Enterprise / Sovereign AI

Enterprise Intelligence Assistant for Live Data and Documents

Client A US enterprise

Text to SQLRAGContinued PretrainingSovereign AI

For a US enterprise, Jungroo AI built an assistant that answers plain-English questions across a real-time stream of structured data in databases and unstructured data in documents and reports. It runs inside the client's environment and shows the query or passage behind every answer. On held-out questions, end-to-end accuracy rose from 52% with the base model to 92% after domain adaptation.

The challenge

Teams needed answers from two kinds of live data: tables that change through the day, and documents and reports. A general open-weight model answered only 52% of their questions fully right. It didn't know the company's internal codes and terms, and the data couldn't leave the company's environment.

The solution

Jungroo AI built one assistant on its four-layer sovereign stack, inside the client's environment:

  • Live Ingestion: Databases and documents are ingested as they change: tables into Postgres with a graph of the schema, and documents into a vector store with source, date and access metadata.
  • Question Routing: A small decision model sends each question to the database, the documents or both, and asks the user to clarify when it isn't sure.
  • Schema-Aware SQL: An entity model marks what the question names, and GraphRAG walks the schema graph, so the model writes SQL against only the tables it needs. A failing query is repaired and run again.
  • Domain-Tuned Retrieval: A retriever trained on the company's own questions finds the passages that answer them.
  • Domain-Adapted Model: Continued pretraining on the company's own documents, then fine-tuning on five tasks: writing SQL, fixing SQL, building charts, summarising and reasoning.
  • Cited Answers: Every answer shows the SQL it ran or the passages it used, and every question is logged with its route, sources and answer.

The impact

Impact

MeasureBeforeAfter
End-to-end accuracy52% with the base model92% after domain adaptation
Internal vocabularyNot trained on internal documentsLearned through continued pretraining

Only the model's training changed between the two results: the same pipeline, retrieval and held-out questions were used for both. An LLM judge graded each final answer, and a question counted only if the route, the data, the answer and its sources were all right.

Have a similar challenge?

See how this would work on your data.

We can benchmark a domain model on one of your tasks in two weeks, at no cost, or start with a short briefing call.

Contact

Tell us what you need.

We partner with a limited number of enterprises at a time, so every engagement gets senior attention. Tell us what you want to build, and our leadership will reply.

We use these details only to reply to you. What you type is saved as you go, so we can still reply if you leave before pressing Send. Privacy

General enquiries

Jungroo AI Labs

Partnerships, projects and products

Leadership

Sethuraman T A

Chief Executive Officer

Engineering

Cibe Hariharan

Chief Technology Officer