Define AI Assistant 'Assumptions' or Defaults for when a user doesn't give context to a natural language query

When a user enters a natural language question, they may not give the full context to the question.

Our data warehouse fact tables have upto 20 dimension tables. When a user asks a question they would typically only supply a few dimensions in the context. For example "Show sales for TVs this year". This question only provides context for two dimensions - product and time. No context is given to all the other dimensions - sales method, sales person and so on. with simple measures and simple additive dimensions, assumming ALL when no context is given is usually ok. However this is rare in an enterprise data warehouse.

The data source modeller should be able to provide default context about the query if the user question is not explicit.

Another example "show the forecasted tv sales for this year". A business will typically have multiple forecasts. The user question has not specified which forecast they want to see. As no context has been given, the AI assistant will assume ALL forecasts which would sum all the forecasts!

As no context has been given to the forecast dimension, the data source modeller should be able to tell the AI to assume the latest forecast.

Another example "compare region 1 sales between 2023 and 2022".
If there was a reorganisation of the regions between the years, then the modeller should be able to tell the AI assistant that the assumption is a like for like answer (such as only showing open stores).

These assumptions would also help business authors. Again, if they create a report and are not explicit in the Forecast, the report will use the data model assumption of latest forecast.