A Gemini app must screen prompts for malicious input and sensitive data. Which tool fits?
Why D is the answer
Model Armor
Model Armor screens prompts for malicious input and sensitive data before they reach the model.
In detail
- Model Armor screens prompts and responses.
- Combine it with safety filters.
Use case
An illustrative scenario, not a real incident.
A Gemini app screens each prompt with Model Armor, which catches attacks and sensitive data before the model.
See it in different ways
flowchart LR A["Prompt"] --> B["Model Armor"] B --> C["Gemini"] C --> D["Safety filters"] D --> E["Response"]
sequenceDiagram participant U as User participant A as Model Armor participant G as Gemini participant F as Output filter U->>A: Prompt A->>G: Screened prompt G->>F: Response F-->>U: Regex and safety checks
sequenceDiagram participant P0 as User participant P1 as Model Armor participant P2 as Gemini P0->>P1: Prompt P1->>P2: Safe prompt P2-->>P0: Response
Key point: Model Armor screens prompts.
Why the other options are wrong
- A. Colab Enterprise
- Colab Enterprise is for notebooks.
- B. Cloud Build
- Cloud Build runs builds.
- C. Dataflow
- Dataflow processes data.