Sources of Context

Holistics AI uses the following sources for context. To improve the accuracy and relevance of AI answers, you can add more information to these sources.

From the modeling layer

• Datasets:

  • Metadata: name, label and description
  • relationships between data models
  • context > analysis including underlying views for View Underlying Data and breakdown groups for Drill Down & Break Down
  • tags

• Data models:

  • Metadata: name, label and description
  • tags

• Fields (dimensions, measures, and metrics):

  • Metadata: name, label, type and description
  • definition

From the reporting layer

• Dashboards:

  • Metadata: name and label
  • blocks: visualization blocks, text blocks, controls and filters
  • tags

• Visualizations:

  • Metadata: label
  • Fields and filters used in the visualization
  • Result data (if shared with Holistics AI)

Organization settings

When you go to Development > settings > ai, you will find a file context.aml. This file is a dedicated place to provide organization-level context to Holistics AI. Refer to Organization Level Context for more details.

Other context sources

• Prebuilt context by the Holistics Engineering team: Role and scope of the AI, product knowledge, feature guidelines, AQL foundations, and documentation knowledge.
• User's current chat: Questions asked within the ongoing conversation.
• Auto-learning context: User preferences (for example: concise responses, more suggestions)