> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tartini.com.br/llms.txt
> Use this file to discover all available pages before exploring further.

# Teach the AI with your website

> Paste your website's link and choose exactly which pages Tino learns, at no cost to discover what's there.

export const Artigo = ({titulo, href, children}) => <a className="lista-artigos-item" href={href}>
    <span className="lista-artigos-texto">
      <span className="lista-artigos-nome">{titulo}</span>
      {children ? <span className="lista-artigos-desc">{children}</span> : null}
    </span>
    <svg className="lista-artigos-seta" viewBox="0 0 24 24" width="18" height="18" aria-hidden="true">
      <path d="M9 6l6 6-6 6" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round" />
    </svg>
  </a>;

export const Lista = ({titulo, children}) => <div className="lista-artigos">
    {titulo ? <p className="lista-artigos-titulo">{titulo}</p> : null}
    <div className="lista-artigos-itens">{children}</div>
  </div>;

Syncing a site imports the content from your pages into the knowledge base, with full control over what comes in: you decide which pages Tino actually learns.

<Note>
  Who can see this: Administrator and Company Manager. Available on all plans. The public audience requires the Scale plan.

  The Tartini interface is in Portuguese. Screen and button names appear here exactly as on screen, with the translation in parentheses.
</Note>

***

## Sync a site

By default, the page mapping includes the subpages of the given domain.

Where to find it: **Cérebro > Propriedades** (Cérebro > Properties), **Site** button.

<Steps>
  <Step title="Open the form">Click **Site**, in the Add group (or, with an empty list, the **Sincronizar site** (Sync site) card).</Step>
  <Step title="Choose the audience">Check **Conhecimento Público** (Public Knowledge) or **Conhecimento Privado** (Private Knowledge).</Step>
  <Step title="Enter the URL">Type the address in **URL do Site** (Site URL), for example `exemplo.com/ajuda`.</Step>
  <Step title="Map the site">Click **Mapear site** (Map site).</Step>
</Steps>

<Note>
  Mapping is free: it discovers the site's pages without indexing anything. Only indexing (processing the content) consumes credits.
</Note>

***

## Map for free and choose what to index

After mapping, the screen lists all the pages found, organized by folder.

<Steps>
  <Step title="Review the pages">Check the pages you want to index, or click **Selecionar tudo** (Select all).</Step>
  <Step title="Filter, if needed">Use **Filtrar páginas...** (Filter pages...) to find a specific page.</Step>
  <Step title="Index">Click **Indexar N página(s)** (Index N page(s)).</Step>
</Steps>

<Note>
  From 50 selected pages on, the screen asks for an extra confirmation, because indexing many pages can take a few minutes and consume more credits.
</Note>

***

## Add pages later

An already synced site can receive new pages without redoing the whole process.

Where to find it: the site's details panel (in **Cérebro > Propriedades**), **Adicionar páginas** (Add pages) button.

<Steps>
  <Step title="Open the site's details">Click the site's row in the Properties list.</Step>
  <Step title="Click Add pages">The site is mapped again automatically.</Step>
  <Step title="Check the new pages">Pages already indexed show the **já indexada** (already indexed) badge and can't be checked again.</Step>
  <Step title="Confirm">Click **Adicionar N página(s)** (Add N page(s)).</Step>
</Steps>

***

## Reindex an already registered site

If you try to sync a URL that's already registered, the screen warns that the site already exists and offers to reindex. Confirming deletes the previous content and replaces it with the new one.

To update the content of already indexed pages without deleting anything or discovering new ones, use **Reindexar** (Reindex) in the site's details panel: the extracted text of each subpage is updated.

<Note>
  These are two different actions: reindexing from the duplicate-site warning deletes and replaces the previous content; reindexing from the details panel updates the text of already indexed pages without deleting anything.
</Note>

***

## The high-volume notice

Sites with 50 or more pages selected at once show a notice before indexing, because the process can take a few minutes and consumes more credits. You can go back to review the selection or proceed anyway.

***

## Frequently asked questions

<AccordionGroup>
  <Accordion title="Does mapping a site cost credits?">
    No. Only indexing, which actually processes the content, consumes credits.
  </Accordion>

  <Accordion title="Can I add more pages after already syncing a site?">
    Yes, from the site's details panel, with the Add pages button.
  </Accordion>

  <Accordion title="What happens if I try to sync a site that's already registered?">
    The screen offers to reindex, which replaces the old content with the new one.
  </Accordion>
</AccordionGroup>

***

## Related articles

<Lista>
  <Artigo titulo="Register the company's properties" href="/en/cerebro/propriedades-da-empresa">See, edit, and manage what's already been registered.</Artigo>
  <Artigo titulo="Use the knowledge base intelligence" href="/en/cerebro/inteligencia-da-base">Review what Tino discovered from your website.</Artigo>
</Lista>


## Related topics

- [Training the Cérebro](/en/primeiros-passos/guias/treinando-o-cerebro.md)
- [Getting Started with Tartini](/en/primeiros-passos/guias/comecando-com-o-tartini.md)
- [Teach the AI with documents](/en/cerebro/documentos.md)