What this is

The AI Path on StackNova has grown to cover the modern AI stack for builders: what a language model actually is, the model families you call, the protocol that connects them to your data, the agents that wrap them in autonomy, what it takes to run those agents in production, and the developer tools that put all of it in your daily workflow. This page is the map across that library - every AI Path article, sorted by what it covers, with a short note on each.

It is not a tutorial and not an opinionated comparison. It is the page you bookmark, send to a teammate who is catching up, or come back to when you are not sure which article to read next. For the agent layers specifically there is now a dedicated deep map - the Agentic AI stack - which this page links into rather than duplicates.

Pick a layer, read its article, follow the cross-links. The map is the index, the articles are the depth.- how to read this page

Foundations

Before any product: what the engine is, the vocabulary around it, and what its answers are doing to the way people find things.

LAYER 01

Foundations

AI · Fundamentals

Start with the engine: what a large language model is and why it is stateless. Then the naming - model, LLM, foundation model - untangled once. The search piece closes the loop on what LLM-generated answers change about finding information at all.

Models

The model layer you actually call: one family in depth, plus the catalog for going deep on it.

LAYER 02

Models

AI · Models

Claude is the model family on which most of the StackNova AI surface is built. The article covers the three-tier family (small / mid / large), what each tier is good for, and how to think about pricing, context windows, and the practical differences from other providers. The learning piece maps the official courses and certifications for going deep.

Protocols

Once a model can call your tools and read your data, you need an interoperable contract between the two sides. In 2026 that contract has a name and a growing set of implementations.

LAYER 03

Protocols

AI · Protocol

Model Context Protocol (MCP) is the open standard for connecting AI assistants to external tools, data sources, and services. It is the JSON-RPC-based contract Claude Desktop, Claude Code, Copilot, and a growing list of clients all speak. Understanding MCP is what lets you build once and integrate everywhere.

Agents

An agent is a model running in a loop with tools, memory, and a goal. This layer is where the AI ecosystem has done the most work in the last two years - enough that it now has its own dedicated map.

LAYER 04

Agents

AI · Agents

Read the concept first, then the mechanics: the context window is the thing every agent design is secretly managing. The two architecture pieces cover the step past one agent - when to split, and the five coordination patterns production systems use. For the full traversal of this layer, open the Agentic AI stack map.

Running agents

Building an agent and operating one are different jobs. Three articles cover the operating side: measuring, failing, and paying.

LAYER 05

Production

AI · Operations

How to know an agent works before trusting it, the recurring ways long runs go wrong, and why a run costs many times what its prompt suggests. Read these before the first production deployment, not after the first incident.

Frameworks and extensions

The harnesses you build agents with, and the units of capability you compose into them once they run.

LAYER 06

Frameworks

AI · Frameworks

The survey names the libraries and platforms a builder is likely to actually pick; the Microsoft Agent Framework piece is a closer look at one mainstream option and the ecosystem around it.

LAYER 07

Agent extensions

AI · Extensions

Functions, MCP servers, Skills, hooks, and plugins are different shapes of the same answer - capability you attach to an agent. Two comparison pieces keep the vocabularies straight, the Skills article covers the packaging format in depth, and the plugins piece covers Claude Code's distribution unit.

Developer tools

The surface most builders interact with daily: editor assistants, terminal agents, a delegated-work app, design helpers, and image generators. Tools on top of the models, packaged for specific jobs.

LAYER 08

Coding tools

AI · Coding

Two AI pair programmers, two different shapes. Claude Code is an agentic session that takes a goal end-to-end; GitHub Copilot lives inside your editor with completions, chat, and agent mode. The three companion pieces compare them - the side-by-side, the temperament essay, and a real migration told screenshot by screenshot. The AI for developers map walks this layer in full.

LAYER 09

Knowledge work

AI · Agent Tools

Claude Cowork is the delegated-work surface built on the same agentic architecture as Claude Code, with no terminal in sight - you hand it files and a goal. The comparison piece settles which of the two agentic surfaces fits which job.

LAYER 10

Design and image tools

AI · Creative

Claude Design is Anthropic's web surface for using Claude as a design partner. Nano Banana (Gemini 2.5 Flash Image) is Google's fast, conversational image-generation and editing model - the practical answer for image work inside a developer workflow.

