AI: The Complete Guide
Retrieval-Augmented Generation (RAG) is the pattern of grounding an LLM's answer in documents fetched at query time instead of relying only on what the model memorised during training. A RAG system turns your knowledge base into embeddings, stores them in a vector database, and at question time retrieves the most relevant chunks to inject into the prompt. This guide pulls together everything on Onexial tagged ai — 121 connected nodes across definitions, workflows, tool stacks, comparisons, prompts and applied use cases — and orders it the way you would actually learn it: vocabulary first, then process, then tooling, then execution. Every item below links to a full node with its own examples and connections, so you can go as deep as you need without losing the map.
Core concepts behind AI
Before wiring anything together, the vocabulary has to be precise. These 88 definitions cover the terms that show up in almost every AI discussion — each one links to a full entry with an example and its own connections inside the graph.
AI Agent
An autonomous AI system that plans and executes multi-step tasks.
RAG (Retrieval-Augmented Generation)
Inject external knowledge into an LLM at query time.
Prompt Chaining
Pipelining LLM calls where each step's output feeds the next.
LLM Orchestration
Coordinating multiple model calls, tools, and data sources into one reliable system.
Vector Database
A database optimized for similarity search over embeddings.
AI SDR (Sales Development Rep)
An autonomous system that researches, qualifies, and contacts leads.
Vibe Coding
Building software by describing intent in natural language and letting AI generate the code.
MCP (Model Context Protocol)
Open protocol that lets LLMs connect to tools, data sources and apps through a standard interface.
Agentic RAG
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.
Embedding
A numerical vector representation of text, image or audio that captures meaning for similarity search.
Fine-Tuning
Continuing to train a base model on your own examples to specialize its behavior.
AEO (Answer Engine Optimization)
Optimizing content to be cited by AI answer engines like ChatGPT, Perplexity and Google AI Overviews.
Workflows: how AI runs end to end
Concepts only matter once they become a repeatable process. Below are 6 documented workflows that apply AI to a concrete problem, with the steps, the tools involved and the variations worth testing.
How to Create a Website with AI
Go from idea to a live, custom-domain website in one afternoon using AI builders.
How to Build an AI Content System
A repeatable pipeline that turns one input into publish-ready content across every channel.
How to Start a Niche Website with AI
Pick a niche, validate demand, build the site, and publish ranking content using AI end-to-end.
Personal Research Assistant Workflow
A repeatable system to research any topic deeply in under 30 minutes.
Build a Tier-1 Customer Support Agent
An agent that handles common tickets end-to-end and hands off the rest.
Turn Deep Research Into a Weekly Executive Brief
Use an AI Deep Research agent every Monday to produce a cited market brief in 20 minutes.
The AI tool stack
A stack is a set of tools chosen for one job, not a list of favourites. These 1 stacks show which combinations hold up in production for AI, and what each layer is actually responsible for.
Trade-offs and comparisons
Most AI decisions are trade-offs rather than right answers. These 26 comparisons break down the real differences, when each option wins, and the recommendation for the common case.
ChatGPT vs Claude
Two leading conversational AI assistants compared across reasoning, writing, coding, and pricing.
Lovable vs Bolt
Two AI app builders compared on speed, backend, deployment, and production readiness.
OpenAI API vs Anthropic API
Choosing between the two leading LLM API providers for production apps.
Lovable vs Cursor
Prompt-to-app builder vs AI-assisted code editor — which one should you reach for?
Perplexity vs ChatGPT Search
Two answer engines, two philosophies: citation-first research vs conversational assistant.
OpenAI vs Gemini for Agent Building
Both ship strong models and SDKs — differences are in tool calling, context and pricing.
RAG vs Long Context Windows
Is RAG obsolete now that context windows are 1M+ tokens? Not quite — here's when each wins.
LangChain vs LlamaIndex
Both are Python/JS frameworks for LLM apps. LangChain leans agents; LlamaIndex leans RAG.
Best AI Workflow Automation Tools: n8n vs Zapier vs Make
The three tools most operators consider for AI workflow automation — compared on pricing, AI integration and technical flexibility.
Claude vs GPT vs Gemini
The three frontier model families, side by side.
Claude Sonnet vs Opus
When to spend up within the Claude family.
Llama vs Mistral
Two leading open-weight families.
Frequently asked questions
- What does RAG stand for?
- Retrieval-Augmented Generation. The model retrieves relevant documents at query time and generates an answer grounded in them.
- When should I use RAG instead of fine-tuning?
- Use RAG for factual, changing or private knowledge — docs, tickets, product data. Use fine-tuning for consistent style, format or a narrow behaviour that prompting cannot reach.
- Do I always need a vector database for RAG?
- No. For small corpora, in-memory search or keyword search (BM25) can outperform a naive vector setup. Vector DBs shine when you have thousands+ documents and need semantic recall.
- How does RAG reduce hallucinations?
- By passing the retrieved passages into the prompt and asking the model to answer only from them (with citations), the surface area for fabrication drops sharply — though prompt design and reranking still matter.
- What does MCP actually stand for?
- Model Context Protocol. It is an open standard for exposing tools, resources and prompt templates to AI models over a JSON-RPC channel.
- Who created MCP?
- Anthropic released the specification in November 2024. OpenAI, Google, Microsoft, Cursor and most agent frameworks have since adopted it.
- How is MCP different from an OpenAI plugin or a Claude tool call?
- Plugins and tool calls are proprietary and tied to one vendor. MCP is a shared protocol: one MCP server works with Claude, ChatGPT, Cursor, VS Code, custom agents and anything else that speaks MCP.
- Do I need to run my own MCP server?
- Only if you want to expose your own data or tools. Public MCP servers already exist for GitHub, Postgres, Notion, filesystems and hundreds of SaaS tools.