# AI & Machine Learning

> Models, training, and putting AI into real products - without the hype or the hand-waving.

13 guides.

- [What AI & Machine Learning Actually Are](https://themissingmanual.dev/guides/what-ai-and-ml-are) _(beginner)_ - AI is a big umbrella, machine learning is the part of it that learns rules from examples instead of being hand-coded, and today's chatbots are powerful pattern-matchers - not minds - that can be confidently wrong.
- [How a Model Learns (Training, in Plain English)](https://themissingmanual.dev/guides/how-a-model-learns) _(beginner)_ - What 'training' actually does to a machine learning model - a model is a bundle of adjustable numbers, and training nudges those numbers until its predictions match known examples.
- [Using an LLM API in Your App](https://themissingmanual.dev/guides/using-an-llm-api) _(beginner)_ - Calling a hosted language model is a normal HTTP request: you POST a list of messages, you get back generated text - and this guide builds the mental model, the cost picture, and the reliability habits you need to ship it without a foot-gun.
- [Prompt Engineering, Honestly](https://themissingmanual.dev/guides/prompt-engineering-honestly) _(beginner)_ - What actually improves the output of a language model - clear, specific, well-structured instructions - and what's just folklore, explained without the hype.
- [Prompt Engineering, Plainly](https://themissingmanual.dev/guides/prompt-engineering-plainly) _(beginner)_ - What actually improves the output of a language model - clear, specific, well-structured instructions - and what's just folklore, explained without the hype.
- [Embeddings & Vector Search, Explained](https://themissingmanual.dev/guides/embeddings-and-vector-search) _(intermediate)_ - What an embedding actually is (meaning turned into a list of numbers), how 'nearness' between two pieces of text is measured, and how vector databases search millions of them by meaning instead of keywords.
- [RAG (Retrieval-Augmented Generation), Explained](https://themissingmanual.dev/guides/rag-explained) _(intermediate)_ - What RAG actually is - retrieving the right facts from your own data first, then asking the model to answer using them - why an LLM needs it, how the pipeline works end to end, and why good RAG is mostly good retrieval.
- [Running Models Locally](https://themissingmanual.dev/guides/running-models-locally) _(intermediate)_ - What it really means to run an LLM on your own machine - the clear-eyed trade-off against a hosted API, a real Ollama session from download to local API call, and how model size, RAM/VRAM, and quantization decide whether it runs at all.
- [Fine-Tuning vs Prompting, Plainly](https://themissingmanual.dev/guides/fine-tuning-vs-prompting) _(advanced)_ - When training your own model is - and isn't - worth it: prompting steers at request time, RAG adds knowledge, fine-tuning changes the model's default behavior, and the no-nonsense order is to try them cheapest-first.
- [Evaluating LLM Output](https://themissingmanual.dev/guides/evaluating-llm-output) _(intermediate)_ - Evals, not vibes: how to measure whether an LLM feature actually works, catch prompt regressions, and ship changes with confidence.
- [Building an AI Agent](https://themissingmanual.dev/guides/building-an-ai-agent) _(intermediate)_ - What an agent actually is under the hood: the model plus tools plus a loop. Function-calling, the reasoning-acting cycle, and where agents go wrong.
- [Prompt Injection and Guardrails](https://themissingmanual.dev/guides/prompt-injection-and-guardrails) _(intermediate)_ - Why untrusted text in an LLM's prompt is dangerous, how injection hijacks the model, and the guardrails that actually contain it.
- [How a Neural Network Is Structured](https://themissingmanual.dev/guides/how-a-neural-network-is-structured) _(intermediate)_ - The structural anatomy of a neural network - layers, weights, biases, activation functions, and how one prediction flows through it - without touching how training works.