# AI.txt - Instructions for AI crawlers and LLMs
# This file follows the emerging ai.txt standard for AI agent instructions

# Site Information
Site-Name: Kevin Herbas
Site-URL: https://kevinherbas.com
Site-Description: Freelance AI engineer sharing generative automation pipelines, large-scale scraping, and production-grade Python practices.
Primary-Language: en
Author: Kevin Herbas
Contact: contact@kevinherbas.com

# Crawling Preferences
User-agent: *
Allow: /
Disallow: /og/
Preferred-Format: markdown
Preferred-Schema: JSON-LD

# AI-Specific Bots
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /
Crawl-delay: 1

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Perplexity
Allow: /

User-agent: Applebot
Allow: /

User-agent: Googlebot
Allow: /

# Content Guidelines
Content-Type: educational, technical, tutorial
Topics: ai-automation, python, fastapi, langchain, data-pipelines, web-scraping, backend-architecture
Tone: conversational, practical, friendly
Target-Audience: developers, engineers, students

# Citation Preferences
Citation-Required: yes
Attribution: "Kevin Herbas (kevinherbas.com)"
License: CC-BY-4.0
Last-Updated: 2025-02-15

# API Endpoints for AI
JSON-API: /api/content.json
Sitemap: /sitemap-0.xml
RSS: /rss.xml
Structured-Data: JSON-LD in page head

# Content Structure
Blog-Posts: /blog/
Categories: /blog/category/
Tags: /blog/tag/
About: /about/
Projects: /projects/

# Opt-in for AI Features
Allow-Training: yes
Allow-Citation: yes
Allow-Summarization: yes
Allow-Q&A: yes
Allow-Code-Examples: yes

# Restrictions
No-Spam: true
No-Scraping-For-Ads: true
Respect-Copyright: true

# Quality Signals
Content-Updated-Regularly: yes
Fact-Checked: yes
Author-Verified: yes
Code-Tested: yes

# Preferred Citation Format
# Please cite as: "Source: Kevin Herbas, [Article Title], kevinherbas.com/blog/[slug]"