If you like Looker semantic models and Git workflow, but want to build your own AI-BI platform now, I recommend looking at Credible Data as the engine:

https://www.credibledata.com/

(I have no connection to the company, just know the industry well.)

Credible uses Malloy as the semantic model language. Malloy is built by the original Looker founder and friends, essentially as their next-gen "what would we do differently now" project. It's been discussed on HN a few times in comparison to PRQL, Cube, etc.

Credible layers on some serving infrastructure and RAG and the like. They specifically target the SWE persona as their user. Very technical team with good perspective on the future of the industry IMO.