Stop AI-built sites from all looking the same with a design review loop
He open-sourced loom, a workflow that gives your coding agent distinct design directions, takes honest screenshots and has a reviewer send the work back until it passes. It works in Claude Code, Cursor, Codex and Antigravity.
Source
@evidencecodes on X · 2026-10-19
Written in our own words. Credit to the original author. Link checked 2026-10-20.
What they did
He open-sourced loom, a workflow that gives your coding agent distinct design directions, takes honest screenshots and has a reviewer send the work back until it passes. It works in Claude Code, Cursor, Codex and Antigravity.
Result (as claimed)
Open source; explained in a thread.
Tools they used
Cost: Claude Code: from $17/mo; Cursor: free plan, paid from $8/mo; OpenAI Codex: free plan, paid from $8/mo.
Set it up
Write a one-page brief
Describe the app in plain words: who it is for, the 3 core screens or actions, and what "done" looks like.
Start the project with your agent
Open Claude Code and paste the brief. Ask it to propose a stack and a file plan before writing code.
Build one slice at a time
Ship the smallest working flow first, run it, then add features one by one. Commit after each working step.
Test it like a user
Click through on desktop and phone. Ask the agent to add basic tests and fix anything that breaks.
Check security and ship
Keep keys in environment variables, check auth and database rules, then deploy and share the link.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Stop AI-built sites from all looking the same with a design review loop What the original author did: He open-sourced loom, a workflow that gives your coding agent distinct design directions, takes honest screenshots and has a reviewer send the work back until it passes. It works in Claude Code, Cursor, Codex and Antigravity. Reported result (as claimed by the author): Open source; explained in a thread. Source: https://x.com/evidencecodes/status/2112193475911303654 Tools they used: Claude Code, Cursor, OpenAI Codex, Antigravity Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Stop AI-built sites from all looking the same with a design review loop What the original author did: He open-sourced loom, a workflow that gives your coding agent distinct design directions, takes honest screenshots and has a reviewer send the work back until it passes. It works in Claude Code, Cursor, Codex and Antigravity. Reported result (as claimed by the author): Open source; explained in a thread. Source: https://x.com/evidencecodes/status/2112193475911303654 Tools they used: Claude Code, Cursor, OpenAI Codex, Antigravity Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Stop AI-built sites from all looking the same with a design review loop What the original author did: He open-sourced loom, a workflow that gives your coding agent distinct design directions, takes honest screenshots and has a reviewer send the work back until it passes. It works in Claude Code, Cursor, Codex and Antigravity. Reported result (as claimed by the author): Open source; explained in a thread. Source: https://x.com/evidencecodes/status/2112193475911303654 Tools they used: Claude Code, Cursor, OpenAI Codex, Antigravity Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to vibe code an app with Claude Code · How to use Cursor agents and automations · How to build with Gemini 4 Argon and Gemini agents · How to run multiple coding agents together
Related use cases
See which coding agent chat is waiting on you from one local board
DHI Orbit is one local board for Claude Code, Codex, Cursor, Gemini CLI and Antigravity that shows what needs you, what is working, your usage limits and a reply box.
Install design constraints so agents stop shipping purple-gradient UI
Published polished-ui-skills, a one-command install of design constraints for Cursor, Claude Code, Copilot and Codex.
Add research agent skills that stop invented citations and follow journal rules
A team open-sourced more than 280 research agent skills aimed at the ways agents fail at academic work: invented citations, generic writing and ignoring current journal rules. They install with one npx command into Claude Code, Codex, Cursor, Gemini CLI and more.
Keep all your Claude Code, Codex and Cursor chats searchable in one place
ChatVault collects chats from Claude Code, Codex and Cursor across accounts, lets you search the whole history and keeps local backups.