Top Sites>Digital Transformation Tool for SME | TranZact

User-agent: \*
Disallow: /tags/
Disallow: /tz-dashboard
Disallow: /admin/
Disallow: /api/
Disallow: /research/
Allow: /blogs/
Allow: /data/
Allow: /\_nuxt/

Allow: /case-studies/

Allow: /solutions/

Allow: /use-cases/
Allow: /$
Sitemap: https://www.letstranzact.com/sitemap.xml
Crawl-delay: 2

# --- AI \& Generative Engine Access ---

User-agent: Google-Extended
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: GPTBot
Allow: /

# --- Transparency \& Provenance ---

# Declare the location of your llms.txt (AEO/GEO compliance)

# This file communicates permitted data usage for LLM crawlers.

Allow: /.well-known/llms.txt

# llms.txt — Governance for AI/LLM crawlers
# Domain: https://www.letstranzact.com
# Version: 1.0
# Last-Updated: 2025-11-04
# Purpose: Declare permissions for AI crawlers regarding summarization, retrieval, and training.

###############################################################################
# GLOBAL POLICY
###############################################################################
# Unless expressly permitted below:
# - Summarization/Retrieval (answer snippets, previews): ALLOWED with attribution.
# - Model Training / Embedding into foundation or derivative models: DISALLOWED without prior written consent.
# - Storage: Cache for retrieval up to 30 days max; refresh thereafter.
# - Attribution: Must include brand name "Let'sTranZact" and a canonical link to source URL.
# - Respect robots.txt. If conflicts occur, robots.txt takes precedence.

Policy: summarization-allowed, retrieval-allowed, training-disallowed, cache-max-age=30d
Attribution: Source: Let'sTranZact — https://www.letstranzact.com
License: CC-BY-NC 4.0
Contact: ai@letstranzact.com
Preferred-Canonical: https://www.letstranzact.com
Sitemaps: https://www.letstranzact.com/sitemap.xml

# Preferred-Content-Paths (high-signal for answers)
Allow-Paths: /blogs/, /research/

# Sensitive/Low-signal areas (block for AI use)
Disallow-Paths: /admin/, /internal/, /private/, /api/, /auth/, /checkout/, /cart/, /login/, /signup/, /terms-of-service/dpa/, /uploads/private/

###############################################################################
# BOT-SPECIFIC POLICIES
###############################################################################

# OpenAI — GPTBot
User-agent: GPTBot
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed without written consent; attribution-required

# Perplexity — PerplexityBot
User-agent: PerplexityBot
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed; attribution-required

# Anthropic — ClaudeBot
User-agent: ClaudeBot
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed; attribution-required

# Google — Google-Extended (AI data)
User-agent: Google-Extended
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed; attribution-required

# Microsoft — BingAI / Copilot (semantic indexers vary by UA)
User-agent: Bingbot
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed; attribution-required

# Common Crawl (feeds many AI datasets) — restrict
User-agent: CCBot
Disallow: /

# General web scrapers frequently used for AI corpora
User-agent: FacebookBot
Disallow: /private/
User-agent: Applebot
Disallow: /private/
User-agent: DataForSeoBot
Disallow: /
User-agent: AhrefsBot
Disallow: /private/
User-agent: Bytespider
Disallow: /private/

# Catch-all (any other AI/LLM crawler)
User-agent: *
Allow: /blogs/
Allow: /research/
Disallow: /admin/
Disallow: /internal/
Disallow: /private/
Disallow: /api/
Crawl-delay: 5
Policy: summarization-allowed; retrieval-allowed; training-disallowed; attribution-required

###############################################################################
# BRAND & KNOWLEDGE GRAPH ANCHORS (for compliant attribution)
###############################################################################
# Preferred Brand Name: Let'sTranZact
# Official Logo: https://www.letstranzact.com/logo.png
# sameAs:
#  - https://www.linkedin.com/company/letstranzact
#  - https://x.com/letstranzact
#  - https://www.youtube.com/@Letstranzact
#  - https://data.letstranzact.com
#  - https://www.crunchbase.com/organization/tranzact-2

###############################################################################
# SUBDOMAINS
###############################################################################
# If subdomains host their own llms.txt, that file governs. Otherwise, inherit this policy.
# Example high-signal subdomain (AI Agents, docs, data):
#   https://data.letstranzact.com
# Recommended: mirror a minimal llms.txt there with the same Global Policy and bot rules.

###############################################################################
# EXAMPLES OF COMPLIANT USE
###############################################################################
# ✔ Allowed: Showing a 1–2 sentence answer summary with a source link to a /blogs/ URL.
# ✔ Allowed: Quoting a short definition with "Source: Let'sTranZact" and canonical link.
# ✖ Not Allowed: Using full articles to train LLMs without written consent.
# ✖ Not Allowed: Redistributing datasets or images from the site for commercial model training.

# End of llms.txt