How it works
The three services behind NQRust Analytics and what happens when you ask a question.
NQRust Analytics combines a product UI, an AI service, and a context/modeling layer so that you can ask business questions without working directly against raw database schemas.
The three core services
Analytics UI
The user-facing application. This is where you:
- connect data sources
- define models and relationships
- ask questions
- review answers, charts, and saved results
- manage users, roles, and dashboards
Analytics Service
The AI service handles retrieval, prompting, SQL generation, and result validation. Rather than sending a raw prompt directly to an LLM, it converts a user question into a grounded query workflow, retrieving the relevant business context first.
Analytics Engine
The engine provides the context and modeling foundation. It manages metadata, business definitions, and SQL translation so the system works from business-aware context rather than schema alone. A companion Ibis Server handles the Python data-transformation layer.
What happens when you ask a question
At a high level, the flow proceeds as follows:
- You ask a question in the Analytics UI.
- The Analytics Service retrieves the most relevant business context for that question.
- The Analytics Service uses that context to generate SQL.
- The Analytics Engine validates and executes the query against the connected data source.
- The Analytics UI shows the answer, a result preview, and any related chart or follow-up questions.
Why the system is split this way
Keeping these responsibilities separate keeps each part focused:
- Analytics UI focuses on user workflow and interaction.
- Analytics Service focuses on retrieval and generation.
- Analytics Engine focuses on context, modeling, and execution.
That separation makes it easier to improve one part without forcing the UI, the AI workflow, and the business-context layer into a single tightly coupled service.