Three reading orders

The map is sorted by topic, but most readers want a route. Three orders, depending on who you are.

For: developer new to AI tools

You write code and want AI in your workflow

  1. What is an LLM?
  2. What is Claude?
  3. What is GitHub Copilot?
  4. What is Claude Code?
  5. Claude Design + Nano Banana
For: agent builder

You want to build the agent, not just use one

  1. What is agentic AI?
  2. What's in an agent's context?
  3. What is Model Context Protocol?
  4. Skills, MCP, Hooks, and Plugins
  5. AI agent frameworks
  6. Then the full Agentic AI stack map
For: depth-first reader

You want the whole stack, in order

  1. The engine + the vocabulary
  2. What is Claude? (the model)
  3. MCP (the wire)
  4. Agentic AI → the context → the patterns
  5. Then the full index table below, top to bottom

The map at a glance

If you read only this section, here is the AI stack from the bottom up:

Every article in the map

Every AI Path article, by category, with a one-line reason to read.

Category Article Why read it
Foundations What is an LLM? 101 The stateless text-completion engine underneath everything else on this map.
Foundations Model, LLM, foundation model 101 Three overlapping terms, untangled once - so the rest of the library reads cleanly.
Foundations AI answers and search 101 What LLM-generated answers change about search, for readers and for the sites they used to visit.
Models What is Claude? 101 The foundation model family most of the StackNova AI surface is built on - tiers, capabilities, and tradeoffs.
Training Learn Claude: courses and certifications 101 The official course catalog and certifications for going deep on Claude, mapped.
Protocol What is Model Context Protocol? 101 The open standard connecting AI assistants to external tools, data, and services.
Agents What is agentic AI? 101 The concept - what makes a system "agentic," the parts of an agent, and how it differs from a chatbot.
Agents What's in an agent's context? 101 The one block of text an agent sends the model every turn - what is in it, what it costs, what falls out first.
Agents Multi-agent systems 201 When to split one agent into several, the three shapes that work, and what handoffs actually cost.
Agents Multi-agent orchestration patterns 201 Orchestrator-workers, pipelines, fan-out, critique, routing - and how to pick the one your job needs.
Production How to evaluate an agent 301 How to measure an agent before trusting it with real work.
Production Why agents fail 301 The recurring failure modes of long agent runs, and the guards that catch them early.
Production What an agent actually costs 201 Why a run costs many times what its prompt suggests once the whole context is re-sent every turn.
Frameworks AI agent frameworks 101 A survey of the libraries and platforms used to build agents in production.
Frameworks What is the Microsoft Agent Framework? 201 Closer look at one mainstream option, with the surrounding Microsoft ecosystem context.
Extensions Functions, MCP, Skills 101 The three vocabularies for "things an agent can do," compared and untangled.
Extensions What are Agent Skills? 201 Anthropic's packaging format for reusable instructions and resources an agent can load on demand.
Extensions Skills, MCP, Hooks, and Plugins 201 The four extension mechanisms side by side, and which job each one belongs to.
Extensions What are Claude Code plugins? 201 Claude Code's packaging for sharing skills, commands, and MCP servers as one install.
Coding What is Claude Code? 201 The terminal-based autonomous coding agent - long-running sessions, file edits, command execution.
Coding What is GitHub Copilot? 101 The editor-resident AI pair programmer - completions, chat, agent mode, and the model picker.
Coding GitHub Copilot and Claude Code 101 The side-by-side - editor vs terminal, when to pick which, and the workflow split.
Coding Copilot vs Claude Code: engineer vs artist 101 The focused temperament essay - one axis, with concrete tasks where each tool's default pays.
Coding Claude Code is a Magician 101 A real 2018 snake game migrated in one Claude Code session - screenshot by screenshot.
Cowork What is Claude Cowork? 101 The delegated-work surface for knowledge work - the same agentic architecture, no terminal.
Cowork Claude Cowork vs Claude Code 201 Which agentic surface fits which job - the knowledge-work one or the engineering one.
Design What is Claude Design? 101 Anthropic's web surface for using Claude as a design partner - where it fits in a designer's workflow.
Image What is Nano Banana? 101 Google's fast image-generation and editing model - the practical answer for image work in a dev workflow.
Image What Nano Banana can do 101 The capability tour - concrete examples of what Nano Banana ships day-to-day.