Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 4 дней назад •via X (Twitter)

Комментарии: 18

Фото профиля Blum
Blum3 дней назад

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

Фото профиля Dean W. Perkins
Dean W. Perkins3 дней назад

thanks dude

Фото профиля Martin Lepka
Martin Lepka4 дней назад

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

Фото профиля ares. 🎧
ares. 🎧4 дней назад

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

Фото профиля Chesny
Chesny4 дней назад

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

Фото профиля Dean W. Perkins
Dean W. Perkins4 дней назад

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

Фото профиля Leo
Leo4 дней назад

saving this for later, nice content dude

Фото профиля Dean W. Perkins
Dean W. Perkins4 дней назад

appreciate it, worth the 40 minutes

Фото профиля Jatin Garg
Jatin Garg4 дней назад

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?

Фото профиля roman
roman4 дней назад

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

Фото профиля Marco
Marco4 дней назад

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

Фото профиля Dean W. Perkins
Dean W. Perkins4 дней назад

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

Фото профиля marcus
marcus4 дней назад

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

Фото профиля Dean W. Perkins
Dean W. Perkins4 дней назад

hard to argue with the team that builds the thing

Фото профиля catman
catman4 дней назад

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.

Фото профиля crsn
crsn4 дней назад

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

Фото профиля astro
astro4 дней назад

@aiscwork barbaridad de vídeo, todo el mundo debería verlo

Фото профиля Hunit
Hunit3 дней назад

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.

Похожие видео