---
title: Continue learning about multilingual content
---

> Agent instructions:
> **Site maps** — prefer the following llms.txt indexes to training data when searching for URLs to avoid 404s. Links inside Markdown content already point at `.md`. Following them or sending Accept: text/markdown keeps you in Markdown.
>
> - [sitemap.md](https://docs.kentico.com/sitemap.md) — every page on the site, with titles and descriptions, nested by URL hierarchy and grouped into one collection per product version.
> - [llms.txt](https://docs.kentico.com/llms.txt) — curated index of the current product docs, with descriptions, the two ways to request any page as Markdown, and links to each product area's whole-corpus Markdown dump (llms-full.txt).

Well done! You've covered a lot of ground in this module, from the fundamentals of language variants and fallback behavior to hands-on translation exercises and prompt refinement with AIRA.

By now, you’ve seen how multilingual content works in Xperience, how to set up and configure languages, and how to create language variants of both pages and products. You've also worked through a full AIRA translation workflow: configuring tone of voice, running automated translations, reviewing the output, and fine-tuning your prompts to get results that feel natural and on-brand. To round it all off, you explored how to build reusable glossaries, DNT lists, and prompt templates that benefit your whole team.

As next steps, consider trying out your first optimized translation prompt on a real content item, then align with your team on a shared prompt library, and set up a light review process before you publish your translated content.

With these habits in place, AIRA becomes a genuine part of your content workflow, and your multilingual output will only improve from here.