Video yükleniyor...
Video Yüklenemedi
Build a Multimodal UI/UX design agent team using Google ADK and Gemini 2.5 Flash Nano Banana. Just upload a screenshot of landing page and the AI agents will analyze design, provide expert feedback, and generate an improved version. 100% Opensource code.
50,473 görüntüleme • 1 yıl önce •via X (Twitter)
33 Yorum

Step-by-step tutorial with Opensource code:

100+ free step-by-step tutorials with code covering: 🚀 AI Agents 📀 RAG Systems 🗣️ Voice AI Agents 🌐 MCP AI Agents 🤝 Multi-agent Teams 🎮 Autonomous Game Playing Agents P.S: Don't forget to subscribe for FREE to access future tutorials.

Stay tuned for more such interesting posts → @Saboo_Shubham_ I have created 100+ AI Agents and RAG tutorials, 100% free and opensource. P.S: Don't forget to star the repo to show your support 🌟

This is AWESOME!!

Thank you!

Very cool. Thanks for sharing!

You’re welcome!

That’s the kind of AI that turns designers into instant multimodal power users.

A smart design squad that never sleeps just hit beta : Imagine snapping a pic of any landing page then unleashing a squad of Google ADK wranglers and Gemini 2.5 Flash Nano Banana virtuosos to dissect every pixel whip up pro-level tweaks and even spin out a fresh mockup on the spot ; no secret sauce needed since the entire codebase is open source and yours to hack, remix, and run wild in your next UI thrill ride.

I will be checking this out

Thank you for this information and example. Unbelievable!

You're welcome!

Love this. Multimodal design agents that critique then improve could compress design cycles and teach better taste over time. What evaluation signals will you use to judge improvements such as usability tests conversion lift or expert heuristics?

One of the coolest advancements in AI design tools. No two landing pages are the same. so the more variations the models train on, the better it will get.

Nice post!

Thanks Nina :)

Impressive stuff! Looking forward to trying it out.

Thank you!

based share!

Thanks!

Incredible work, keep going!

@yocha0109112342 Thank you!

Love this! Your post are pure gold!!🚀

Thank you!

I also built one :)

Thanks!! This is great! Any URL where we can try this out?

Such a smart approach. Getting expert level feedback automatically could save tons of back and forth. How do you handle conflicting suggestions from multiple AI agents?

This is amazing! Using Google ADK and Gemini 2.5 for UI/UX design feedback is such a practical application. Love the opensource approach - definitely going to try this out!

Open-source multimodal design agents make expert UX review + redesign instant, product teams will ship better interfaces faster.

Interesting! Opensource multimodal agents could democratize UI/UX design feedback access.

Open-source tools like this? cool approach for empowering creators

Sounds like the future of design just dropped! Can't wait to see what these AI agents whip up.

This is wild. We're basically at the point where AI can critique design decisions better than most junior designers. Next step is AI arguing with itself.
Benzer Videolar
Sensitive content
I built a Multimodal AI Agent using Gemini 2.0 that can understand videos and search the internet at the same time. 100% Opensource Code with step-by-step tutorial.
Shubham Saboo
97,889 görüntüleme • 1 yıl önce
