正在加载视频...

视频加载失败

anthropic engineers just built a full app from scratch with a loop of agents, start to finish in 40 minutes it's the claude code team. they used three agents: one plans, one builds, one checks the work. they keep cycling until the app actually runs the model matters less...

15,276 次观看 • 4 天前 •via X (Twitter)

18 条评论

Blum 的头像
Blum4 天前

Great workshop, watched the whole thing and it was worth every minute

Dean W. Perkins 的头像
Dean W. Perkins4 天前

thanks dude

Martin Lepka 的头像
Martin Lepka4 天前

I like the plan / build / check split. Plan agent is the one I'd watch tho.. a bad brief just gets built faster now :)

ares. 🎧 的头像
ares. 🎧4 天前

lo que me parece más útil es que el que revisa no sea el mismo que escribe, si no se da el visto bueno a sí mismo

Chesny 的头像
Chesny4 天前

lo interesante es que siguen ciclando hasta que arranca, no se conforman con la primera versión

Dean W. Perkins 的头像
Dean W. Perkins4 天前

that's the part that makes it work, the first version is never the one that runs

Leo 的头像
Leo4 天前

saving this for later, nice content dude

Dean W. Perkins 的头像
Dean W. Perkins4 天前

appreciate it, worth the 40 minutes

Jatin Garg 的头像
Jatin Garg4 天前

the 40-minute end-to-end is interesting. how did they handle the agent failures - retry with same prompt or route to a different agent?

roman 的头像
roman4 天前

lo de que el modelo importa menos que el bucle es la frase que más gente debería leer hoy

Marco 的头像
Marco4 天前

me lo guardo, justo estoy montando algo parecido y lo tengo todo en un único agente

Dean W. Perkins 的头像
Dean W. Perkins4 天前

I’d love to see it when you’re finished with it

marcus 的头像
marcus4 天前

que lo enseñe el propio equipo que construye la herramienta le quita toda la duda

Dean W. Perkins 的头像
Dean W. Perkins4 天前

hard to argue with the team that builds the thing

catman 的头像
catman4 天前

The loop had distinct jobs: one agent planned, one built, and one checked whether the app actually ran. That validation step is what closes the gap between generated code and a working app.

crsn 的头像
crsn4 天前

the checker agent is doing the heavy lifting here. planner and builder are easy, getting something that actually says "no, redo it" and is right about it is the hard part

astro 的头像
astro4 天前

@aiscwork barbaridad de vídeo, todo el mundo debería verlo

Hunit 的头像
Hunit4 天前

A planner, a builder, and a checker looping until the app actually runs is a neat pattern, and it fits the idea that the harness around the model matters as much as the model itself. You and @mlkbfrey are the two accounts I enjoy following most.

相关视频