Legal Tech
Wolters Kluwer
Asking your data questions in plain English
Business users just type their question in normal language. Behind the scenes a semantic layer makes sure the answer comes from the right, governed dataset.
Results achieved
Faster data access
Explainable data queries
Fewer ad-hoc requests
The challenge
Business teams needed analytics support for every operational question about products or campaigns. This created a bottleneck for decision making and tied up analysts with repetitive requests.
Our approach
- 1.Build a semantic layer to map business concepts to data structures.
- 2.Translate plain text into SQL queries with strict execution limits.
- 3.Deploy the architecture within the existing cloud environment.
- 4.Run a pilot with business users to validate the outputs.
The solution
A self-service platform where business teams query datasets using plain text. The semantic layer ensures the results remain consistent and explainable.
AzureLLMSQLSemantic layer