Observability Agent Technical Overview

Overview

Monte Carlo's Observability Agent is an internally developed application that uses licensed models from Anthropic (accessed via Amazon Bedrock) to ask questions of your data platform.

We've created this section to provide a technical overview of the observability Agent and answer frequently asked questions. For technical specs, such as Model Types and Versions click here.

How the Observability Agent Works

Users interact with the agent through a web interface, where they can ask questions. The agent accesses internal data, like alerts history, assets, and monitors, by securely connecting to the organization’s servers. Each user sees only their own conversations.

Data Privacy & Data Retention

The Observability Agent relies on AI Models provided by Amazon Bedrock (within AWS), in addition to a monitoring application provided by LangChain (LangSmith). They are noted on our Subprocessors page.

As the same policies apply from the Troubleshooting agent to the Observability agent, see Privacy Considerations for the Troubleshooting Agent for additional information. No customer sampling data is processed in the observability agent.