Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Part 3: Replaying A2UI Cache with Widgetbook. Testing generated UI can be tricky. I cover how I built a custom add-on connected to Firestore, allowing to replay and inspect those cached A2UI outputs directly inside Widgetbook.

Cagatay Ulusoy

5,587 subscribers

12,716 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing the A2UI Widget Builder ⚙️ An interactive demo and template to build A2UI Widgets and bring them into your application. Powered by CopilotKit & Google's new A2UI spec Includes... - Widget Gallery: premade UI widgets you can use & modify - Material Icons: 100 of the most commonly used icons - UI Components: common components preview, usage and props - Source code and data on any widget/icon/component - Built with CopilotKit- so you get chat UI, generative UI, etc. Try it out: Tutorial of how to get started: Repo:

Introducing the A2UI Widget Builder ⚙️ An interactive demo and template to build A2UI Widgets and bring them into your application. Powered by CopilotKit & Google's new A2UI spec Includes... - Widget Gallery: premade UI widgets you can use & modify - Material Icons: 100 of the most commonly used icons - UI Components: common components preview, usage and props - Source code and data on any widget/icon/component - Built with CopilotKit- so you get chat UI, generative UI, etc. Try it out: Tutorial of how to get started: Repo:

CopilotKit🪁

18,783 views • 9 months ago

Wouldn't it be super convenient to have your Snapchat lenses all inside OBS with a built-in UI to change effects and settings? I built a utility just for that. It loads your whole lens group in a custom panel.

Wouldn't it be super convenient to have your Snapchat lenses all inside OBS with a built-in UI to change effects and settings? I built a utility just for that. It loads your whole lens group in a custom panel.

Brielle Garcia

101,852 views • 9 months ago

Inspired by Built a 3d learning platform for DSA with one prompt. Not live yet still testing. Will push it to github soon. Do comment how it looks and what all I can add to this

Inspired by Built a 3d learning platform for DSA with one prompt. Not live yet still testing. Will push it to github soon. Do comment how it looks and what all I can add to this

Neeraj Walia

29,528 views • 1 month ago

The harder part of QA on a team isn't always finding the bug. It's getting the finding in front of the right person with enough context to actually fix it. I tested Replay on ClientFlow, a React client-delivery dashboard I built. Replay caught an issue in the review workflow where approving work caused the status indicator to jump out of view. But the part I wanted to test was what happens next. With Replay for Teams, the QA findings are shared with the project, and teammates can be brought directly into the Bug or Test Run context instead of passing screenshots and explanations around. Find it → share the context → get it to the right person. That feels much closer to how QA should work when more than one person is shipping. Check out Replay for Teams on Product Hunt: Replay

The harder part of QA on a team isn't always finding the bug. It's getting the finding in front of the right person with enough context to actually fix it. I tested Replay on ClientFlow, a React client-delivery dashboard I built. Replay caught an issue in the review workflow where approving work caused the status indicator to jump out of view. But the part I wanted to test was what happens next. With Replay for Teams, the QA findings are shared with the project, and teammates can be brought directly into the Bug or Test Run context instead of passing screenshots and explanations around. Find it → share the context → get it to the right person. That feels much closer to how QA should work when more than one person is shipping. Check out Replay for Teams on Product Hunt: Replay

Iris Quinn

60,483 views • 26 days ago

im blown away with this highly controllable shader system that opus 5 built inside of sentinel i gave it an image reference and it made a procedural system + custom ui to create infinite variations with no assets

im blown away with this highly controllable shader system that opus 5 built inside of sentinel i gave it an image reference and it made a procedural system + custom ui to create infinite variations with no assets

Spencer Sterling

10,679 views • 1 month ago

IMHO, Dear ImGui is easily the most underrated library for in-game UI. I built a custom UI framework on top of it (skinning, animations, layouts, HUD elements, scaling, aligment etc) for my engine. Couldn't be happier with how fast and clean it turned out.

IMHO, Dear ImGui is easily the most underrated library for in-game UI. I built a custom UI framework on top of it (skinning, animations, layouts, HUD elements, scaling, aligment etc) for my engine. Couldn't be happier with how fast and clean it turned out.

Ioannis Koukourakis

17,829 views • 1 month ago

I've been testing Bot Mode in the Hermes Desktop App a bit today, so I made a quick video showing the key features and how it differs from a normal Hermes session: - Side bar shows a list of bots (agent profiles) you can talk to - Agent Inbox allows bots to communicate directly with one another - Create Agent to make a new bot with a custom PFP, description, and configuration - Cron jobs bar on the right to create crons for specific bots Still in testing for the next day, so let's test it out and see how it can be improved!

