StackNova / Paths / AI
PATH 01 · AI

Build with agents.

Build with the new generation of agents - from the model itself to the design tools, frameworks, and the people whose work is moving the field.

54 ARTICLES

Articles in this path.

Three angles on the current generation of AI - the assistant most teams build on, the design tool from the same lab, and the engineers worth following as the agentic field evolves.

55 of 55 shown
Sort / / /
MAP · AGENTIC AI / LEVEL 101

Agentic AI stack

The agent slice walked in full - the idea, the window, the extensions, the architectures, production, and the frameworks - with three reading orders for different readers.

Read it
MAP · AI / LEVEL 101

AI stack

One page that ties the AI library together - every article outside the agent layer sorted by layer (foundations, models, platforms, protocols, retrieval, tools), a hand-off to the Agentic AI stack, and four reading orders.

Read it
AI · SEARCH / LEVEL 101

AI answers and search

Answer engines write you a paragraph instead of ten links - but crawl, index, and rank still run underneath. What retrieval-augmented generation changes, and what it leaves exactly where it was.

Read it
AI · RETRIEVAL / LEVEL 101

What is RAG?

An 800-page document and one question: why pasting it all into the prompt fails, and how retrieval-augmented generation finds the few pages that matter instead. What it costs to build, and what the prompt looks like; the internals are in Inside a RAG pipeline.

Read it
AI · RETRIEVAL / LEVEL 301

Inside a RAG pipeline

Chunking, embeddings, cosine similarity, BM25, and rank fusion - each part of the retrieve step taken apart one at a time, and the failure modes that decide how you tune it.

Read it
AI · RETRIEVAL / LEVEL 201

RAG vs MCP: pipeline or tool?

Not rivals - a pattern and a protocol. The real choice is who triggers retrieval: your code before every call, or the model through a tool. The axes that decide it, and the shape most teams end up with.

Read it
AI · DEVELOPER TOOLS / LEVEL 101

What is GitHub Copilot?

The AI pair programmer that lives inside your editor - inline completions, a chat sidebar, agent mode, and a model picker that now spans OpenAI, Anthropic, and Google.

Read it
AI · CODING TOOLS / LEVEL 101

GitHub Copilot and Claude Code

The two AI pair programmers most developers reach for today - one in the editor, one in the terminal. How they differ, when to pick which, and why a lot of teams use both.

Read it
AI · TEMPERAMENT / LEVEL 101

Copilot vs Claude Code: engineer vs artist

The focused essay on the one axis that most decides which AI pair programmer fits which task. One tool ships clean parts; the other proposes whole designs.

Read it
AI · CONTEXT / LEVEL 101

What's in an agent's context?

The six things sitting in the window on any given turn, what each one costs, and what gets thrown away when it fills up.

Read it
AI · MEMORY / LEVEL 201

Inside agent memory

Context, state, long-term memory, and retrieval - the four words builders keep merging, separated, placed on one diagram, and given the one design decision each of them needs.

Read it
AI · FUNDAMENTALS / LEVEL 101

What is a model?

The learned "brain" of an AI system - patterns learned from data, applied to new input. The data-to-output chain, a worked translation example, what the file is made of, and four things a model is not.

Read it
AI · FUNDAMENTALS / LEVEL 101

What is an LLM?

One kind of AI model - very large, trained on text, predicting what comes next. What the three words in the name mean, what the model is actually doing, why it invents things, and why it cannot remember yesterday.

Read it
AI · FUNDAMENTALS / LEVEL 301

Inside an LLM

One question - what is the capital of the UK? - followed from keystroke to answer: the template, the tokens, attention, the probability table, and the loop that runs again for every word.

Read it
AI · FUNDAMENTALS / LEVEL 101

What is Gen AI?

The umbrella term - software that composes new text, code, images, audio, and video instead of labelling what exists. How it works, the modalities, where LLMs and agents fit, what it is good and bad at, and the three ideas that made it possible.

Read it
AI · FUNDAMENTALS / LEVEL 101

Why do AI models hallucinate?

A confident, fluent, false answer is not a malfunction - it comes from the same process as every correct one. The mechanism, the forms it takes (facts, citations, code, agent reports), where it clusters, and how to build a product that catches it.

Read it
AI · FUNDAMENTALS / LEVEL 101

What is Augmentation?

One word, four things it gets added to - a person, a training set, a product, or a model's prompt. Human, data, and AI augmentation, plus RAG, with the two questions that tell them apart.

