AI Safety

Try @HumanBuy @Human SubscriptionJoin @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