Guides — AI Hub
10 articles on Guides from AI Hub.
Context Engineering, Explained
Curating what a model sees — system prompt, retrieved docs, tool output, memory — not just what you ask it. Bigger context windows made this harder, not easier.
Self-hosted LLM stack in 2026
A practical guide to running Ollama, Open WebUI, and MCP tools on a home NAS — privacy-first, no cloud lock-in.
How coding agents actually work
From autocomplete to autonomous: how terminal-native coding agents read a repo, plan, edit, run tests, and iterate — and where they still break.
What is RAG, in plain English?
Retrieval-augmented generation explained without the jargon — when you need it, when you don't, and common pitfalls.
How to pick an LLM for your use case
Cloud vs. local, context length, cost per token, and latency — a decision tree for builders and architects.
AI agents: what can go wrong in production
Tool misuse, prompt injection, runaway loops, and audit trails — the guardrails checklist before you ship.
Real-time voice AI, explained
Speech-to-speech models replaced the old three-step pipeline. What changed, where it's used, and where it still stumbles.
Video generation models, in plain English
How text-to-video actually works, what changed from 4-second clips to coherent scenes, and why it's still not final-pixel production ready.
Reasoning models and test-time compute
Why 'thinking' models spend extra compute before answering, when that trade is worth it, and when it's just added latency for no gain.
Multi-Agent Orchestration Explained
Why teams split monolithic agents into planner, worker, and reviewer roles — common patterns, when it pays off, and when it's pure overhead.