It's a bit scary to know they have conversation data from people even if their datasets are anonymized. They say they gather actual conversation data from "third party data sources". For obv reasons they won't cite where they got it from.
Rainy / cold days, busy families, and being able to access a greater variety of food in urban areas. These are scenarios with a high degree of pain that have not yet been solved by modern urban or surburban lives.
Watched your Youtube. I love this - will try it out and give it to our team. This is effectively the "full mode" version of the mode I currently use Cursor for.
Curious how this is going to affect Cursor - I'm assuming it'll just be a drop-in replacement and we can expect Cursor to get the same speed-up as VSCode.
Congrats on launching! Wish we had this years ago at Flexport for our ops / science teams. Traditional ML approaches are expensive, and the idea of defining your final shape of data and automating the ETL process is the best abstraction out there.
Curious - what do you guys use for the T step of your ELT? With nested blocks 12 layers deep, I can imagine it gets complicated to try to de-normalize using regular SQL.
Literally just had this idea 2 days ago - each TS agentic project feels like doing this stdlib work over and over again, but with a slightly differently architecture each time.
One question for our use case - what if a standard function requires bi-directional communication (as opposed to a single call to `generateText`)?
For one standard function, our envisioned interaction loop is:
Agent --> SSE to browser --> browser processes --> browser sends results back to server --> server sends to Agent --> Agent returns result