# Runa

> Hands-on books on technology and applied AI, written by an SRE in the financial sector. Real examples, copy-ready code and prompts. Available on Amazon.

Digital publisher of hands-on books on technology and applied AI. The site is the showcase; sales happen on Amazon.

## Books
- [Zero to AI](https://readruna.com/en/books/zero-to-ai.md): Go from zero to using AI at work in 30 days, no code.
- [GEO: Get Cited by AI](https://readruna.com/en/books/geo-get-cited-by-ai.md): Show up when people ask AI for a recommendation.
- [Prompts That Work](https://readruna.com/en/books/prompts-that-work.md): Stop improvising: use tested prompts for every task.
- [Selling with AI](https://readruna.com/en/books/selling-with-ai.md): Sell more with AI without becoming a programmer.
- [AI Agents in Practice](https://readruna.com/en/books/ai-agents-in-practice.md): Build agents that get work done and know when to stop.

## Learning paths
- [Get into AI](https://readruna.com/en/paths/get-into-ai.md): Use AI at work within 30 days — no coding required.
- [AI in production](https://readruna.com/en/paths/ai-in-production.md): Ship LLMs and agents to production — safely.
- [Sell with AI](https://readruna.com/en/paths/sell-with-ai.md): Get found by AI assistants and sell more with agents.

## Author
- [Felipe Auleon](https://readruna.com/en/author.md): Site Reliability Engineer in the financial sector

## Articles
- [How to run LLMs in production: a 10-point checklist](https://readruna.com/en/articles/how-to-run-llms-in-production.md): A practical checklist for running LLMs in production safely: SLOs, observability, cost caps, prompt injection, fallbacks and runbooks. An SRE's view.

## AI Glossary
- [AI agent](https://readruna.com/en/glossary/ai-agent.md): An AI agent is a system where an LLM decides, in a loop, which tools to use (fetch data, call APIs, run code) to reach a goal, until it finishes or asks for help.
- [Embedding](https://readruna.com/en/glossary/embedding.md): An embedding is a list of numbers that represents the meaning of a text, so that texts with similar meaning end up close together in vector space.
- [GEO (Generative Engine Optimization)](https://readruna.com/en/glossary/geo.md): GEO is the set of practices that get a brand, product or piece of content found and cited in answers from AI assistants such as ChatGPT, Gemini, Claude and Perplexity.
- [Hallucination (AI)](https://readruna.com/en/glossary/hallucination.md): A hallucination is when an AI model produces false or non-existent information that looks true, such as a made-up quote, number or reference.
- [LLM (Large Language Model)](https://readruna.com/en/glossary/llm.md): An LLM is an AI model trained on massive amounts of text to predict the next word, which lets it answer questions, summarize, translate and write code.
- [Prompt injection](https://readruna.com/en/glossary/prompt-injection.md): Prompt injection is an attack where malicious text, from a user or a document, tries to make the LLM ignore its original instructions and do something else.
- [RAG (Retrieval-Augmented Generation)](https://readruna.com/en/glossary/rag.md): RAG is the technique of retrieving relevant passages from a document base and handing them to the LLM along with the question, so the answer is grounded in real, current sources.
- [SLO (Service Level Objective)](https://readruna.com/en/glossary/slo.md): An SLO is a reliability target for a service, expressed as the percentage of good events over a time window — for example, 99.9% of responses under 2 seconds over 30 days.

## Optional
- [For business](https://readruna.com/en/business)
- [Catalog as JSON](https://readruna.com/catalog.json)
- [Full version](https://readruna.com/en/llms-full.txt)