This is blowing up. It looks like building Dagger from first principles is paying off.
Dagger is a runtime for composable workflows. Sure it's great for CI. But it turns out AI agents also need more repeatable, modular and observable workflows - very badly! So here's the plan🧵
Just like we containerized webapps, we'll have to containerize AI agents... but how? What first principles led to containers in the first place, and how do they transpose to LLMs?
This was my first talk at an AI meetup, but I doubt it will be the last!
Recording 👇