PRODUCTION SCENARIO
A children's tutoring app on Gemini must block responses that carry even a low likelihood of harassment or dangerous content. A separate internal engineering assistant finds those same settings too restrictive when it discusses security topics.
How should the platform team handle the two applications?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: Set the blocking threshold per harm category separately for each application
Gemini's configurable content filters block unsafe content by harm category at a blocking threshold the customer chooses, and that threshold is meant to be set for what each use case and business needs. The non-configurable filters covering child sexual abuse material and personal data cannot be turned off, and filters sit outside system instructions as a separate barrier.