What does content filtering do in Copilot Chat?
Why A is the answer
It scans prompts and responses to detect and block harmful content
GitHub describes content filtering as a safety system that scans prompts and responses for harmful content.
In detail
- Content filtering scans prompts and responses.
- It detects and blocks harmful content.
- Filtering is a safety layer, so it does not replace code review.
Use case
An illustrative scenario, not a real incident.
A user pastes a harmful request into Copilot Chat. The filtering system detects it and blocks it, and it scans the response as well.
See it in different ways
flowchart LR A["Your prompt"] --> B["Add context"] B --> C["Content filtering"] C --> D["Language model"] D --> E["Content filtering"] E --> F["Response in your editor"]
sequenceDiagram participant D as Developer participant C as Copilot client participant P as Proxy and filters participant M as Model D->>C: Prompt C->>P: Prompt plus context P->>M: Filtered request M-->>P: Response P-->>D: Filtered response
sequenceDiagram participant P0 as User participant P1 as Content filter participant P2 as Model P0->>P1: Prompt P1->>P2: Allowed prompt P2-->>P1: Response P1-->>P0: Allowed response
Key point: Content filtering scans prompts and responses.
Why the other options are wrong
- B. It checks each generated line of code for correct syntax before it appears
- It is not a syntax checker.
- C. It sorts your chat history so that the newest messages are sent first
- It does not organize chat history.
- D. It removes all of the comments from the code that you send to the model
- It does not remove your code comments.