Google Fellowship

Cognitive-Process Assessment

Grading the thinking behind AI-assisted design, not just the artifact

Open source, CC BY 4.0. Use it, tailor it, reweight it for your own class. Credit is the only condition. Nothing here asks you to detect AI use. It asks what the student decided, and what they can show for it. This is the page the printed handout points to.

The eight dimensions

Each one carries its own evidence trail. The tool column is what my own studio sequence uses, and it is the first thing you should replace.

DimensionWhat it measuresEvidenceTools
Prompt ArchitectureStrategic intent, vocabulary depth, and the context framed behind AI instructions.Raw prompt logs, systematic variable testing, multi-turn iteration history.Google Stitch, Gemini
Orchestration LogicHow the student chains multiple AI tools into an end-to-end design workflow.Workflow maps, tool-handoff documentation, architectural decision rationales.Gemini Notebook
Strategic & Content DevelopmentCritical thinking in making and justifying content decisions, feature scope, content priorities, and value proposition, grounded in research findings rather than default or generic choices.Feature-scope prioritization frameworks, content and IA decision logs, value-proposition rationale.Gemini Notebook, Gemini
Critical CurationThe student's ability to evaluate, stress-test, and refine raw AI output against constraints, naming each catch as an Attribution Error, a Logical Error, or a Representational Error.Revision trails, error-tracking sheets, source-verification and fact-check logs, written critiques of AI-generated content.Gemini
Creative Art DirectionTaste, aesthetic consistency, and conceptual choices that override default AI biases.Annotated style matrices, mood boards, mood-to-asset translation logs.Google Stitch
Domain Specific Knowledge ApplicationVisual communication craft, typography, hierarchy, color, and compositional judgment, applied well enough to turn AI-assisted output into original, intentional design work.Typography and hierarchy exploration notes, color and composition rationale, design system documentation, before and after craft comparisons.Google Stitch, Figma
Reflective ReasoningThe student's ability to explain why they made specific curatorial choices, as a legible reasoning chain where each step is independently defensible, not just the final conclusion.Timestamped process notes, file annotations with rationale, spoken walkthroughs in critique.Gemini Notebook, Gemini Gems
Direct Creative ContributionHuman authorship. What the student sketches, develops into original artifacts or moodboards, writes, or fundamentally transforms.Original source files, before and after authoring comparisons showing hand-finished or transformed work.Gemini Notebook, Google Stitch, Figma

Three kinds of error

Two are Google's own language, from the REVEAL paper on verifying reasoning chains. The third came out of my classroom.

Attribution Error. A fact the AI made up. A claim or source that simply isn't true, and wasn't caught.

Logical Error. A step that doesn't follow. A flawed deduction, even from true premises.

Representational Error. New, and provisional. A default the model keeps returning. A demographically skewed output, repeated against an explicit instruction to do otherwise. It is not a fabricated fact and it is not bad reasoning. It is a different failure and it needs its own name.

Honest about the evidence. Representational Error rests on my own R&D plus one documented student account, with no outside replication. I am publishing it as a live claim, not a settled category, and I would like other programs to test it. Background on where it came from is in the Merino interview.

Jacovi, A., Bitton, Y., Bohnet, B., Herzig, J., Honovich, O., Tseng, M., Collins, M., Aharoni, R., & Geva, M. (2024). A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains. Proceedings of ACL 2024. arXiv:2402.00559.

Where the assessment happens

In critique. In every class, students discuss the what and the why of their work. Design education has run on critique for a century, so CPA does not add an event to your calendar. It adds a rubric to a conversation you are already having, and that recurring conversation is what dates the record.

And it cannot be only written. A written log can be generated in seconds. A spoken one cannot, because you can stop a student and ask why they rejected the other three directions, and both of you find out in real time whether they know. Live explanation is also where the thinking happens, not only where you check it.

"I wouldn't recommend 100 percent written, simply because it's easy for people to just AI it. Which sounds horrible, but trust, it will probably happen."

Thalia Merino, FIT. She had never seen this rubric.

Make it yours

This rubric was built for a UX and UI studio sequence. It is not a standard and it is not finished.

  • Reweight the dimensions your course actually cares about.
  • Drop the ones it doesn't. Eight is what my course needed, not a magic number.
  • It does not have to stay in design. The structure is: name the decision, show the evidence, explain it out loud.
  • Change the tool column entirely. The dimensions are about judgment, not about which products a student used.

You do not need my permission and you do not need to tell me. If you do test it, I would like to hear what broke.

Where this came from

CPA is Chapter 2 of Empowering Design Education with AI: Curriculum Innovation in the Age of Creative Intelligence, by Christie Shin and C.J. Yeh. The rubric and the research are open source. The book is a separate purchase.

Built during the Google Higher Ed Faculty AI Fellowship, Inaugural North America Cohort 2026, and tested in CT302, Digital Product Design One, at the Fashion Institute of Technology. The empathy interviews behind it and the Institute materials are on this site.

License: CC BY 4.0. Use it, change it, teach with it, publish with it. The only condition is credit. Suggested wording: Cognitive-Process Assessment rubric, Christie Shin, Fashion Institute of Technology. The book Empowering Design Education with AI is not covered by this license. Full license terms โ†—