Operations agent

The Operations Agent is the main conversational interface inside Monte Carlo. It is the single entry point for interacting with your Data + AI Observability platform through natural language -- ask questions, take action, and let it route you to the right specialized agent when a task calls for one.

How to access

The Operations Agent is the chat interface available in the Monte Carlo UI. Navigate to the Agentic Operations section to start a conversation.

What it can do

Answer questions directly

The Operations Agent can handle a wide range of questions and actions on its own:

• "Are there any alerts assigned to me in the past day?"
• "How's the health status of table X?"
• "What are some trends and patterns in my alerts?"
• "When was my table Y last updated?"
• "What assets and reports would this data issue impact?"
• "Can I deprecate table X?"
• "Add a comment to X alert."

All operations exposed by the Monte Carlo MCP Server are available to the Operations Agent. See the MCP Server documentation for full details.

Route to specialized agents

When a request requires deeper analysis or a specialized workflow, the Operations Agent automatically routes to the right agent:

You do not need to navigate to each agent separately. Simply describe what you need, and the Operations Agent determines the best agent to handle it.

Using AI agents in your IDE

The Operations Agent works inside Monte Carlo's UI. If you prefer working from AI coding agents like Claude Code or Cursor, Monte Carlo offers a separate path:

• MCP Server -- connects your IDE agent directly to Monte Carlo.
• Agent Toolkit -- pre-built skills that teach your agent to monitor data, triage alerts, validate code changes, and more.

Ask support

You can ask questions about your Monte Carlo setup, integrations, monitors, and more.

You can also create support tickets directly from the Operations Agent if you need additional help or deeper investigation.

FAQ

What permissions does the Operations Agent have? What data can it access?

The Operations Agent runs with the same permissions as the user interacting with it. As a result, it cannot perform any action or access any data that the user themselves cannot.