A critique harness combining brand, accessibility, content, representation, and user-task rubrics.
CRAFT · Masterclass
Feedback, Fidelity, and Fairness
Make the system critique the work without letting it grade itself.
Use structured critique, adversarial review, accessibility evaluation, and human testing to find plausible-looking mistakes.
Before-and-after artifact, issue log, human test notes, unresolved risks, and correction rationale.
Brand, Accessibility, and Representation Critique Harness
Class requirement: create or sign in to your Alternate Clouds account, deploy the Brand, Accessibility, and Representation Critique Harness template, and submit its live URL before the class is marked complete.
Create your Alternate Clouds account ↗Use only work you own or are authorized to use.
Every submission needs a source-and-license manifest covering text, code, images, audio, video, fonts, datasets, models, weights, and AI reference inputs. Attribution alone is not permission. Questionable material stays private or is replaced before deployment or showcase.
Ask about rights clearance01A rubric before a reaction+
Define hierarchy, clarity, brand, task completion, accessibility, and trust criteria.
Write a weighted critique rubric and test whether two reviewers can use it consistently.
02The fidelity trap+
Recognize when polished output hides weak information architecture, fake content, or impossible behavior.
Strip a polished concept to its task flow and identify every unsupported assumption.
03Accessibility and representation+
Test contrast, keyboard use, reading order, captions, motion, language, and stereotyped outputs.
Run an accessibility and representation review with named evidence.
04Adversarial review+
Use separate models and people to challenge claims, edge cases, and production feasibility.
Red-team the chosen direction and publish what remains uncertain.
The complete course adds the teaching deck, Alternate Clouds lab, source-bounded guide, review rubric, and instructor feedback.
Find a class