Published 17 September 2026 · Source dated 5 September 2026
More first drafts are arriving via AI agents, but the fundamentals of a good design critique haven't moved. IxDF's literature on critique still holds regardless of who — or what — made the first version.
When an AI agent hands you a first-pass layout instead of a teammate, it's tempting to critique it differently — more technical, less human. Interaction Design Foundation's literature on critique is a useful check against that: separate opinion from evidence, ground feedback in the user's goal, critique the work rather than the maker (or the model). None of that changes because a machine generated the first draft. What does change is the volume of drafts you'll be asked to react to — which makes having a repeatable critique habit more useful, not less, this year.
Coach
next time you review an AI-assisted design, ask 'what user problem does this solve?' before commenting on how it looks.
Jakob Nielsen's ten usability heuristics have been the backbone of UX critique since 1994. They're worth relearning properly, not just skimming the list.
AI tools can generate screens fast, but they don't validate usability — that's still on you. Classic heuristic evaluation is more relevant, not less, now that production speed has gone up.
As AI agents generate more first-draft wireframes and flows, the design skill in demand is shifting toward structured critique and evaluation rather than pure production. Design practitioner writing this month frames this as the real workflow shift for UX, not the AI tools themselves.
Next time you use an AI tool to draft a screen, run a 10-minute heuristic pass on it before you touch it — write down every issue before you fix anything.