VORCL
← All courses
Beginner · 7 lessons

AI-native IDEs: Cursor, Copilot, and the new editor workflow

Autocomplete, chat, and agent mode as the three gears of an AI editor: a Cursor deep dive (Tab, Cmd+K, Agent), rules files and project context, Copilot in VS Code, disciplined review of inline edits, and a final refactor in all three modes.

Start →
  1. 01Three gears: autocomplete, chat, and agentA mental model of the AI editor: how autocomplete, chat, and agent mode differ, how much control you cede at each gear, and how to pick a mode for the size and risk of a task.35 min
  2. 02Cursor deep dive: Tab, Cmd+K, and AgentA deep dive into Cursor: Tab predictions of the next edit, inline edits via Cmd+K, the multi-file Agent (Composer), and @-symbols for precise context.50 min
  3. 03Rules files and project contextProject rules as repeatable context: migrating from .cursorrules to .cursor/rules, rule types, globs and alwaysApply metadata, AGENTS.md, and portability across tools.45 min
  4. 04Copilot and agent mode in VS CodeGitHub Copilot in VS Code: inline suggestions and Next Edit Suggestions, chat in Ask and Edit modes, autonomous agent mode with tools, and instruction files.45 min
  5. 05Reviewing inline edits without rubber-stampingThe discipline of reviewing AI diffs: why Accept All is a trap, red flags in generated edits, small batches, checkpoints, and questions to the agent as a verification tool.40 min
  6. 06When to leave the IDE for a terminal agentThe limits of the IDE agent: which tasks are better handed to terminal agents like Claude Code, handoff criteria, and a hybrid workflow with git worktree.40 min
  7. 07Capstone: a three-mode refactorFinal project: the same refactor of a real repository in three modes — Tab, Cmd+K, and Agent — measuring time, diff size, and review effort.60 min

Sources

AI-native IDEs: Cursor, Copilot, and the new editor workflow · VORCL