Read it
AI · AGENTS / LEVEL 201

What an agent actually costs

Why a run costs many times what its prompt suggests, where the money goes, and the gap between an agent that works and one you can afford to run every day.

Read it
AI · ORCHESTRATION / LEVEL 201

Multi-agent orchestration patterns

Orchestrator-workers, pipelines, fan-out, critique, routing - the five ways production systems wire agents together, and how to pick the least dynamic one that fits.

Read it
AI · AGENTS / LEVEL 201

Multi-agent systems

The move from one agent that does everything to several that each do one thing well - why teams make it, and what the handoffs cost.

Read it
AI · AGENTS / LEVEL 301

How to evaluate an agent

A chatbot answer is one artifact you can read. An agent run is twenty hidden steps and a confident summary - what to measure, and how to catch quality sliding rather than breaking.

Read it
AI · AGENTS / LEVEL 301

Why agents fail

The failure modes that only show up once an agent leaves the demo - runaway loops, exhausted context, compounding errors, and the one that costs most: a run that reports success on work it never did.

Read it
AI · AGENTS / LEVEL 101

What is an agent?

Model, tools, loop - the strict definition, how an agent differs from a chatbot and from a workflow, one task traced end to end, and the ten-line loop that runs it.

Read it
AI · AGENTS / LEVEL 101

What is Agentic AI?

A short, honest tour of the term everyone is using - what agentic AI actually means, how it differs from a chatbot, the loop that powers it, and where it earns its keep in real work.

Read it
AI · AGENTS / LEVEL 201

What are Agent Skills?

Portable, composable units of expertise an agent can load on demand - the way you teach Claude (or any modern LLM agent) to do specialised work without rebuilding the model around it.

Read it
AI · ASSISTANT / LEVEL 101

What is Claude?

Anthropic's AI assistant - a family of large language models built for conversational reasoning, writing, coding, and analysis, with safety as a first-class design goal.

Read it
AI · TRAINING / LEVEL 101

Learn Claude

Claude Academy's free catalog after the August 2026 move off Skilljar - every course with its lesson count, hours, and badge, grouped as the Academy groups them, and where to start in it.

Read it
AI · DEVELOPER TOOLS / LEVEL 201

What is Claude Code?

Anthropic's coding agent that runs in your terminal - reads your codebase, edits files, runs commands, and ships features. Claude with your shell at its disposal.

Read it
AI · KNOWLEDGE WORK / LEVEL 101

What is Claude Cowork?

Anthropic's agent for knowledge work - hand it a goal and it plans and runs the multi-step task across your files and tools, returning a finished deck, doc, sheet, or brief. Same engine as Claude Code, no terminal.

Read it
AI · AGENT TOOLS / LEVEL 201

Claude Code vs Claude Cowork

Two agents, one engine, two jobs - knowledge work versus software engineering. Where each lives, what it acts on, what it hands back, and how to tell which a task belongs to.

Read it
AI · PLUGINS / LEVEL 201

What are Claude Code plugins?

Bundle skills, MCP connections, hooks, and agents into one installable unit - what a plugin is made of, how a marketplace serves it, and how install and updates actually work.

Read it
AI · AGENTS / LEVEL 201

Skills, MCP, Hooks, and Plugins

The building blocks you extend an agent with - instructions it reads, live links to your tools and data, deterministic guardrails, and the plugin that bundles them. One overview, with links to the deep dives.

Read it
AI · CASE STUDY / LEVEL 101

Claude Code is a Magician

A real 2018 snake game - ASP.NET Core, gulp, .cshtml, scattered JavaScript - migrated to HTML5 + TypeScript + esbuild in a single Claude Code session. Twenty minutes of work, screenshot by screenshot.

Read it
AI · DESIGN TOOLS / LEVEL 101

What is Claude Design?

Describe what you want and an AI designer builds it as a working artifact - mockups, prototypes, and decks your whole team clicks, comments on, and changes in one place.

Read it
AI · FRAMEWORKS / LEVEL 201

What is Microsoft Agent Framework?

Microsoft's open-source framework for building agentic AI applications - the successor to AutoGen, with first-class C# and Python SDKs and an Azure AI Foundry integration.

Read it
AI · FRAMEWORKS / LEVEL 101

AI Agent Frameworks

The six frameworks teams reach for when they move from one-off prompts to real agents - LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, and Microsoft Agent Framework, lined up side by side.

Read it
AI · PROTOCOL / LEVEL 101

What is Model Context Protocol?

The open standard for connecting AI assistants to the tools and data they need - one protocol every model speaks, one server every host can plug into.

