The Crit
Honest design feedback in under 60 seconds
Project snapshot
Design, UI, UX, Product, Engineering
Live
Next.js, TypeScript, Tailwind, Claude API, Stripe, Supabase
A critique and learning system: URL and image reviews, real critique examples, structured feedback cards, prioritized fixes, designer resources, practical design tools, and a credit-based review flow.
Make automated critique useful in the moment while also teaching designers the language, patterns, and tools to make stronger decisions next time.
A web app that gives designers informed, structured critique on any visual work, then backs it up with examples, tools, and learning content so they can build better judgment over time.
How the system works
Feedback with structure
Reviews are organized around design categories designers can act on: hierarchy, typography, layout, navigation, mobile, accessibility, content, case study, and first impression.
Content that teaches the eye
Articles, examples, and resources turn the critique language into something reusable, so designers leave with a sharper framework instead of one-off advice.
Small helpers around the work
Resume Review, Case Study Builder, Font Pairing, and other tools support the moments where designers need a useful next move, not a vague prompt.
Credits without heavy checkout energy
The credit model keeps repeat reviews lightweight while preserving the core promise: submit real work, get specific feedback, and know what to fix first.
Get the design feedback you've been looking for.
Informed, specific, actionable critique on any visual work. Paste a URL or upload images — know exactly what to improve and why it matters.
The problem
Designers share portfolios for feedback and get "looks great!" Friends are kind; strangers are scarce; senior designers are expensive. You should not have to be enrolled in my class to have access to quality critique.
The feedback loop that every designer needs to improve is broken for 99% of them — and the learning loop is broken too, because most advice names the fix without teaching the eye behind it.
The approach
Build the thing a senior designer would say if they sat with your work for an hour, then surround it with the teaching materials I wish every designer had earlier. Structured review — visual hierarchy, typography, layout, navigation, accessibility, content — returned fast enough to keep momentum while the work is still open, plus examples and tools that help the lesson stick.
The thesis
As AI makes it easier to generate interfaces, the scarce skill shifts from making more screens to knowing which screens are worth making. Design principles, design thinking, and taste become more important, not less, because AI can produce infinite plausible options without understanding whether the work is clear, useful, or right for the moment.
The Crit is built around that belief. The goal is not to replace judgment with automation. It is to give designers sharper language, faster feedback, and more reps seeing why a decision works or does not work.
AI makes screens cheap
More interfaces will exist, and more of them will look plausible at first glance.
Principles matter more
Hierarchy, clarity, intent, and usefulness become the filter for what is worth keeping.
Critique builds taste
Specific feedback gives designers language for what is working and what is not.
Tools turn it into reps
Resources and small workflows help designers apply the lesson to the next decision.
What I designed and built
End-to-end product: brand, landing, submission flow, credit-based review model, the critique experience itself, a growing library of design resources, and the tools suite (Resume Review, Case Study Builder, Font Pairing). The product is part feedback engine, part teaching library, part practical toolkit. Implementation on Next.js with Claude for critique generation, Stripe for payments, Supabase for submissions, GA4 server-side for honest analytics.
Behind the build
The critique structure wasn't invented — it was distilled from more than a decade of teaching design. Before writing code, I mapped what designers actually need from a critique: strengths first so it's received, specific issues so it's useful, vocabulary so it becomes learnable, and a priority list so nobody walks away wondering what to tackle first.
That teaching layer is why the site includes articles, critique examples, and small tools alongside the review flow. The point is not just "get a result." It is to help designers understand why the result matters and practice the decisions behind it.
It took multiple rebuilds to get the critique quality right. Earlier versions hit ceilings on prompt control and voice consistency. The submission UX looked like a generic form. Cache issues kept telling users their finished critique was still "processing." The version that's live now is ground-up — multi-step submission flow, real-time status polling, and vision models analyzing the actual design files instead of descriptions of them.
Craft decisions I care about
Show real critique examples before someone submits — the highest-leverage trust bet on the site, because abstract promises are cheap and specific feedback is the product. Keep resources and tools close to the review flow so the site feels like a working studio, not a checkout funnel. Serif typography and warm palette to feel human, not SaaS. Strict left-alignment discipline. Every CTA earns its place; "learn more" is banned.