Lab 107: How GitHub Copilot Works: Context, Models, Agents, and Data Flow¶
Free-first design
Complete the guided exercise with Copilot Free or the included simulation. Paid features are optional and explicitly labeled.
AI Credit impact
Low for guided work; medium/high for agentic or repeated runs. Prefer automatic model selection, plan before acting, keep context focused, and avoid unnecessary parallel sessions.
What You'll Learn¶
- Describe the Copilot request lifecycle
- Separate context selection from model selection
- Distinguish completions, chat, and agents
- Explain data boundaries, retention, and AI Credits at a conceptual level
GH-300 alignment¶
GH-300 foundation · Data and architecture. This mapping follows the GH-300 curriculum snapshot dated 2026-08-07. The official outline may retain older product wording such as “Copilot Edits”; this lab teaches the current product experience and calls out that difference.
Concept Map¶
flowchart LR
U[User intent] --> C[Selected context]
C --> P[Policies and controls]
P --> M[Model routing]
M --> R[Response or agent plan]
R --> T[Optional tools]
T --> V[Human verification]
R --> V
Hands-on Exercise¶
Step 1: Trace a request¶
Follow editor signals, explicit references, repository instructions, policy checks, model routing, response generation, and user verification.
Step 2: Compare experiences¶
Completions predict code locally in your editing flow; chat answers a conversation; agents plan and use tools over multiple steps.
Step 3: Map data and billing¶
Document who controls the repository, which context leaves the client, applicable retention and exclusion policies, and which interactions consume AI Credits.
Supporting kit¶
The site build generates stable PDF and ZIP downloads. The ZIP contains the lab guide and every supporting file declared for this lab.