Content by wendy breiding (2)

Wendy Breiding explains how to keep GitHub Copilot (and other frontier coding models) effective by treating repository instructions as a high-signal budget: document the local facts, constraints, and validation commands the model can’t infer, and remove vague “prompt folklore” that adds noise.

Wendy Breiding shares practical ways .NET developers can get more value from GitHub Copilot by choosing the right surface (Visual Studio, VS Code, CLI, or cloud agent) and matching it to the task—whether that’s understanding legacy code, generating tests, planning refactors, or running bounded multi-step changes.