Free GH-300 flashcards

Which GitHub Copilot surface explains existing code in prose without changing any files?

Copilot Chat. It handles conversational question-and-answer about code, describing existing behaviour and design rationale in natural language without applying edits, which fits a read-only explanation need where you do not want files touched.

Agent Mode is the right choice when you only want existing code explained in words.

Wrong. Agent Mode is built to take autonomous action and edit files, tracing call graphs and applying refactors it judges necessary. That exceeds and contradicts a read-only request. For a prose explanation with no edits, Copilot Chat is the fit.

What generative-AI risk does GitHub Copilot show when it suggests a convincing function or API that does not actually exist?

Hallucination: the model generates fluent, confident output that is not grounded in fact, so it can invent a plausible-looking helper, API, or behaviour that is not real. A convincing name or signature is not evidence the thing exists, so suggestions must be validated rather than trusted on appearance.

A plausibly named Copilot helper that may not exist is an example of bias in the output.

Bias concerns unfair treatment learned from skewed training data, where one group of inputs is handled less fairly than another. A fabricated helper that may not exist is about invented output, which is hallucination, not unfairness.

What prompting practice gives GitHub Copilot the best chance of generating an accurate first draft of a function body?

Provide a descriptive function signature plus a short comment naming the inputs, expected output, and an example. Copilot predicts completions from the context it is given, so this narrows the prediction toward the intended behaviour and produces a far more accurate draft than an empty or contextless prompt.

Typing only the keyword def on a blank line lets Copilot invent the best function unconstrained.

With no name, parameters, or stated intent, Copilot lacks the context it needs and is far more likely to produce an irrelevant or generic body. A descriptive signature and a comment describing inputs and output guide it toward the intended behaviour.

How do you stop GitHub Copilot from using a named file, such as a secrets file, as context for completions and IDE chat across a whole repository?

Add the file path to the repository's Copilot content exclusions. Available on Copilot Business and Enterprise, content exclusions match files by path and prevent the matched files being sent to Copilot as context for code completions and IDE chat. This is a Copilot context control, separate from Git tracking, duplication detection, or Model Context Protocol.

Adding a file to .gitignore withholds it from Copilot context because untracked files are never sent as context.

.gitignore only controls what Git tracks; it has no effect on what Copilot reads as context. To stop a file being used by Copilot you must add its path to repository content exclusions, not to .gitignore.