THE TALK, PUT INTO PRACTICE
From prompt
to production.
Using AI agents to build better course materials. A practical companion for faculty, from the first idea to a resource worth teaching with.
One teaching need. A complete production process.
This companion follows the 70-slide faculty talk from how language models work to how agent workspaces can help create course materials. Explore the explanations, try a small activity, and keep the learning goal visible as the resource takes shape.
FOLLOW THE NARRATIVE
A field guide from
idea to artifact.
Move through the chapters in order, or start with the teaching problem on your desk.
How AI works
Training shapes the model. Context shapes the current task. Generation produces a response that still needs evaluation.
Agent workspaces
A workspace connects a model to files, tools, and feedback so work can continue across several steps.
Learning design
An attractive resource becomes useful when it helps learners produce evidence of the capability you intend to teach.
Research
Use AI to organize inquiry while keeping source support, uncertainty, and disciplinary judgment visible.
Visual materials
A module image, explanatory diagram, and slide sequence make different demands on the tools and on your review.
Assessment
Use AI to draft criteria, examples, and feedback, then test whether those distinctions fit the actual student task.
Build lab
Explore the campus module, then identify one small interaction that would help students think in your course.
Activities
Choose an activity by the teaching problem you want to solve, then adapt its prompt to your course.
Resources
Download the talk and working materials, then keep the sources and review decisions alongside your own resource.
The educator keeps the purpose, the evidence, and the final teaching decision.
AI can help draft, build, compare, and revise. Begin with one worthwhile teaching problem and a standard you can explain.
Take the starter kitPUT THE IDEA TO WORK
Try this in your course.
Define the win
Describe the learners, the learning outcome, and the evidence you want to see.
Give the agent a brief
Write the course context, approved sources, constraints, and review criteria in one reusable file.
Build a one-page module
Ask Cursor or Antigravity to turn your brief into a local web page with outcomes, explanation, practice, and an exit ticket.