# Working with AI

> Practical AI for everyone, not just ML engineers - prompting, agents, CLIs, MCP, skills and plugins, context and loop engineering, and getting real work done with AI. The hype-free user's manual.

16 guides.

- [What an AI Assistant Really Is](https://themissingmanual.dev/guides/what-ai-assistants-really-are) _(beginner)_ - Demystify the thing behind the chat box: a model that predicts text, wrapped in tools and a loop. Once you see the three parts, agents stop being magic.
- [Prompting That Actually Works](https://themissingmanual.dev/guides/prompting-that-works) _(beginner)_ - Stop guessing at magic words. Clear instructions, the right context, and a few reliable patterns get better results than any secret prompt.
- [When to Trust AI](https://themissingmanual.dev/guides/trusting-ai-output) _(beginner)_ - AI sounds equally confident when it is right and when it is making things up. Learn why, and the habits that catch the difference before it costs you.
- [AI Privacy and What Not to Paste](https://themissingmanual.dev/guides/ai-privacy-and-safety) _(beginner)_ - Before you paste that document into a chatbot, know where it goes and what could come back to bite you. A practical privacy guide for everyday AI use.
- [AI Agents, Explained](https://themissingmanual.dev/guides/ai-agents-explained) _(beginner)_ - An agent is a chatbot that can act: it plans, uses tools, looks at the result, and tries again. Here is the loop, the power, and where to keep it on a leash.
- [AI in the Terminal (CLIs)](https://themissingmanual.dev/guides/ai-in-the-terminal-clis) _(intermediate)_ - Coding agents that live in your terminal can read files, run commands, and edit code on your say-so. The workflow, the habits, and how the main CLIs compare.
- [AI in Your Editor](https://themissingmanual.dev/guides/ai-in-your-editor) _(beginner)_ - From autocomplete to a chat that knows your codebase: how editor AI like Copilot and Cursor actually helps, and the one discipline that keeps it from hurting.
- [What Is MCP (Model Context Protocol)](https://themissingmanual.dev/guides/what-is-mcp) _(intermediate)_ - MCP is the standard plug that lets an AI assistant talk to your tools and data, the same way USB-C connects any device. What it is, how it is shaped, and how to add one safely.
- [Skills and Plugins](https://themissingmanual.dev/guides/ai-skills-and-plugins) _(intermediate)_ - Two ways to extend an AI assistant: skills teach it reusable know-how, plugins give it new powers. What each is, how they differ, and how to add or write your own.
- [Context Engineering](https://themissingmanual.dev/guides/context-engineering) _(intermediate)_ - The model only knows what is in front of it. Context engineering is the craft of controlling that window: what to include, what to cut, and what to pull in on demand.
- [Loop Engineering](https://themissingmanual.dev/guides/loop-engineering) _(intermediate)_ - The newest piece of the agent puzzle: designing the act-check-repeat loop so the AI corrects itself instead of confidently finishing wrong. A practical look at a term still settling.
- [Vibe Coding](https://themissingmanual.dev/guides/vibe-coding) _(beginner)_ - Building software by describing what you want and letting AI write it. What vibe coding is, where it genuinely shines, and where it quietly bites.
- [RAG in Plain English](https://themissingmanual.dev/guides/rag-explained-simply) _(intermediate)_ - Retrieval-augmented generation is how you get an AI to answer from your documents instead of its memory. The idea, the moving parts, and why it goes wrong.
- [Running AI Locally (Ollama)](https://themissingmanual.dev/guides/local-ai-with-ollama) _(intermediate)_ - Run a capable model on your own machine: private, free per use, and offline. What Ollama does, how to start, and the real tradeoffs versus the big cloud models.
- [Automate Your Work with No-Code and AI](https://themissingmanual.dev/guides/automate-work-with-ai) _(intermediate)_ - The crossover that makes both worlds click: a no-code automation that calls an AI step. Triage, summarize, and draft on autopilot, with guardrails so it does not run wild.
- [Building a Multi-Agent System](https://themissingmanual.dev/guides/building-a-multi-agent-system) _(advanced)_ - When one agent juggling too much starts dropping things, the fix is splitting work across several narrower agents. The real orchestration patterns, and the failure modes that come with them.