I'm still not sure. Would love thoguhts on this.. but in this new ai world we are in... is it better to go fullstack typescript? or go with proven mature frameworks? .net, ruby, django, etc? Seems TS is moving fast but maybe its time to not reach for the shiny object and stick with proven tech? or in 5 years will we regret it?
Agreed. When I watch the llm start to explore the db - it really does impress me.
Can you expand on this:
You can even incrementalize the schema description process itself by way of the system tables. Intentionally not providing a schema description tool/document/prompt seems to perform better with the latest models than the other way around.
Not quite sold on this. I'm going to stick with pydantic ai and dbos/temporal/celery. I do not want to be vendor locked into one of these players. I want to work with absoluately any llm I want... I think we need to keep pushing for best in class open source orchestrtion and not get sucked into this platforms.
When is MCP the right choice though? For example - letting internal users ask questions on top of datasets? Is it better to just offer the api openapi specs and let claude run wild? or provide an MCP with instructions?
I like mikro orm - cool to see you use that. I do prefer django however.
I see express as the backend. Why not nestjs? And are you using openapi at all for generating your frontend client?
What i've discovered is - any backend + orm should expose an openapi spec'd backend... and your frontend can autogen your client for you. Allows you to move extremely quick with the help of ai.
you mention hasura - is that open source? you are leaning on a product for migrations that are not open source is my main concern with the above comments.
Are you able to share some of the tech stack choices behind the scenes? React, fastapi, django, go, pydantic ai, ag-ui, firecrawl, vertex ai, etc. Would love to see the tools and frameworks others are deploying with.