Approved endpoints still serve requests while disappearing from the governed discovery path.
Fast model selection depends on visible catalog entries, while enterprise controls depend on keeping those entries scoped.
Who you’d be doing this for
“My service works with the old endpoint, but every new project starts with an empty catalog.”
Zhila Yilmaz · AI Engineer
Builds production applications that must select approved models through governed platform controls.
What is at stake
Eligible engineers cannot find approved endpoints even though those endpoints still serve existing applications. You must weigh rapid discovery recovery against preserving the access boundaries enterprises rely on.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- fast model discovery vs. catalog access boundaries
- narrow release scope vs. customer setup friction
- direct endpoint continuity vs. governed adoption
Why Databricks
Foundation Model APIs depend on Unity Catalog to make governed model access usable for enterprise AI engineers.
Written with these in mind
Not your kind of problem? 107 more at Databricks, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.