Pinned Tweet
I work on agents that can work with each other, and with us. A2A for agent collaboration. A2UI for agents driving your design system. Open standards with AAIF. I'll share things I'm building, questions I'm stuck on, and what we learn making these work outside demos.
3
295
alan blount retweeted
How do you make generative UI 4x faster with zero changes to your client renderer? 🤔 In my latest blog post, I explore A2UI Express and Swappable Inference Formats:
⚡ Compact Python-like <a2ui> DSL that cuts output tokens by 4x and prompt size by 55%
🔧 Compiles on the server via a2ui-agent-sdk into 100% identical A2UI v0.9 Wire JSON
🐍 Interactive side-by-side explorer comparing Direct JSON, A2UI Express, Atom, and Elemental with Gemini Flash and @a2ui/lit
Blog post: medium.com/google-cloud/a2ui…
GitHub sample: github.com/meteatamel/genai-…
#GenAI #AIAgents #A2UI #Gemini #GoogleCloud
alan blount retweeted
Can you engineer a smart home energy system over a weekend without writing the code yourself?
I did using the following toolchain:
- Antigravity
- Gemini 4 Hydrogen
- Gemini 4 Carbon
- Day-one secret protection and PR gates
alan blount retweeted
Today we are releasing A2UI 1.0, now faster, easier, and stable, an open protocol and framework for generative UI across web, Android, iOS, wearables, TVs, and any other surface.
👇 Check out what shipped
Registration is open for AGNTCon + MCPCon North America, April 28-29 at Moscone. Two days with the maintainers, contributors, and working groups building the agent stack. CFP is open through Jan 18. Early bird tickets are up. events.linuxfoundation.org/a…
1
2
44
Good read from Isaac Sacolick in InfoWorld. Dial tone, not the whole stack. MCP and A2A are the foundation; ARD, AI Catalog, A2UI, AP2, UCP are some of the layers above. Open questions I'm tracking include auth z down scoped to tasks and also reputation and certification attestations. infoworld.com/article/424662…
2
2
63
alan blount retweeted
🎉 Today, we're excited to be joining Google's release of A2UI 1.0
We’ve worked with Google’s A2UI team since the first release, helping shape A2UI into the best spec for declarative Generative UI.
Generative UI is now truly mature for real products. The building blocks behind it are now faster, more capable and easier to use.
So stop letting your agents answer with giant walls of text.
With A2UI 1.0 and CopilotKit, you can bring the equivalent of OpenAI's intelligent UI in YOUR agentic app with two lines of code.
✨ Your own components, or our pre-built catalog
📲 Any user-facing surface: React, Angular, Flutter, Slack
🔌 Any agent stack: LangChain, ADK, Mastra, Claude Agents and more
Big shoutout to everyone on our team who helped bring this together including @sofiiiiiasz, @GetContextable, @JerelVelarde and @AlemTuzlak
And thank you to @zeroasterisk, Vishal and Jay from the Google team for the continued collaboration.
Read more: go.copilotkit.ai/a2ui1.0-blo…
Check out the A2UI playground: a2ui-playground.copilotkit.a…
alan blount retweeted
We used to only care about how our products look to the human eye.
Now there are completely new layers:
1. AX – how agents experience and interact with your product (WebMCP, MCP, APIs, Poppy, A2A, etc)
2. UAX – how humans perceive your product inside their agent (MCP Apps, A2UI, UI SDK, json-render, voice hints, etc)
The UAX layer is fascinating and overlooked, and it's where a lot of the new innovation opportunities are.
alan blount retweeted
The @CopilotKit crew wrote up a great summary of A2UI 1.0, the standard protocol for generative UIs.
Get details on what's new, what's changed, and how to get started.
copilotkit.ai/blog/introduci…
alan blount retweeted
We built an A2UI playground
Ask the agent for anything and watch it build live, interactive UI.
- See the A2UI it writes, line by line
- Swap design systems: shadcn, Material, or your own
- Copy one prompt to add it to your app
a2ui.open.bot
alan blount retweeted
Knowledge Catalog, Google Cloud's universal context engine, turns knowledge into shared business context so agents answer and act with higher accuracy and trust ↓
alan blount retweeted
This is my favorite type of launch blog.
Even if you don't care about A2UI—you should, personalized UIs are the future—open the link and see:
✅ Clear why, with examples
✅ List of what's new in 1.0
✅ Proof points from users
✅ Links galore
developers.googleblog.com/a2…
I tend to talk fast and skip a lot of the details, but I ended up getting totally sucked in watching this video build up from first principles step by step how to understand the mechanics under A2UI.
It's brilliant, and I enjoyed watching all 1hr of it
A2UI reached version 1! 🚀
This protocol lets agents define a component tree, and frameworks like #Angular or #React render it.
Our video explains how A2UI works and shows it in action:
🎥 youtube.com/watch?v=kZ7fzADj…
#A2UI #AgenticAI #GenerativeUI
4
123
alan blount retweeted
When Google’s A2UI team says your language inspired theirs 🫡
The Google team really cooked with 1.0. Best explanation I’ve read of why generating code for Generative UI is a bad idea.
OpenUI + A2UI interop coming soon!
alan blount retweeted
🎉 Introducing Open Intelligent UI in your app
Powered by A2UI 1.0 and CopilotKit
It takes just two lines of code, to get full generative UI inside of your application:
✨ Use your own components, or our pre-built catalog
🔌 Any model, any agent stack
⌚️ Lower latency and fewer tokens
🩺 Self-healing output
Add generative UI anywhere in your product with Surfaces, starting from our ready-made catalog. Set it up in 2 lines of code!
Get Started (repo, docs): go.copilotkit.ai/open-intell…
alan blount retweeted
a much anticipated launch! amazing seeing the work @CopilotKit and @Google co-contributed to A2UI go live
🤸♂️play around with it at go.copilotkit.ai/a2ui-playgr…
big thanks to @zeroasterisk & @MotwaniVishal for enabling this partnership
alan blount retweeted
Yes, working on an official interop:
github.com/modelcontextproto…
alan blount retweeted
Replying to @GoogleCloudTech
alan blount retweeted
Just wanted to share a (very much WIP) little side project of mine showcasing the benefits/speed of @googlegemma DiffusionGemma 🙂 (text diffusion model)
Project is called “DiffusionGearvis” (mix between DiffusionGemma and Jarvis, IronMan’s AI assistant) and I wanted to implement some features for which I believe text diffusion can really shine, the first one being computer use.
With the success of Muse from Meta, it is very clear that computer use has tremendous value for users. However, this feature is 1) notoriously slow 2) raises serious privacy concerns (screenshots and other personal data uploaded to the cloud). DiffusionGemma can help with both 🙂 It is super fast thanks to text diffusion and is open-weight so people can run it privately on their own desktop / VM. All the demo videos were run locally on a desktop with a single @NVIDIAAIDev RTX 5090 with speech-to-text and text-to-speech from @kyutai_labs (stt-1b-en_fr and pocket_tts) .
This is with the vanilla NVFP4 checkpoint served on @vllm_project so performance can vastly be improved with dedicated fine-tuning or distillation from larger open-weights models. I hope that in a few months, the open-source community will create some fast “local Muse” on top of it :



























