Copilot, current shape

Before you build on Copilot, know its current shape. Agent mode is generally available^⊙ , and the product has reorganized around agents rather than chat: local agents that run in your editor, a cloud agent that runs in a sandbox and opens a pull request^⊙ , subagents that a lead agent can fan work out to in parallel^⊙ , and a sessions hub to watch them. The October 2025 reorganization brought third-party agents from several vendors into Copilot subscriptions under one roof^⊙ . Custom agents — the definitions you will write next lesson — are honored across the editor and the cloud agent alike.^⊙

You do not need to use all of it. You need to know it exists, because the harness leans on three pieces: local agents for interactive work, subagents for delegation, and the cloud agent for work you can hand off and walk away from.

Choosing a model

Copilot lets you pick a model per request, which means model choice is now a skill. A defensible policy — offered as a policy, not a prescription:

• A capable, fast model for most agent work. Claude Sonnet 5 is currently listed as generally available^⊙ ; evaluate it against the tasks you actually run.
• A stronger model for planning- and synthesis-heavy work — writing the data model, reconciling findings, designing the demo script. Claude Opus 4.8 is listed as generally available^⊙ ; compare its results and total cost rather than assuming a higher price buys a better answer.
• A fast, cheap model for mechanical edits — renames, reformatting, boilerplate. Several capable models sit in this tier^⊙ .

The point is not the specific names, which will rotate. The point is to match the model to the job instead of defaulting to whichever felt best last month.

Usage and cost

Current Copilot billing uses GitHub AI credits, with allowances that depend on the plan and consumption that depends on the model’s token prices. Legacy premium-request multipliers are not the current budgeting model.^⊙ Check the billing reference before quoting a price. Compare total cost per completed task, including retries and review, rather than only the model’s unit price.

In the field

Add three lines to your engagement instructions naming your default model, your planning model, and your mechanical-edit model — by role, not just by name, so the note still makes sense when the names change. You now have a policy instead of a habit.