I've been testing Bot Mode in the Hermes Desktop App a bit today, so I made a quick video showing the key features and how it differs from a normal Hermes session: - Side bar shows a list of bots (agent profiles) you can talk to - Agent Inbox allows bots to communicate directly with one another - Create Agent to make a new bot with a custom PFP, description, and configuration - Cron jobs bar on the right to create crons for specific bots Still in testing for the next day, so let's test it out and see how it can be improved!

tonbi

107,089 views • 1 month ago

Based on the WWDC 2026 leaks, I tried to recreate the iOS 27 revamped Siri interaction inside the Dynamic Island in swift ui with lots of different settings and some custom shaders. And yeah, if it’s like that, it will be kinda boring going from a rainbow like ui to a monochrome one.

Based on the WWDC 2026 leaks, I tried to recreate the iOS 27 revamped Siri interaction inside the Dynamic Island in swift ui with lots of different settings and some custom shaders. And yeah, if it’s like that, it will be kinda boring going from a rainbow like ui to a monochrome one.

Tykra

38,717 views • 3 months ago

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

Pratham

33,920 views • 7 months ago

I built my first native Mac app! It's called Coverage. It connects with whatever you're playing on Spotify and makes effects play on the album cover. This effect is called Sheet. And when I say I, you know of course that I mean Astra and I. I don't know how to make Mac apps. That doesn't matter anymore. I'll make a demo video soon about how it works and how I prompted Astra. But I can't now because I'm on a plane, and that would be weird for my seat mates. So I just asked Codex to add a new feature to Coverage. I had it make a video capturing how rad it looks.

I built my first native Mac app! It's called Coverage. It connects with whatever you're playing on Spotify and makes effects play on the album cover. This effect is called Sheet. And when I say I, you know of course that I mean Astra and I. I don't know how to make Mac apps. That doesn't matter anymore. I'll make a demo video soon about how it works and how I prompted Astra. But I can't now because I'm on a plane, and that would be weird for my seat mates. So I just asked Codex to add a new feature to Coverage. I had it make a video capturing how rad it looks.

Craig Dennis

21,658 views • 8 days ago

I submitted SunsetCity 🌇 to #vibejam 🤙 Now the parkour graph extends to window and doors’ frames 🎉 In the next days I’m doing polishing, improving textures and sprites and a lot of testing. Gotta fine tune those constants! I created 3 quality presets, forcing LOW on mobile. I think I’ll add also 3 difficulties presets ✌️ #gamedev

I submitted SunsetCity 🌇 to #vibejam 🤙 Now the parkour graph extends to window and doors’ frames 🎉 In the next days I’m doing polishing, improving textures and sprites and a lot of testing. Gotta fine tune those constants! I created 3 quality presets, forcing LOW on mobile. I think I’ll add also 3 difficulties presets ✌️ #gamedev

Francesco Di Donato

27,861 views • 4 months ago

During testing... I'm often asked how long I test a single style. I don't have a fixed timeframe. Sometimes styles are very consistent and I can test them for 2-3 hours. Other times I really love a style and I'm willing to fight to the end to get the result I want — and that can take anywhere from a few days to a week. And the most complex but equally amazing styles take even longer — those I generally don't share on my website. Instead I create moodboards from what I consider the best results and use those styles that way.

During testing... I'm often asked how long I test a single style. I don't have a fixed timeframe. Sometimes styles are very consistent and I can test them for 2-3 hours. Other times I really love a style and I'm willing to fight to the end to get the result I want — and that can take anywhere from a few days to a week. And the most complex but equally amazing styles take even longer — those I generally don't share on my website. Instead I create moodboards from what I consider the best results and use those styles that way.

Olga Volosin

32,726 views • 2 months ago

I tried creating a customizable sword smear rig in Blender that can be imported directly into game engines without requiring custom shaders. This way, i don't have to manually add sword slash VFX in the editor and hope they match the animation timing in-game lol

I tried creating a customizable sword smear rig in Blender that can be imported directly into game engines without requiring custom shaders. This way, i don't have to manually add sword slash VFX in the editor and hope they match the animation timing in-game lol

Lez

263,172 views • 2 years ago

Okay, this is probably the best RAG UI I have ever seen. Just wow. I got a local version running in about 30 seconds with my existing Weaviate data. Here are some of the things I loved right away: 1) You can examine the raw data by collection 2) You can chat 3) You can see a tree for how the responses were generated 4) You can provide real-time feedback that can be used to train a model to improve the RAG workflow. 5) Still testing, but lots more! Well done Weaviate AI Database team!

