AI coding assistants look complicated because nobody explains how the layers fit together. This page does.

AI coding assistant tooling comes with a lot of overlapping vocabulary — “model,” “agent,” “Copilot,” “instructions,” “MCP” — and very little clarity about what those words actually mean. This site cuts through that. Every page anchors to one specific layer of the stack.

The Confusion This Site Solves

When you switch the model in GitHub Copilot to “Claude,” are you using Anthropic’s model, Anthropic’s agent, or something else entirely? The answer is: it depends, and that ambiguity is the problem.

The vocabulary of AI coding assistants has not kept pace with the tools themselves. Words get reused across different layers of the stack with different meanings. This site maps those layers clearly, so you can stop guessing.

The AICA Onion

Think of AI coding assistants as a stack of layers — each one built on the one below it. We call this the AICA Onion.

The AICA Onion Concentric ring diagram showing the 6 layers of the AI Coding Assistant stack. From innermost to outermost: Layer 0 Model (grey), Layer 1 AI Coding Assistant (blue), Layer 2 Agent (teal), Layer 3 Orchestrator (purple), Layer 4a Instructions and Layer 4b Tools/MCP (both orange, split top and bottom). The AICA Onion Layer 0 Model GPT-5, Claude Layer 1 AI Coding Assistant Copilot · Cursor Layer 2 Agent Agent Mode · Coding Agent Layer 3 Orchestrator Copilot Agents Tab Layer 4a Instructions copilot-instructions.md Layer 4b Tools / MCP MCP Servers · Extensions
LayerNameWhat it isExamples
0The ModelThe math engine — predicts text given a promptGPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Pro
1The AI Coding AssistantThe product you use — responding to you: autocomplete, chat, inline suggestionsGitHub Copilot, Cursor, Windsurf
2The AgentSame product, now acting — loops, uses tools, reads files, makes decisions autonomouslyCopilot agent mode, Copilot coding agent
3The OrchestratorSame product, now routing — delegates your request to a third-party agent instead of handling it directlyGitHub Copilot (Agents tab)
4aInstructionsMarkdown files that shape behaviour — not agentscopilot-instructions.md, AGENTS.md
4bTools / MCPCallable external capabilities — not agentsMCP servers, Copilot Extensions

Each layer depends on the one below it. The model does nothing without a product to call it. An agent does nothing without a model to reason with.

Layers 1, 2, and 3 can all be the same product — GitHub Copilot. The difference is what it’s doing. At Layer 1 it’s responding to you; at Layer 2 it’s acting on your behalf; at Layer 3 it’s routing your request to a third-party agent. When you “switch to Claude” in Copilot, you could be at Layer 0 (swapping the model) or Layer 3 (routing to Claude’s Agent) — the answer depends on which option you picked.

⚠️ “Agent” means two different things in GitHub Copilot — Agent Mode is a local IDE feature for multi-file edits; the Copilot Coding Agent is a separate cloud-based product that works asynchronously via GitHub Actions. The Agent Mode and Copilot Coding Agent pages explain the difference.

Where to Start

Read these in order — each page builds on the last:

  1. What is a Model? — Layer 0. The foundation everything else is built on.
  2. What is an AI Coding Assistant? — Layer 1. The product you actually use day-to-day.
  3. What is an Agent? — Layer 2. When the assistant acts autonomously on your behalf.
  4. Models vs Agents — The most common confusion, addressed head-on.

Already know the basics? Jump straight to Models vs Agents — it’s the highest-value page on the site.

Begin reading

📍 Start Here · All Layers · Documentation Index