AI coding tools have converged on a similar feature set (inline completions, chat, agents that edit many files and run commands, cloud agents that turn issues into pull requests, automated code review and MCP integrations), yet they differ sharply in where they live and how they fit a team: an extension across many IDEs, a terminal-first agent, an AI-native editor, or a CLI and cloud service tied to a chat subscription. This course teaches each tool hands-on and then teaches the durable skill underneath all of them: giving an agent the right context, constraining what it may do, and verifying what it produces.
You will configure GitHub Copilot agent mode, Copilot cloud agent (formerly the Copilot coding agent) and Copilot code review; Claude Code's CLAUDE.md, permission modes, plan mode, hooks, skills, subagents and MCP servers; Codex's AGENTS.md, sandboxing and approval modes across CLI, IDE and cloud tasks; and Cursor's Agent, Tab, rules, cloud agents and Bugbot. The later modules cover test-first loops, reviewing AI-written diffs for hallucinated APIs and silent behavior changes, secrets and prompt injection through repositories and issues, licensing and data-retention settings, and measuring impact honestly. Product details are stated as of the review month with links to each vendor's documentation. Completion and a passing exam score earn a Wirewalk Institute of AI certificate of completion and assessment; it is not a vendor certification and is not endorsed by any vendor named.