AI Agent Concepts Every Developer Should Know

Augment Code
521 views February 20, 2026

Every AI coding agent term explained in under 10 minutes. Rules, custom commands, sub-agents, hooks, MCP, permissions, task lists, skills, and context engine — there's a ton of new terminology in AI-powered development tools like Augment Code and Claude Code. In this video, I break down what each concept actually does, when to use it, and where it lives in your project so you can configure your AI coding agent like a pro.Whether you're setting up agents.md, writing your first custom slash command, creating sub-agents for specialist tasks, or wiring up MCP integrations with GitHub, Linear, and Playwright — this guide covers it all with practical examples. 📖 Augment Code Docs: https://docs.augmentcode.com00:00 - Overview of all terms 01:41 - Rules and agents.md explained 03:31 - Custom commands walkthrough 04:17 - Sub-agents deep dive 04:46 - Hooks and lifecycle events 06:22 - MCP integrations 07:02 - Skills as packaged behaviors 07:19 - Permissions configuration 07:36 - Task list planning interface 08:01 - Context engine explained #aicoding #AugmentCode #ClaudeCode #CodingAgent #MCP #ModelContextProtocol #AgentsMD #DevTools #AIagent #SoftwareDevelopment #SubAgents #Hooks #CodingWorkflow #VibeCoding #AITerminology

Keyboard shortcuts

On. Switch them off if they collide with your assistive tools; ? still opens this sheet.

Go to

Press g then the letter.

  • gh Latest
  • gs Sources
  • gm Media
  • gv Videos
  • gp Podcasts
  • gc Calendar
  • gd Decoder
  • gz Dataviz
  • ga Datasets
  • gb Blog
  • gk Markets
  • gj Careers
  • gn Prompt Notebook

On this page

  • / Focus search, where there is one
  • t Back to top
  • ? This list
  • Esc Close