GitHub GH-300 glossary of Copilot prompts, suggestions, code review, and workflow terms.
Use this glossary when GitHub Copilot (Copilot) terms start to blur together. The goal is practical recognition, not encyclopedia coverage.
| Term | Exam meaning |
|---|---|
| Prompt | Instruction or question given to Copilot. |
| Context window | Code and text available to the model when generating an answer. |
| Suggestion | Generated code or text proposed by Copilot. |
| Policy exclusion | Configuration that limits where Copilot can use or suggest content. |
| Hallucination | Plausible generated output that is wrong or unsupported. |
| Human review | Developer responsibility to inspect and approve generated work. |
| Pair | How to separate them |
|---|---|
| Prompting and context vs Code review and validation | Ask which layer the scenario is testing, then match the answer to that layer only. |
| Control vs evidence | A control changes behavior; evidence proves behavior or supports investigation. |
| Managed service vs custom build | Managed services win for lower operational effort unless the requirement needs unsupported customization. |
| Prevention vs detection | Prevention blocks or reduces a bad event; detection finds or reports that it happened. |
Do not memorize terms in isolation. For each term, write one scenario where it is the best answer, one scenario where it is a distractor, and one signal that proves it worked.