What does Copilot combine with your prompt before sending it to the language model?
Why C is the answer
Additional context, such as open files or repository data
The prompt is combined with context such as open files or repository data, and the conversation history also counts.
In detail
- Copilot adds context, such as open files or repository data.
- That helps the model answer about your code.
- Better context usually does more than a longer prompt.
Use case
An illustrative scenario, not a real incident.
A developer asks "why does this fail?" Copilot adds the open file and the conversation so far, so the model can answer about this code.
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
flowchart LR S0["Your words"] --> S1["Open files"] --> S2["Repository data"] --> S3["Combined prompt"]
Key point: Copilot combines your prompt with context.
Why the other options are wrong
- A. A list of your teammates and the permissions that they each hold
- It does not send a list of teammates.
- B. Nothing at all, because the model only ever sees your exact words
- The model sees more than your exact words.
- D. A complete copy of every repository in your whole organization
- It does not send every repository in your organization.