GitHub Copilot Fundamentals
Everything a developer needs before using Copilot seriously: what it is, how to install it, how completions and chat work, what agent mode does, which plan to buy, and how to review what it writes.
The Copilot Stack
Your path from Copilot beginner to agentic software engineer.
Curriculum roadmap
Only Cluster 1 is published. The remaining clusters are shown so you can see where the curriculum is going — they deliberately have no placeholder lesson pages.
Everything a developer needs before using Copilot seriously: what it is, how to install it, how completions and chat work, what agent mode does, which plan to buy, and how to review what it writes.
Editor-level mastery: workspace context, edit mode, checkpoints, workspace indexing, next edit suggestions, and integrating Copilot into an existing day-to-day workflow.
Language-specific technique for Python, JavaScript, TypeScript, Go, Java, C#, Rust, SQL and shell — including where Copilot's suggestions systematically need correction.
Dockerfiles, Compose, Kubernetes manifests, Helm, Terraform, Ansible, GitHub Actions and incident workflows — with the review discipline infrastructure code demands.
The terminal agent in depth: sessions, permissions and sandboxing, plan and autopilot modes, worktrees, delegation, programmatic use and CI integration.
Prompt engineering for code, model selection and trade-offs, custom instructions, prompt files, agent skills and AI credit economics.
The cloud agent, custom agents, subagents, MCP servers and tools, third-party agents, and designing multi-step autonomous workflows you can actually trust.
Copilot code review, content exclusion, secret handling, policy management, audit logs, data residency and rolling Copilot out across an engineering organisation.
Someone who can scope work for an agent, supervise it, review what it produces, and know which parts of the job should not be delegated at all.