generated course accessible?
45 minAccessibility is checked, not assumed: structure, alternatives, captions and multiple means of engagement.
Objectives
- Check generated pages against WCAG 2.2
- Write meaningful alternative text
- Apply Universal Design for Learning checkpoints
Topics
Activity. Audit one generated module and fix every accessibility failure you find.
Building a course from one department's documents
45 minThe lab: a complete course draft from your own folder, exported to your LMS.
Objectives
- Produce outcomes, outline, content and assessments
- Pass the faculty review gate
- Export the course in an interoperable package
Topics
Activity. Build the draft course and import it into an LMS sandbox.
What is the capstone project?
A source-traced course draft with its review record
Turn a real document set into a course draft: rights register, outcomes, an eight-module outline with passage citations, aligned assessments, an accessibility audit and the faculty review record.
Deliverable: A course package imported into an LMS sandbox, with its rights register and provenance log.
How are learners assessed?
- Every generated claim in the capstone module traces to a source passage
- Assessment items reviewed by a subject expert for alignment and level
- Accessibility audit of one module against WCAG 2.2
What ships with the course?
Facilitator guide
Session-by-session running order, discussion prompts, and the questions that reliably derail a room.
Learner workbook
Exercises, checklists, and the templates each module's activity produces.
Hands-on lab environment
A sandboxed ibl.ai deployment so exercises run against real agents, not screenshots.
Assessment bank
Scenario questions and rubric criteria mapped to each stated learning outcome.
Source bibliography
Every primary regulation and standard cited on this page, linked and dated.
Which AI agents does this course use?
The hands-on modules run against agents already deployable on the ibl.ai platform for higher education.
Where does the course material come from?
Every module is grounded in primary sources — the regulation, standard, or research itself, not a summary of it. Each was resolved at authoring time.
- Higher Ed Course Design Rubric
Quality Matters
The alignment standard used to review generated outcomes and assessments.
- Universal Design for Learning Guidelines
CAST
Checkpoints for multiple means of engagement, representation and expression.
- Web Content Accessibility Guidelines (WCAG) 2.2
W3C
The accessibility criteria the generated course is audited against.
- Copyright and Artificial Intelligence
U.S. Copyright Office
Background for the rights questions learners take to counsel.
- 17 U.S. Code § 107: Fair use
Cornell Legal Information Institute
The statutory fair use factors, read as questions, not as a determination.
- Common Cartridge
1EdTech
The interoperable package format used to export the draft into an LMS.
Delivery notes
Binding guidance for anyone preparing and delivering this course.
- Module 2 must not tell learners what is or is not fair use. It teaches the questions; the institution's counsel decides.
- Insist that learners bring real documents. A generator looks impressive on clean sample material and fails on the contradictory folders institutions actually hold.
- Module 4's unsupported-claim check is the module that earns faculty trust. Demonstrate a fabricated claim being caught.
- Coordinate with HE-7 on retrieval: the effective-dating problems in catalogs apply to course source material too.
Why run AI training on a platform you own?
You own the course, not a licence to it
Course content, learner data, and the platform run inside your perimeter — you own all the code and the data.
Model-agnostic delivery
Run the course's AI components on any LLM — Claude, GPT, Llama, Gemini, Command — and switch anytime.
No per-seat training licences
Usage-based or self-hosted, so cost tracks actual use rather than headcount.
Deploy anywhere
Cloud, private VPC, on-premise, or fully air-gapped — including for cohorts that cannot use public AI tools.
Frequently asked questions
What does the Create a Course From Your Own Documents with AI course cover?
Most institutions already hold the material for a course in documents nobody has organized into one. This course shows how to have an AI agent draft outcomes, an outline and assessments from those documents, trace every module back to a source passage, clear the rights questions first, and keep a faculty review gate before anything publishes. It runs 6 hours across 8 modules, at intermediate level, and closes with a capstone: A source-traced course draft with its review record.
Who should take Create a Course From Your Own Documents with AI?
It is written for Instructional designers and teaching and learning center staff, Faculty converting existing material into online courses, Continuing and professional education directors, Academic technology staff who run the LMS. Prerequisites: Bring a folder of real source documents for one course or training program; Access to your institution's LMS or a sandbox course shell.
Can we run this course on our own infrastructure?
Yes. ibl.ai is model-agnostic and deploy-anywhere — cloud, private VPC, on-premise, or fully air-gapped — and you own all the code and the data. Cohort data, submissions, and any material learners upload stay inside your perimeter, which matters for higher education teams that cannot send work to a public AI tool.
How do we get access to Create a Course From Your Own Documents with AI?
Request access and we will set it up for your cohort — hosted by ibl.ai, or running against your own deployment. Tell us the group size and timing you need, and whether it should run inside your own perimeter.
How much does AI training for higher education cost on ibl.ai?
There is no per-seat pricing — you pay for usage or self-host and pay only for the infrastructure, so a 5,000-person rollout does not cost 5,000 licences. 1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University.