A Generative AI Engineer prototyping an LLM system unintentionally executed thousands of inference queries against a Foundation Model endpoint over a weekend. What action should they take to prevent this from recurring?

Exam-Like

Last updated: January 1, 2026 at 14:03

Use prompt engineering to instruct the LLM endpoints to refuse too many subsequent queries.

4.5%

Require that all development code which interfaces with a Foundation Model endpoint must be reviewed by a Staff level engineer before execution.

6.0%

Build a pyfunc model which proxies to the Foundation Model endpoint and add throttling within the pyfune model.

20.9%

Configure rate limiting on the Foundation Model endpoints.

68.7%

Databricks Certified Generative AI Engineer - Associate