Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Agent tree component, see who started whom

226,460 görüntüleme • 18 gün önce •via X (Twitter)

27 Yorum

Arek profil fotoğrafı
Arek18 gün önce

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

Flo profil fotoğrafı
Flo18 gün önce

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

Arek profil fotoğrafı
Arek18 gün önce

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

Flo profil fotoğrafı
Flo18 gün önce

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

Stheno profil fotoğrafı
Stheno18 gün önce

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

Sasha ༊·˚ profil fotoğrafı
Sasha ༊·˚18 gün önce

this is insane!!! ✨✨

Flo profil fotoğrafı
Flo18 gün önce

Thank you Sasha!!

kamran Ahammed Aman profil fotoğrafı
kamran Ahammed Aman18 gün önce

How i can create

heyflo profil fotoğrafı
heyflo18 gün önce

You're on fire man!

Razor profil fotoğrafı
Razor18 gün önce

很酷

Nicholas profil fotoğrafı
Nicholas18 gün önce

Mate, your components look great.

don0x0 profil fotoğrafı
don0x018 gün önce

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

Atakan profil fotoğrafı
Atakan18 gün önce

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

Limited Edition Jonathan profil fotoğrafı
Limited Edition Jonathan18 gün önce

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.

Michel David profil fotoğrafı
Michel David18 gün önce

nice!

Guilherme Lippert profil fotoğrafı
Guilherme Lippert18 gün önce

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

Shawn profil fotoğrafı
Shawn18 gün önce

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

Justin Bennett profil fotoğrafı
Justin Bennett18 gün önce

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?

Alex · AI & UX profil fotoğrafı
Alex · AI & UX18 gün önce

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?

3lite profil fotoğrafı
3lite18 gün önce

looks so clean :)

ziziran profil fotoğrafı
ziziran18 gün önce

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

murloc.eth profil fotoğrafı
murloc.eth18 gün önce

This rocks hopefully there’s a source 👀

Ravi profil fotoğrafı
Ravi18 gün önce

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

Aapakari profil fotoğrafı
Aapakari18 gün önce

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

Paul Martin profil fotoğrafı
Paul Martin18 gün önce

tasty!

eikkenberg profil fotoğrafı
eikkenberg18 gün önce

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

Kashif Ali Khan profil fotoğrafı
Kashif Ali Khan18 gün önce

visual tracing for spawned sub-agents is so clean man

Benzer Videolar