Design Review and Critique with Agents
Critique is where design quality is actually decided, and it is the part of the process most teams under-resource. This course covers using agents to make review sharper and more frequent without outsourcing taste: structured critique loops, heuristic evaluations and cognitive walkthroughs run at a scale no team could staff, visual regression evidence, accessibility and content review, and design review wired into every pull request.
Modules5 modules
Last updated2026-06-02
Audience and outcomes
Design leads, senior designers, and design-minded engineers responsible for review quality — particularly teams where critique currently depends on whoever has spare time that week.
- Run critique loops where the agent applies named dimensions and the human makes the calls.
- Execute heuristic evaluations and cognitive walkthroughs across whole products with evidence per finding.
- Use screenshot-based regression evidence so visual review stops relying on memory.
- Run accessibility and UX-writing reviews as standard passes rather than special projects.
- Wire design review into every pull request with clear severity levels and human escalation.
- Keep taste and final judgment human while making the mechanical parts of review continuous.
Modules
Modules marked Available have full slide decks with speaker notes and narration scripts. The rest show their planned outline until production catches up.
Critique Loops with Agents
The structure of a useful critique loop: named dimensions instead of vibes, the agent as a tireless first reviewer, and the difference between feedback an agent can act on and feedback that needs a human decision.
- Define critique dimensions — hierarchy, density, tone, states, accessibility — for your product.
- Run an agent critique pass that produces findings with evidence, not opinions.
- Separate actionable feedback from judgment calls and route each correctly.
Heuristic Evaluation and Cognitive Walkthroughs at Scale
Two classic methods most teams skip because of cost, run across an entire product by agents: standard heuristics applied screen by screen, task-based walkthroughs step by step, and the human pass that turns findings into decisions.
- Set up a heuristic evaluation across a full product surface with consistent criteria.
- Run cognitive walkthroughs against defined user tasks rather than screens in isolation.
- Triage large finding sets without drowning the team in low-severity noise.
Visual QA and Regression Evidence
Replacing it looked fine last time I checked with evidence: screenshot baselines, agent-run sweeps across states and breakpoints, and regression reports a designer can act on in minutes rather than re-checking everything by hand.
- Establish screenshot baselines for the surfaces that matter.
- Run regression sweeps that compare against the baseline with diffs as evidence.
- Distinguish genuine regressions from intended change without manual re-review of everything.
Accessibility and Content Review
Two reviews that are chronically deferred, made routine: accessibility sweeps that go beyond automated contrast checks, and UX-writing review that holds copy to the product's voice with the same rigour as the visuals.
- Run accessibility reviews covering structure, keyboard flow, and screen-reader sense, not just contrast.
- Audit interface copy for voice, clarity, and consistency against a written standard.
- Decide which findings agents can fix directly and which need design or legal judgment.
Design Review on Every PR
The end state: every change that touches the interface gets a design review automatically — token and component checks, screenshot evidence, severity levels — with humans reviewing what matters instead of everything or nothing.
- Define what a per-PR design review checks and what it deliberately ignores.
- Set severity levels and escalation so humans see the findings that need them.
- Roll the practice out without turning it into a blocking bureaucracy.
Books and articles behind this course
The course teaches the practice; the books and articles carry the depth, the sources, and the worked runs it draws on.
The operating model for product designers, design leads, and builders who need to understand what changes when agents join design work.
- Visual QA With Agents
A long-form workflow for using agents to inspect screenshots, compare implementation against intent, run accessibility checks, and produce fix-ready review notes — traced against a real review of this site's own article page.
- Design Critique Loops With Agents
A practical workflow for turning agent critique from vague opinion into structured findings, evidence, severity, revision passes, and human design decisions.
- Design System Audits With Agents
A deep workflow for finding design-system drift across tokens, components, screenshots, copy, interaction states, and product meaning.
- Four Agentic Design Workflows in Production: What Actually Happened
Four real agentic design workflows traced from their own repositories — an editorial site, a multi-agent book pipeline, a book-to-video pipeline, and the design system underneath the site — with the timelines git can prove, the configs that did the steering, the failures the gates caught, and the patterns that repeat across all four.