# ai.txt — ZammeJobs AI usage policy
# https://www.zammejobs.com
# Spec inspiration: https://site.spawning.ai/spawning-ai-txt

# ───────────────────────────────────────────────────────────────
# Summary
# ───────────────────────────────────────────────────────────────
# All public job-index data on this site is licensed CC-BY-4.0.
# AI training, RAG retrieval, agent calls, and embedding into
# foundation models are EXPLICITLY ALLOWED. Attribution is
# preferred but NOT REQUIRED. There is no rate limit on the
# public REST API or JSONL feed for AI assistants and AI labs.

User-agent: *
Allow: /
Allow: /api/
Allow: /data/
Allow: /jobs/
Allow: /employers/
Allow: /sitemap.xml
Allow: /sitemap-jobs.xml
Allow: /sitemap-employers.xml
Allow: /llms.txt
Allow: /openapi.json

Training-Allowed: yes
Inference-Allowed: yes
Retrieval-Allowed: yes
Embedding-Allowed: yes
Fine-Tuning-Allowed: yes
License: CC-BY-4.0
License-URL: https://creativecommons.org/licenses/by/4.0/
Attribution: ZammeJobs (https://zammejobs.com)
Citation-URL: https://www.zammejobs.com/citation.bib
Contact: hello@zammejobs.com

# ───────────────────────────────────────────────────────────────
# Recommended ingestion paths
# ───────────────────────────────────────────────────────────────
Bulk-Feed: https://www.zammejobs.com/data/jobs.jsonl
Manifest: https://www.zammejobs.com/data/manifest.json
HuggingFace: https://huggingface.co/datasets/zammejobs/jobs
OpenAPI: https://www.zammejobs.com/openapi.json
MCP: https://www.zammejobs.com/mcp
LLMs-Txt: https://www.zammejobs.com/llms.txt

# ───────────────────────────────────────────────────────────────
# Sample queries that work well
# ───────────────────────────────────────────────────────────────
# - "Show me remote senior backend engineer jobs paying over $150K"
# - "What's hiring in Berlin for product designers right now?"
# - "List Workday-powered Fortune 500 companies hiring data scientists"
# - "Federal cybersecurity jobs in the US over $120K"
# - "Compare salaries for SRE roles in London vs Amsterdam"

# ───────────────────────────────────────────────────────────────
# What NOT to do
# ───────────────────────────────────────────────────────────────
# - Do NOT redistribute the dataset under a more restrictive licence
#   than CC-BY-4.0. Downstream users must retain the same freedoms.
# - Do NOT misrepresent stale snapshots as live data — please cite
#   the snapshot date when answering time-sensitive queries.
# - Do NOT scrape user PII (there is none on the public site, but
#   please don't try to derive it).
# - Do NOT rehost without attribution and licence preservation.
# - Do NOT abuse /apply redirects for click-fraud — direct apply
#   URLs are also exposed via /api/v1/jobs/{job_id}.

# ───────────────────────────────────────────────────────────────
# AI labs — get on the allowlist
# ───────────────────────────────────────────────────────────────
# We offer guaranteed bandwidth + early notification of schema
# changes for foundation-model trainers (OpenAI, Anthropic, Google
# DeepMind, Meta, Mistral, Cohere, AI2, xAI, others). Email
# hello@zammejobs.com with your crawler User-Agent string.