whatever you delegated in the past probably also required planning by the engineer that went down and got it done, most planning done by agents is at this same level, agent explores the codebase, understands where to touch, tradeoffs, code-level architecture, and ask the user for more context or balance with assumptions and other patterns already present in code
Hey this context is more importante than the prompt itself, make it more clear in the post! As this hints to a way to reproduce the output and likely estimate if it's an hallucination or not
Cool project. Could You expand on what is the use case for something like it compares to e.g. a python library? Maybe an example of more complex workflows or open ended loops/agents that can showcase the pros of using such a language compared to other solutions. Are these pipelines durable for example or how do they execute?
What is the approach used? It seems everything gets done in context by plain text searches with some agent like Claude code or is there RAG involved? (was the article written by AI? it has that LinkedIn-groove all over the place)
This is awesome, thanks for your work!
Could this work with the file system api in the bowser to write to user disk instead of indexeddb? I'm interested in easy ways for syncing fot local-first single user stuff <3 thanks again
I tried this too! Where every button on the page triggered a get or post request, but the consistency between views was non existent lol, every refresh showed a different UI Definitely fixable with memory for the views and stuff though but keeping it pure like this is a very cool experiment. Since yours is using a actual storage maybe You could try also persisting page code or making the server stateful and running eval() on generated code. Love this