What this is
The AI Path on StackNova has grown to cover the modern AI stack for builders: the foundation models you call, the protocols that connect them to your data, the agents that wrap them in autonomy, the extensions that shape what an agent can do, and the developer tools that ship those agents to your daily workflow. This article 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.
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
Models
The foundation layer: large language models you call from your own code. Most other layers on this map exist to make these models useful for a specific job.
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.
- → What is Claude? LEVEL 101
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.
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.
- → What is Model Context Protocol? LEVEL 101
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, and where the vocabulary still settles.
Read the concept first, then the frameworks that implement it. The concept piece names the parts (planner, tools, memory, control loop). The frameworks piece surveys the ones a builder is likely to actually pick. The Microsoft Agent Framework is a closer look at one mainstream option.
- → What is agentic AI? LEVEL 101
- → AI agent frameworks LEVEL 201
- → What is the Microsoft Agent Framework? LEVEL 101
Agent extensions
Once you have an agent, the question is what it can do. Skills, functions, and MCP servers are three different shapes of the same answer - units of capability you compose into an agent.
Agent Skills are Anthropic's packaging format for reusable instructions and resources an agent can load on demand. The comparison piece sits one level above and untangles the three vocabularies (functions, MCP, Skills) that are easy to confuse.
- → What are Agent Skills? LEVEL 101
- → Functions, MCP, Skills LEVEL 201 - the three vocabularies, compared
Developer tools
The surface most builders interact with daily: editor assistants, terminal agents, design helpers, and image generators. Tools on top of the models, packaged for specific jobs.
Two AI pair programmers, two different shapes. Claude Code lives in your terminal as a long-running autonomous agent; GitHub Copilot lives inside your editor with inline completions, chat, and a more recent agent mode. Most teams use both, for different parts of the workflow.
- → What is Claude Code? LEVEL 101
- → What is GitHub Copilot? LEVEL 101
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.
- → What is Claude Design? LEVEL 101
- → What is Nano Banana? LEVEL 101
- → What Nano Banana can do LEVEL 101 - the practical capability tour
Three reading orders
The map is sorted by topic, but most readers want a route. Three orders, depending on who you are.
You write code and want AI in your workflow
You want to build the agent, not just use one
You want the whole stack, in order
- What is Claude? (the model)
- What is Model Context Protocol? (the wire)
- What is agentic AI? + frameworks
- Agent Skills + Functions/MCP/Skills
- Every tool article (Copilot, Claude Code, Claude Design, Nano Banana)
The map at a glance
If you read only this section, here is the AI stack from the bottom up:
- Model: Claude (and other foundation models you call via API).
- Protocol: MCP for tool and data integration.
- Agent: a loop around a model - read agentic AI, then a framework.
- Extensions: Agent Skills for capability packaging; Functions/MCP/Skills to keep the three vocabularies straight.
- Tools: GitHub Copilot in the editor, Claude Code in the terminal, Claude Design for design work, Nano Banana for images.
Every article in the map
Every AI Path article, by category, with a one-line reason to read.
| Category | Article | Why read it |
|---|---|---|
| Models | What is Claude? 101 | The foundation model family most of the StackNova AI surface is built on - tiers, capabilities, and tradeoffs. |
| 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 | AI agent frameworks 201 | A survey of the libraries and platforms used to build agents in production. |
| Agents | What is the Microsoft Agent Framework? 101 | Closer look at one mainstream option, with the surrounding Microsoft ecosystem context. |
| Extensions | What are Agent Skills? 101 | Anthropic's packaging format for reusable instructions and resources an agent can load on demand. |
| Extensions | Functions, MCP, Skills 201 | The three vocabularies for "things an agent can do," compared and untangled. |
| Coding | What is Claude Code? 101 | 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. |
| 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. |