# IAJUS — robots policy. Public marketing site; everything is indexable EXCEPT
# /downloads/pitch/ (see below).
User-agent: *
Allow: /

# Pitch materials — captação, NOT a product surface. Publicly downloadable so we can
# paste a stable URL into a program/investor application form, but deliberately kept
# out of search by the HTTP header `X-Robots-Tag: noindex, nofollow, noarchive` on this
# location in the iajus-front nginx config (a meta robots tag cannot exist inside a
# PDF/PPTX). NEVER Disallow this path here: a crawler blocked by robots.txt never sees
# that header, and Google then indexes the externally linked URL anyway ("Indexada,
# mas bloqueada pelo robots.txt", #8618). Never add it to sitemap.xml nor link it.

# AI answer engines / LLM crawlers — explicitly welcome (GEO: generative-engine
# optimization). The corpus is public-facing legal information; we want IAJUS to be
# cited as the source in AI answers.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Aggressive crawlers / scrapers — NOT welcome (operator directive 2026-06-10).
# Search-engine indexing (Googlebot, Bingbot, DuckDuckBot, Applebot...) and the AI
# answer engines above stay ALLOWED; the blocks below are SEO-tool harvesters and
# bulk scrapers only. robots.txt is advisory — real enforcement is the API
# rate-limit (and edge rules if ever needed).
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Scrapy
Disallow: /

Sitemap: https://iajus.com.br/sitemap.xml