# AI Safety

Try @Human Buy @Human Subscription Join @Human Community

### Safety by Design @Human Agentic comes with a significant list of safety features. These are likely to evolve as AI technology evolves and will always remain a top priority for Planet Crust. ### Essential Features #### Active/Inactive Setting All Agents can be easily switched on or off

#### Model Choice LLM Provider and Model choice is exclusively set by the Administrator

#### Temperature The randomness "Temperature" of any Agents can be set individually

#### Budget Controls Token count and iterations can be controlled on a per Agent basis

#### Timeouts Excessive looping and other expensive runtime errors can be mitigated

#### Behavioral Guardrails An unlimited number of guardrails can be specified per Agent

#### Internal Knowledge Base Dedicated internal knowledge bases can be used to guide Agentic behaviour

#### MCP Policy An MCP Policy enforces local data access

... and access to Automation tools

#### RBAC Integration Agentic access can be integrated with the @Human RBAC system

--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.planetcrust.com/human-agents/ai-safety.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.