Model Selection

Your coding agent isn’t one task — planning, grinding boilerplate, hunting bugs. Run /subagents to read the Copilot team’s own task→model map: cheap+fast for grinding, a different family for critique, your strong model for review. Vendors now ship the ladder.

Model choice is one lever; how hard the model thinks is another. Reasoning effort (low→xhigh) can matter more than model size — a mid-tier model thinking hard often beats a big one thinking little. In Copilot, set it in the /model picker with ←/→.