Sleek?

KINDAYou can build the valuable core, but the established product has meaningful operational complexity. Pick one narrow promise for v1.

BUILD FIRST

One specific customer type and one primary use case
A vertical slice that completes the main job without manual workarounds
Visible limits, review steps, and a fallback when an external dependency fails

LEAVE FOR LATER

Broad third-party integrations
High-scale collaboration, syncing, and permissions
Automation that can cause harm without human review

RESEARCH NOTES

What this tool actually does.

Checked 2026-09-06

Sleek (sleek.design) is an AI-powered mobile app designer. Users describe an app idea in plain language or upload a reference image; the AI generates complete iOS/Android screens — layout, components, copy, styling — following mobile conventions (iOS HIG, Material Design, native navigation, accurate device dimensions, tap-target sizing). Users iterate via chat or edit visually. Exports: one-click paste into Figma as native, editable layers (no plugin) and code as HTML or React with Tailwind CSS. Users own all generated designs/code, including commercial use. Free plan: 1 project, limited AI usage. Paid plans (Starter ~$39/mo, Pro ~$49.99/mo or $30/mo yearly, Team per-user) add AI credits (a screen ≈ 30; edits 5–30), unlimited projects, team features. Pro/Team include a REST API and agent skill so coding agents (Claude Code, Cursor, Codex) create projects, generate screens, and pull HTML/

SOURCES

RESEARCHED BUILD PROMPT

Give this to your coding agent.

Build a web app inspired by Sleek's workflow: an AI mobile app designer where a user describes an app idea (or uploads a reference image) and receives complete, editable mobile screens, then exports them to code. Do not copy Sleek's brand, name, logo, marketing copy, or UI; create an original product with a different name and visual identity.

Workflow: 1) Chat/prompt input with optional image upload; 2) backend calls an LLM to produce a structured screen spec (JSON: screens, layout tree, components, copy, colors, typography) constrained to mobile platform conventions (iOS HIG / Material Design, safe areas, device frames, tap-target sizes); 3) a renderer draws pixel-accurate previews of each screen in the browser; 4) a visual editor lets users select components and tweak properties (text, colors, spacing) and re-prompt the AI for edits; 5) export generates HTML and React + Tailwind CSS files per screen; 6) a REST API (start generation, poll status, fetch HTML/screenshots) so coding agents can drive it.

Technical requirements: React or Svelte frontend; Node/Python backend; LLM API with structured-output/JSON mode; deterministic spec-to-code renderer; project persistence (SQLite/Postgres); API-key auth; async job queue with polling.

Out of scope: Figma plugin/export integration, real-device preview, app-store publishing, image generation, team billing, multi-user collaboration.

Deliver a README covering setup, env vars, how generation works, and important limitations (LLM cost/latency, spec fidelity, no pixel-perfect guarantee, single-user scope).

Visit the official product page