Platform Overview

Introduction

BlueRock Dashboard is a platform for monitoring, analyzing, and governing activity across AI agent applications and their supporting services.

BlueRock Sensors running in the BlueRock host generates obervability events in OTEL format at runtime for AI agentic and MCP application workloads and sends it to BlueRock Dashboard for visibility, security, policy management, cost analysis, and investigation.

The platform provides a centralized view of activity and relationships across agents, MCP servers, LLMs, tools, sessions, and related events.

BlueRock Capabilities

The BlueRock Dashboard provides the following capabilities:

• Visibility Charts: Provides visibility into operational and security activity across the environment.

• Graph Explorer: Provides an interactive view of entities and their relationships, allowing users to explore activity and trace related events.

• Policy Management: Provides centralized management of security and governance policies, including creation, review, approval, revision, and deployment.

• Cost Management: Provides visibility into token usage, estimated spend, and cost-related activity.

• Alert Rules: Provides rule-based monitoring that evaluates activity and generates alerts when configured conditions are met.

• Investigation: Provides a structured workspace for investigating observed entities and activity.

Architecture and Data Model

A typical BlueRock deployment consists of one or more BlueRock Hosts and a BlueRock Dashboard.

The BlueRock Host is the customer workload environment where AI agent applications, MCP applications, and their associated BlueRock sensors run.

Each monitored application can have its own BlueRock sensor. The sensors collect activity from the applications and send events to the bluerockd service running on the BlueRock Host.

The bluerockd service collects the sensor events and sends the resulting telemetry directly to the BlueRock Dashboard using OTLP.

The BlueRock Dashboard hosts the bluerockccpd application and provides the Dashboard UI and services for processing and presenting the collected activity.

At a high level, activity flows through the platform as follows:

Customer Workload → BlueRock Sensors → bluerockd → OTLP → BlueRock Dashboard

BlueRock Dashboard represents relationships between entities in the monitored environment. At a high level, these relationships include:

Host → Agent → LLM / MCP Server → Tool

Events are associated with these entities and grouped to provide context for activity within a session.

This data model allows users to understand how activity flows through the environment and investigate relationships between agents, LLMs, MCP servers, tools, sessions, and events.

Graph Explorer provides a visual way to explore these relationships and trace related activity.

---