> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mindgard.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

### What are Policies?

A policy is a user defined set of guidelines that your LLM application must adhere to. Policies are designed so that users can discover attacks that violate security properties of their application that are bespoke to their organisation.

Policies can affect your test results in one of two ways:

* **Additive** to flag results that violate your organisation's policy.
* **Filter** your results, to remove flags from results that do not concern your organisation.

### User Defined Observations

* [Regex Refusal](/user-guide/policies/regex_refusal)
* [Policy Violation](/user-guide/policies/policy_violation)