Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Agent tree component, see who started whom

226,460 Aufrufe • vor 18 Tagen •via X (Twitter)

27 Kommentare

Profilbild von Arek
Arekvor 18 Tagen

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

Profilbild von Flo
Flovor 18 Tagen

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

Profilbild von Arek
Arekvor 18 Tagen

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

Profilbild von Flo
Flovor 18 Tagen

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

Profilbild von Stheno
Sthenovor 18 Tagen

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

Profilbild von Sasha ༊·˚
Sasha ༊·˚vor 18 Tagen

this is insane!!! ✨✨

Profilbild von Flo
Flovor 18 Tagen

Thank you Sasha!!

Profilbild von kamran Ahammed Aman
kamran Ahammed Amanvor 18 Tagen

How i can create

Profilbild von heyflo
heyflovor 18 Tagen

You're on fire man!

Profilbild von Razor
Razorvor 18 Tagen

很酷

Profilbild von Nicholas
Nicholasvor 18 Tagen

Mate, your components look great.

Profilbild von don0x0
don0x0vor 18 Tagen

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

Profilbild von Atakan
Atakanvor 18 Tagen

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

Profilbild von Limited Edition Jonathan
Limited Edition Jonathanvor 18 Tagen

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.

Profilbild von Michel David
Michel Davidvor 18 Tagen

nice!

Profilbild von Guilherme Lippert
Guilherme Lippertvor 18 Tagen

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

Profilbild von Shawn
Shawnvor 18 Tagen

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

Profilbild von Justin Bennett
Justin Bennettvor 18 Tagen

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?

Profilbild von Alex · AI & UX
Alex · AI & UXvor 18 Tagen

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?

Profilbild von 3lite
3litevor 18 Tagen

looks so clean :)

Profilbild von ziziran
ziziranvor 18 Tagen

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

Profilbild von murloc.eth
murloc.ethvor 18 Tagen

This rocks hopefully there’s a source 👀

Profilbild von Ravi
Ravivor 18 Tagen

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

Profilbild von Aapakari
Aapakarivor 18 Tagen

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

Profilbild von Paul Martin
Paul Martinvor 18 Tagen

tasty!

Profilbild von eikkenberg
eikkenbergvor 18 Tagen

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

Profilbild von Kashif Ali Khan
Kashif Ali Khanvor 18 Tagen

visual tracing for spawned sub-agents is so clean man

Ähnliche Videos