#****************************************************************************
# robots.txt | ise.org.br
# Atualizado em: 08/2026
#
# Politica: site aberto a buscadores tradicionais e a crawlers de IA.
# Bloqueios restritos a areas administrativas, busca interna e um PDF legado.
# Indice para sistemas de IA: https://ise.org.br/llms.txt
#
#****************************************************************************

# --- Regras gerais ---
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /*?s=
Disallow: /*?replytocom=
Disallow: /wp-content/uploads/2018/10/family-office-report-2018-ise_ineo_.pdf

# --- Crawlers de IA: acesso liberado, mesmas restricoes acima ---
# Treinamento: GPTBot, ClaudeBot, Google-Extended, Applebot-Extended,
#              meta-externalagent, CCBot
# Indexacao de resposta: OAI-SearchBot, Claude-SearchBot, PerplexityBot, Amazonbot
# Acesso disparado por usuario: ChatGPT-User, Claude-User, Perplexity-User
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: MistralAI-User
User-agent: DuckAssistBot
User-agent: CCBot
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /*?s=
Disallow: /*?replytocom=
Disallow: /wp-content/uploads/2018/10/family-office-report-2018-ise_ineo_.pdf
Allow: /

Sitemap: https://ise.org.br/sitemap_index.xml