Monitoring Agent Technical Specs
Purpose & Functionality
Generates intelligent recommendations for custom data quality monitors; assesses schema, metadata, query history, and data samples to detect patterns and coverage gaps; recommends monitor logic (e.g., anomaly detection, null thresholds, formatting consistency.)
Model Details & Testing
Source of AI Model [Application]
Internally developed by Monte Carlo, including the agent orchestration, recommendation logic, context and user interface.
Source of AI Model [Foundational Model]
Licensed from third-party – Anthropic; accessed via Amazon Bedrock
Model Provider
Anthropic via Amazon Bedrock & OpenAI
Model Type
LLM-powered agent
Version
Claude Haiku 3.5 + GPT-4o
Testing [Application]
Monte Carlo only uses internal test data for testing purposes. No customer data is used to test or train.
Testing [Foundational Model]
Responsibility of the respective AI model provider.
Fairness and Bias
No applicable due to domain-specific, non-human context
Primary and optional use cases
System Requirements
Works with existing implementation of Monte Carlo, operating on the customer's cloud data warehouse. Data Sampling must be turned on.
Prompt/Input Requirements
Automatically gathered by Monte Carlo: structured inputs include data schema, historical query logs, column-level profiles, and metadata.
Acceptance Rate
~60% of Monitoring Agent recommendations are accepted by users
Continuous Monitoring Plan
Monte Carlo captures telemetry data (using OpenTelemetry) on the model behaviors; Monte Carlo monitors quality of responses in production using LLM-as-a-judge monitors; customer feedback loop informs future iteration of the agent.
Updated about 5 hours ago