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
216
I was most impressed by web to wearables, sharing similar component names but wildly different UI
1
14
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
3
76
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!
Replying to @ade_oshineye
Would you be interested in an A2A extension for poppy / PAP? I've thought about making one...
1
1
30
Hey Steven, what would you want? Agent Plugins spec (I think it supports this already)? ARD & AI Catalog spec? Which specs and formats please...
1
1
40
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…
Replying to @notinvariant @GoogleCloudTech
Yes, the 1.0 evolution guide covers the contract changes and migration steps: a2ui.org/specification/v1.0-…
1
13
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…
Answer: the protocol is agnostic. Streams come in and variables are hydrated, renderers would render RTL.
I imagine some layout examples (skills) you may give differently for RTL, but I'm assured it should just work.
Let me know
8
alan blount retweeted
Replying to @GoogleCloudTech
Replying to @jessicayxw @GoogleCloudTech
A2UI is a type of message + sytems to handle it.
It can be emitted by a tool, a workflow, a system one model making choices or (often) by a LLM. The LLM choses to emit A2UI based on instructions, examples, skills, etc... or a fine-tuned model can specialize
21
Replying to @gaurav0bhowmick @GoogleCloudTech
Love the question. Components are drawn on the screen. Those components must have accessibility. A2UI can help with filling in variables, and adhering to design choices (catalog or skill)... but ultimately, it's up to the front end to have affordances
1
16
Replying to @david_kara4595 @GoogleCloudTech
Designers should ❤️ A2UI, because their design systems and components are being used, not mimiced.
2
17












