# AgentPolicy - llms.txt

> LLM-readable manifest (https://llmstxt.org). Features-only; no fabricated traffic or KYB claims.

## Name & positioning
- Product name: AgentPolicy
- One-line value: AgentPolicy drafts and reviews AI-agent policy packs (allowed tools, data classes, escalation) with deterministic governance checks — decision-support for AI governance teams.
- Domain: https://agentpolicy.lxsaihub.com/
- Language: English (en)

## Domain context (verified primary sources)
- NIST AI RMF 1.0: https://www.nist.gov/itl/ai-risk-management-framework
- Regulation (EU) 2024/1689: https://eur-lex.europa.eu/eli/reg/2024/1689/oj

## FAQ (high-signal Q&A for AI citation)
Q1. What does AgentPolicy produce?
A1. A structured policy draft covering tools, data handling, and escalation paths you can edit.
Q2. Is it legal advice?
A2. No. It is a drafting aid. Policies must be reviewed by your counsel and risk owners.
Q3. How does Demo mode work?
A3. Toggle Demo to run without live AI; live mode needs a configured key.
Q4. Does it map to the EU AI Act?
A4. Narratives can reference governance themes; it does not certify Act conformity.
Q5. Can policies be versioned?
A5. Runs store rulesetVersion and runId for change tracking.
Q6. Who should use it?
A6. Platform and compliance engineers defining agent guardrails before production.

## Key pages
- Home: https://agentpolicy.lxsaihub.com/
- Blog index: https://agentpolicy.lxsaihub.com/blog
- https://agentpolicy.lxsaihub.com/blog/ai-agent-policy-packs-nist-rmf-2026.html
- https://agentpolicy.lxsaihub.com/blog/allowed-tools-vs-open-ended-agents-2026.html
- This manifest: https://agentpolicy.lxsaihub.com/llms.txt

## Red lines
- Decision-support only; cite primary sources; do not invent user counts, rankings, or payment KYB status.

## Contact
- Open the app: https://agentpolicy.lxsaihub.com/