Article
The AI Agent Code of Conduct: Automated Guardrail Policy-as ...
arxiv.org
Quoted on this wiki
Every place a page here uses this source, in the order the words come in it.
6Limitations “Future work includes leveraging production interaction logs (inputs, outputs, tool calls, actions) to mine candidate rules and hard examples that continuously enrich the policy tree and prompts” References
Abstract “We introduce "Policy as Prompt," a new approach that uses Large Language Models (LLMs) to interpret and enforce natural language policies by applying contextual understanding and the principle of least privilege.” 1Introduction
Abstract “Our system first ingests technical artifacts to construct a verifiable policy tree, which is then compiled into lightweight, prompt-based classifiers that audit agent behavior at runtime.” 1Introduction