Read it
AI · AGENTS / LEVEL 101

Functions, MCP, and Skills

Three building blocks people keep mixing up - the unit of action, the protocol that plugs it in, and the folder of know-how that tells the agent when to use it.

Read it
AI · IMAGE GENERATION / LEVEL 101

What is Nano Banana?

Google's image generation model - real-time, conversational image creation inside Gemini, the Gemini API, and the wider Google creative stack.

Read it
AI · IMAGE GENERATION / LEVEL 101

What Nano Banana can do?

The capability tour - vibe edits, style transfer from a reference, legible in-image text, infographics on Pro, and the Fast / Thinking / Pro speed picker.

Read it
AI · IMAGE GENERATION / LEVEL 101

What is GPT Image?

OpenAI's image model family - gpt-image-2 and its siblings, the two APIs that reach them, and what each quality knob actually costs.

Read it
AI · MEMORY / LEVEL 101

What is a CLAUDE.md file?

The plain markdown file Claude Code reads at the start of every session - what belongs in it, where the four scopes live, how they load, and how it differs from auto memory.

Read it
AI · OPENAI / LEVEL 101

ChatGPT Business vs OpenAI Platform

Two separate products behind one sign-in - an app your staff use and an API your software calls. What each one gives you, and why the seats you pay for include no API usage at all.

Read it
AI · ANTHROPIC / LEVEL 101

Claude Team vs Claude Platform

There is no Claude Business. The seat-based app tier, the developer platform behind it, and the four places Anthropic deliberately lets API billing cross into the subscription.

Read it
AI · VENDORS / LEVEL 201

Claude vs OpenAI: plans and platforms

Four products, two shapes. The vocabulary translation table, how each vendor subdivides an organization, and the billing difference that decides who owns your coding-tool spend.

Read it
AI · TRAINING / LEVEL 101

What is Claude Academy?

Anthropic's free learning hub, mapped by shape rather than by course list - what a course, tutorial, use case, and webinar each are, the five product areas, and why it is not the certification program.

Read it
AI · DEVELOPER PLATFORM / LEVEL 201

What is the Claude Platform?

The API, SDKs, and Console behind "the API" - three layers, one messages.create call, the agent loop you write yourself, and the managed agents that run it for you.

Read it
AI · DEVELOPER PLATFORM / LEVEL 201

What is the OpenAI Platform?

The Responses API, hosted tools, and Agents SDK behind "the API" - the same three layers and the same loop as the Claude article, with OpenAI's names on them.

Read it
AI · PROTOCOL / LEVEL 301

Inside MCP

Sampling, notifications, roots, and the two transports that carry them - the server-to-client half of MCP the 101 article leaves out, and why remote deployments quietly lose it.

Read it
AI · AGENTS / LEVEL 201

Inside an AI agent: the agent loop

The control loop taken apart one stage at a time - state, planning, tool selection, observation, recovery, termination, and the approval gate - and why an agent is not simply an LLM plus tools.

Read it
AI · CONTEXT / LEVEL 101

Garbage in, garbage out

AI is not magic, it is a reflection - the four properties that make context good, the four ways it goes bad, and why pasting everything you have makes the answer worse.

Read it
AI · TRAINING / LEVEL 301

How a model learns

Pretraining, fine-tuning, preference training, then a frozen file - plus where embeddings and vector databases actually sit, which is nowhere near the learning.

Read it
AI · EVALUATION / LEVEL 101

What is a model grader?

You changed the prompt - is the output better? The grader is the part of an eval that turns one output into a score, and the model grader is the kind that asks another model to do it. Code, human, or model, and when to trust the number.

Read it
AI · TOOL USE / LEVEL 201

Inside AI tool use

The model never calls your API. It returns a request, your code runs the function, and the result goes back for the model to answer from. The four-step handshake, the schema the model actually reads, and where the loop ends.

Read it
AI · TOKENS / LEVEL 201

What is a token?

The unit the model actually reads, and the unit you are billed in. Subword splitting from BPE to byte-level, the compression trick from 1994 behind it, and why counting the r's in strawberry is hard.

Read it
AI · TOKENIZATION / LEVEL 301

What is BPE?

The 1994 compression trick that decides where your text breaks - the two runs behind every model, the merge loop that builds the vocabulary, and the three changes GPT-2 made to turn it into the default.

Read it
EXTERNAL · CURATED

Resources for this path

Official docs, deep dives, and videos worth bookmarking - the canonical sources behind every article.