This NEW AI Design Tool Changes EVERYTHING
Julian Goldie introduces Replit Design, a new AI-powered design tool launched July 29, 2026, that enables users to create professional designs without traditional design software by using ambient intelligence and one-click iterations. The tool integrates multiple AI models, built-in design references from Mobbin, brand system support, and direct integration with live product deployment on the Replit platform.
Summary
Julian Goldie presents Replit Design as a revolutionary AI design tool that fundamentally changes how design work gets done. Unlike traditional AI design tools that require users to prompt repeatedly and wait for single outputs, Replit Design uses "ambient intelligence" to continuously suggest improved versions and next steps that users can accept with single clicks, creating an iterative refinement process rather than a slot-machine approach.
The tool's core capabilities include: ambient intelligence that proactively shows variations; a template system that acts as flexible ingredients rather than locked starting points; built-in integration with Mobbin, a library of 600,000+ real screens from 1,000+ apps used by 2 million designers; support for multiple top AI models (Claude, GPT-5, Gemini, Kimmy, GLM) that users can swap between projects; and brand system integration that applies consistent colors and fonts across all designs with a single click.
The most significant feature, according to Goldie, is that all design work lives on Replit alongside the actual product code, eliminating the traditional gap between design files and deployed websites. Users no longer need to export designs, hand them off to developers, or rebuild them in separate tools—the design and working product exist in the same environment.
Goldie demonstrates practical applications including landing page creation for the AI Profit Boardroom, welcome screens for new members, and marketing graphics. He identifies common mistakes when choosing AI design tools: selecting tools that force users to start from zero with each iteration, using tools that split work across multiple applications, getting locked into a single AI model, and creating designs that cannot be converted to functional products.
The tool supports multiple starting points including plain text prompts, screenshots, website links, Figma files, and existing design systems. Goldie recommends starting from existing references rather than blank pages, leveraging one-click suggestions over excessive typing, loading brand systems before building, experimenting with different AI models, using clear descriptive language, and working in focused bursts to maintain performance.
Key Insights
- Previous AI design tools operated like slot machines where users had to prompt and wait for single outputs repeatedly, whereas Replit Design uses ambient intelligence to continuously show improved versions and next steps that users accept with clicks
- Replit Design treats templates as flexible ingredients that can be dropped in at any point during a project rather than as locked starting lines, allowing users to get unstuck mid-way through work
- The critical feature that changes everything is that designs live on Replit alongside actual product code, eliminating the gap between pretty design pictures and working websites—no exporting, rebuilding, or handoffs required
- Every AI model has its own taste and style, so users who can swap between Claude, GPT-5, Gemini, Kimmy, and GLM on different projects will explore more options and reach better results faster than being locked to one model
- A design that cannot actually ship and become a real working product is not truly a design—it's just a screenshot, making the design-to-live product workflow a fundamental criterion for evaluating design tools
Topics
Transcript
[0:00] This new AI design tool changes everything. What if you never had to open a design app again to make something look amazing? No Figma, no Canva, no hours pushing pixels around, just the idea in your head on the screen in seconds. Sounds too good to be true, right? It's real. And most people have no clue it just dropped. I'm the digital avatar of Julian Goldie. My whole job is helping you actually learn and use AI tools in your real work, not just watch cool demos and forget them by lunch. And today I want to show you something that flips design on its head. Stick with me because there's one feature near the end that…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Google AI Studio Just Got A Huge Security Upgrade
Google is reportedly developing a new "Security Check" mode for AI Studio that would apply secure coding practices to AI-generated applications. The feature aims to automate security verification during app development, addressing common vulnerabilities like exposed keys, weak authentication, and data access issues before deployment.
New Gemini Skills Update Is WILD!
Google has launched Gemini Skills, a new feature allowing users to save custom instructions once and reuse them repeatedly by typing a slash command, replacing the discontinued Gems feature. Skills can include reference files, be combined together, and are built on an open file format (skill.md) that allows portability across different AI tools.
NEW Codex CLI Update Is ABSURD!
OpenAI's new Codex CLI update transforms terminal-based programming assistance by enabling multiple AI agents to work simultaneously on different tasks, visible in a full-screen control center interface. The update includes features like Agent View, work trees, voice control, and parallel task execution, fundamentally changing how AI assistance operates from sequential Q&A to autonomous team-based work management.
NEW Hermes Cloud + Agent OS is Crazy! 🤯
Hermes Cloud combined with Agent OS enables users to deploy AI agents in the cloud 24/7 using free models without API keys or local setup complexity. The system provides persistent memory, sandbox isolation, and integration with custom workflows like content research, competitor analysis, and news monitoring.
Manus 2.0 Just Changed AI Agents Forever
Manas 2.0 represents a fundamental architectural overhaul that enables users to create games, websites, videos, and automations through simple text requests, with the key innovation being editable components rather than fixed outputs. The platform uses a new Cascade engine that reduces token usage by 23% and improves task speed by 28%, while maintaining all project elements in one connected workspace.