AI / GitHub Copilot CLI Fundamentals Interview Questions
How does Copilot CLI read and understand repository context?
Copilot CLI builds its understanding of your codebase from several sources - the directory you run it in, the files it reads during a session, project configuration files, and the copilot-instructions.md file.
| Source | What Copilot learns |
|---|---|
| copilot-instructions.md | Build commands, test procedures, architecture overview, conventions |
| AGENTS.md | Agent behavioural rules, tool permissions for autonomous sessions |
| Directory structure | Project layout, frameworks, languages in use |
| Files read during session | Full content of files explicitly opened or referenced in the task |
| Git history and diffs | Recent changes, branch context, commit messages |
| GitHub.com data | Issues, PRs, CI results - accessed via native GitHub integration or MCP |
# Copilot CLI reads context progressively during a session # It does NOT index the entire codebase upfront # To give Copilot specific context: "Look at src/auth/login.ts and explain the authentication flow" # → Copilot reads that file and builds context from it # For large codebases, guide Copilot to the relevant files: "The bug is in the payment processing module in src/payments/" # → Copilot narrows its file reading to that directory # copilot-instructions.md reduces the need for repeated context: # Instead of explaining your stack every session, put it in the file
Context limits: like all LLM-based tools, Copilot CLI has a context window limit. For very large files or repositories, it reads selectively. Providing clear, targeted prompts and maintaining a well-written copilot-instructions.md reduces the risk of Copilot operating with incomplete context.
What is the recommended file for providing Copilot CLI with persistent project context like build commands and architecture notes?
Does Copilot CLI index the entire codebase upfront when you start a session?
More Related questions...
