Loading video...

Video Failed to Load

Go Home

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 views • 4 days ago •via X (Twitter)

18 Comments

Blum's profile picture
Blum4 days ago

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

Dean W. Perkins's profile picture
Dean W. Perkins4 days ago

thanks dude

Martin Lepka's profile picture
Martin Lepka4 days ago

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. 🎧's profile picture
ares. 🎧4 days ago

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's profile picture
Chesny4 days ago

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

Dean W. Perkins's profile picture
Dean W. Perkins4 days ago

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

Leo's profile picture
Leo4 days ago

saving this for later, nice content dude

Dean W. Perkins's profile picture
Dean W. Perkins4 days ago

appreciate it, worth the 40 minutes

Jatin Garg's profile picture
Jatin Garg4 days ago

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's profile picture
roman4 days ago

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

Marco's profile picture
Marco4 days ago

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

Dean W. Perkins's profile picture
Dean W. Perkins4 days ago

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

marcus's profile picture
marcus4 days ago

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

Dean W. Perkins's profile picture
Dean W. Perkins4 days ago

hard to argue with the team that builds the thing

catman's profile picture
catman4 days ago

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's profile picture
crsn4 days ago

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's profile picture
astro4 days ago

@aiscwork barbaridad de vídeo, todo el mundo debería verlo

Hunit's profile picture
Hunit3 days ago

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.

Related Videos