Okay, this is probably the best RAG UI I have ever seen. Just wow. I got a local version running in about 30 seconds with my existing Weaviate data. Here are some of the things I loved right away: 1) You can examine the raw data by collection 2) You can chat 3) You can see a tree for how the responses were generated 4) You can provide real-time feedback that can be used to train a model to improve the RAG workflow. 5) Still testing, but lots more! Well done Weaviate AI Database team!

William J.B. Mattingly

33,340 views • 1 year ago

Wild what's possible now: I can ship a 3D experience prototype to a museum in a single afternoon. Everything coded and generated with Omma, leveraging AI to iterate fast. 3D models generated in Omma. Scene built on top of Three.js. Prompted for dissolving shaders + particle systems?

Wild what's possible now: I can ship a 3D experience prototype to a museum in a single afternoon. Everything coded and generated with Omma, leveraging AI to iterate fast. 3D models generated in Omma. Scene built on top of Three.js. Prompted for dissolving shaders + particle systems?

Joseph Azar

93,557 views • 3 months ago

Our vision for Simulacrum is to enable anyone to create onchain AI agents with a single post or DM 🪄 How? By allowing builders & protocols to add skills that can then be stacked like Lego pieces to make custom AI agents: - Uniswap - DEXScreener - Etherscan - X feed and much more The only limits? Builder imaginations and user creativity 🚀 👉 See how at

Our vision for Simulacrum is to enable anyone to create onchain AI agents with a single post or DM 🪄 How? By allowing builders & protocols to add skills that can then be stacked like Lego pieces to make custom AI agents: - Uniswap - DEXScreener - Etherscan - X feed and much more The only limits? Builder imaginations and user creativity 🚀 👉 See how at

Empyreal

11,668 views • 1 year ago

I am creating amazing websites in hours. Not days, not weeks with Claude. Example here: I'm part owner of a basketball training facility called Swish365. We built a custom app in the appstore/play store and its a challenge to update. The website too (original built on wordpress). Two hours, I converted our app to mobile UI without an app, integrated into Stripe's API's to manage subscriptions. Built fully dynamic and automate reporting for payments to each franchise location with all fees/royalties taken out. Something that took us hours before. Trending analysis of each facility on upward/downward trends for facility. Dynamic location creation so when we add new franchises it automatically creates it. Convert all existing members from old to new system. If they book once a week, it creates a streak similar to NBA Jam, if they get to BOOMSHAKALA they get a free shirt. Beautiful webpage, custom business processes directly to our business and enhancements over previous systems. Two hours. It's unbelievable.

I am creating amazing websites in hours. Not days, not weeks with Claude. Example here: I'm part owner of a basketball training facility called Swish365. We built a custom app in the appstore/play store and its a challenge to update. The website too (original built on wordpress). Two hours, I converted our app to mobile UI without an app, integrated into Stripe's API's to manage subscriptions. Built fully dynamic and automate reporting for payments to each franchise location with all fees/royalties taken out. Something that took us hours before. Trending analysis of each facility on upward/downward trends for facility. Dynamic location creation so when we add new franchises it automatically creates it. Convert all existing members from old to new system. If they book once a week, it creates a streak similar to NBA Jam, if they get to BOOMSHAKALA they get a free shirt. Beautiful webpage, custom business processes directly to our business and enhancements over previous systems. Two hours. It's unbelievable.

Dave Kennedy

10,552 views • 6 months ago

This is what Elon Musk childhood looked like. I spent over $10,000 on Seedance 2.0 in the past few weeks... i decided to create a guide with EVERYTHING i know about this model: - workflows - prompts - how to get the best outputs RT + reply "ELON" and i'll send it for free (must be following so i can dm)

This is what Elon Musk childhood looked like. I spent over $10,000 on Seedance 2.0 in the past few weeks... i decided to create a guide with EVERYTHING i know about this model: - workflows - prompts - how to get the best outputs RT + reply "ELON" and i'll send it for free (must be following so i can dm)

Amir D

156,319 views • 5 months ago