Design Tools

The missing design vocabulary for agents. Impeccable strips the slop from AI-generated interfaces, gives you precise commands to steer, and iterates visual…

Prompt-to-HTML design tool from Meng To that generates landing pages, mobile screens, motion designs, and reusable design systems — with Figma handoff and React export on paid plans.

AI-powered UI design canvas from FlutterFlow that generates production-quality screens from prompts and connects directly to code output. Available as a macOS app and in-browser.

AI-native canvas for product teams that turns intent into shippable UI. Dawn builds opinionated, structured interfaces with real design judgment — not templates. Founded by Brendan and Leo (ex-Envision, Google), the tool targets anyone going from idea to production without the design-to-dev handoff.

UX Pilot generates wireframes and high-fidelity UI screens from text prompts, with standout multi-screen flow consistency that most AI tools get wrong. It includes predictive heatmaps, automated design review, bidirectional Figma integration, and HTML/CSS export. At $14-22/month, it's priced for individual designers; the credit-based model can be disruptive when credits run out mid-project.

Moonchild is an AI design tool that generates high-fidelity UI screens from PRDs or product briefs, but its distinguishing feature is that it generates inside your design system rather than inventing its own — using your actual components, spacing scale, and color tokens from Figma. It produces multiple design directions, critiques them against the original brief, and exports to Figma. Getting active coverage in early 2026 as a serious alternative to Figma Make and Uizard.

A toolkit for coding agents — Claude Code, Cursor, Codex — to build UIs that don't embarrass you. Made by Adam Wathan and Steve Schoger, the team behind Tailwind CSS and Refactoring UI. Early access.

Google Stitch is Google Labs' AI UI design tool powered by Gemini 2.5, generating complete design systems, interactive prototypes, and exportable code from text prompts or images. A major March 2026 update added an infinite canvas, voice interaction, a design agent, and an MCP server connecting to Claude Code, Cursor, and Gemini CLI. May 2026 (Google I/O): real-time streaming — the canvas updates as you type rather than generating complete outputs — and simultaneous multi-user editing, the most-cited missing feature. Free with 350 generations per month and Figma-format export, no download required. No pricing announced.

Variant skips the blank canvas entirely — type a prompt and a scrolling feed of fully-formed UI designs appears. You scroll for more variations without re-prompting, use the Style Dropper to transfer visual DNA between designs, and export as HTML or React code. Built by Ben South (ex-Postmates VP); better for rapid design direction exploration than production refinement.

Banani generates editable, multi-screen UI prototypes from text prompts, reference images, or screenshots, then lets you export directly to Figma, HTML/CSS, or image. It is aimed at non-designers — PMs, founders, engineers — who need to move fast without hiring a designer. Free tier includes 20 generations per day; paid plans start at $20/month.

Vercel's AI UI generator for React/Next.js — turns prompts, screenshots, and Figma exports into clean, production-ready components using Tailwind CSS and shadcn/ui. Rebranded to v0.app in January 2026 with full-stack sandbox, Git integration, and database connectors. Over 6 million developers on platform. Best understood as a frontend scaffolding tool, not a complete app builder.

Anthropic's design tool built on Claude Opus 4.7. Reads your codebase and design files to build a custom design system, then generates visual work through conversation. Included with Claude Pro/Max/Team/Enterprise.

Open-source, local-first AI design editor that reads and writes .fig files and exports directly to production code.