Загрузка видео...

Не удалось загрузить видео

На главную

Agent tree component, see who started whom

226,460 просмотров • 18 дней назад •via X (Twitter)

Комментарии: 27

Фото профиля Arek
Arek18 дней назад

Florian you’re unstoppable! 🔥 it looks like you’re creating the most interesting component library i’ve seen so far 💪

Фото профиля Flo
Flo18 дней назад

Really appreciate it Arek! I'm trying to adapt to the agents era 👀

Фото профиля Arek
Arek18 дней назад

and you're doing it very well, man! i take my hat off to you 🔥

Фото профиля Flo
Flo18 дней назад

Thanks a lot!! I really appreciate to hear that from you!

Фото профиля Stheno
Stheno18 дней назад

Would this make sense to do in t3 code? @theo

Фото профиля Sasha ༊·˚
Sasha ༊·˚18 дней назад

this is insane!!! ✨✨

Фото профиля Flo
Flo18 дней назад

Thank you Sasha!!

Фото профиля kamran Ahammed Aman
kamran Ahammed Aman18 дней назад

How i can create

Фото профиля heyflo
heyflo18 дней назад

You're on fire man!

Фото профиля Razor
Razor18 дней назад

很酷

Фото профиля Nicholas
Nicholas18 дней назад

Mate, your components look great.

Фото профиля don0x0
don0x018 дней назад

Hold up. Is this just a UI component or a real product? I want an an agent orchestrator like this.

Фото профиля Atakan
Atakan18 дней назад

love this. we just shipped the memory side of the same idea: every memory shows who wrote it. who-spawned-whom + who-wrote-what is most of the debugging story for multi-agent setups

Фото профиля Limited Edition Jonathan
Limited Edition Jonathan18 дней назад

Ooh, I like this view. I have something similar going on, but in a way that I could actually respond to the agents, Answer questions and send new work. this is legitimately incredible.

Фото профиля Michel David
Michel David18 дней назад

nice!

Фото профиля Guilherme Lippert
Guilherme Lippert18 дней назад

I really prefer the T3’s Orchestrator v2 approach, not focusing too much on the subagents output BUT letting you see if you want Do we really need to know who started which agent or we should focus more on the quality of the output? Feels like babysitting to me, tbh, but I could be very wrong

Фото профиля Shawn
Shawn18 дней назад

This is sick man! I want to know if it works or will be working on mobile ?

Фото профиля Justin Bennett
Justin Bennett18 дней назад

Really cool, but I feel like it takes too much visual space. What if you used a compact dag visualization along the left and attached the agent cards to that?

Фото профиля Alex · AI & UX
Alex · AI & UX18 дней назад

the tree is nice for who started whom. i'd be curious how it holds up at 30 agents, do you collapse finished branches or fade them out?

Фото профиля 3lite
3lite18 дней назад

looks so clean :)

Фото профиля ziziran
ziziran18 дней назад

For the stopped Tester, a link to its replacement (when there is one) would help distinguish a retry from an independent sibling task.

Фото профиля murloc.eth
murloc.eth18 дней назад

This rocks hopefully there’s a source 👀

Фото профиля Ravi
Ravi18 дней назад

love that the cost sits right on each card. once agents start spawning other agents, knowing which branch is spending the money is exactly what you want at a glance

Фото профиля Aapakari
Aapakari18 дней назад

Does it capture why each agent was spawned, or only who?

Фото профиля Paul Martin
Paul Martin18 дней назад

tasty!

Фото профиля eikkenberg
eikkenberg18 дней назад

No way you got a similar UX as me!! Yours feels much more polished though

Фото профиля Kashif Ali Khan
Kashif Ali Khan18 дней назад

visual tracing for spawned sub-agents is so clean man

Похожие видео