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

# System Overview

> The runtime inspection layer between your GenAI application and the LLM.

Protector Plus deploys as an **inline runtime defence layer** between AI-driven applications and their LLM endpoints. The platform is **LLM-agnostic** — supporting cloud-hosted models (OpenAI, Anthropic, Google Gemini), open-weight models (Llama, Mistral, AI Singapore SEA-LION), and customer-self-hosted models on the same architecture.

## Logical layout

<Frame caption="ShieldPrompt™ protects prompts and responses end-to-end across first- and third-party LLMs; the AI Security Portal manages policy, surfaces analytics, and forwards events to the customer's SIEM.">
  <img src="https://mintcdn.com/cloudsineai-5cd7c547/GGS4yz3OwEKS-tHW/images/diag-shieldprompt.png?fit=max&auto=format&n=GGS4yz3OwEKS-tHW&q=85&s=119e030010f0c6ecd7de8d6497e57807" alt="Protector Plus + ShieldPrompt architecture" width="1198" height="645" data-path="images/diag-shieldprompt.png" />
</Frame>

## Two services, both over HTTPS

<CardGroup cols={2}>
  <Card title="Management Console" icon="gauge">
    Web UI for tuning security policies, reviewing alerts, generating API keys, and configuring SIEM forwarding.
  </Card>

  <Card title="Guardrail Service API" icon="bolt">
    HTTPS endpoints for prompt inspection (`/input-check`) and response inspection (`/output-check`). Can be called directly by the application or through an LLM gateway.
  </Card>
</CardGroup>

## Design principles

<AccordionGroup>
  <Accordion title="Agentless adoption" icon="plug">
    No agents on web servers or inside the GenAI application. Integration is HTTP-level — fast, low-friction onboarding without infrastructure changes.
  </Accordion>

  <Accordion title="Scalable & trackable deployment" icon="arrows-up-down">
    Designed for horizontal scaling. In the Kubernetes variant, additional capacity is provisioned through standard Helm chart configuration. Updates ship through CD pipelines — infrastructure as code.
  </Accordion>

  <Accordion title="Coverage for emerging threats" icon="shield-virus">
    The LLM-powered engine catches evasive threats in near-real-time. The Threat Vector Database provides a continuously updated library of malicious prompt patterns without requiring model retraining.
  </Accordion>

  <Accordion title="Manageable by multiple custodians" icon="users-gear">
    Role-based, fine-grained permissions support administration by multiple parties — typically separating the platform Super Admin from per-application owners.
  </Accordion>
</AccordionGroup>

## Where to next

<CardGroup cols={2}>
  <Card title="Deployment modes" icon="route" href="/architecture/deployment-modes">
    Forwarding and non-forwarding topologies.
  </Card>

  <Card title="Detection layers" icon="layer-group" href="/architecture/detection-layers">
    Standard Guardrails and ShieldPrompt.
  </Card>
</CardGroup>