Glossary

Agent: An intelligent AI component specialized for specific data management tasks (e.g., Data Quality Agent, Catalog Agent).

Asset: A data object such as a table, database, file, or dataset managed within your data catalog.

Conversation: An interactive session between a user and ADM where context is maintained across multiple messages.

Knowledge Base: Repository of organizational documents that enhance ADM's responses with company-specific context.

LLM (Large Language Model): The AI model that powers ADM's natural language understanding and generation capabilities.

MCP (Model Context Protocol): Open standard for connecting ADM with external tools and services like Google Drive and Gmail.

Notebook: Collection of queries that can be executed together and scheduled for regular runs.

Policy: Set of data quality, governance, or compliance rules applied to data assets.

Policy Score: Percentage indicating overall data quality health, calculated from policy execution results.

Prompt: Text input provided to ADM to elicit a response or action.

Response Style: Setting that adjusts how ADM formats and presents information (e.g., Data Engineer, Business Analyst).

Slash Command: Shortcut command starting with / that triggers specific actions or workflows.

Thought Process: ADM's reasoning steps shown before generating a response, providing transparency into AI decision-making.

Token: Text chunk processed by LLM; approximately 4 characters equal 1 token.

Workflow: Multi-step automated process that guides users through complex data management tasks.