On-premise · source-grounded · enterprise-grade RAG

Your organisation's expertise,
queryable in plain language.

kroons is a single-tenant, retrieval-augmented knowledge platform that turns terabyte-scale document corpora into a citable answer engine — deployed inside your own infrastructure, governed by your own access policies.

What is the bearing replacement interval for the API 610 pumps on project 20560? Ask

Bearings on the centrifugal pumps in this project are replaced every 8,000 operating hours, with torque specified at 45 Nm. The figure is drawn directly from the maintenance datasheet…

[source: pump_spec_v3.pdf, p.12]

The platform

Retrieval-augmented intelligence, engineered for the enterprise

A purpose-built stack that combines hybrid retrieval, contextual indexing and large language models — without ever surrendering your data or trusting a black box.

Hybrid retrieval

Dense semantic vectors and keyword search run in parallel, fused and neurally re-ranked so the most relevant passage surfaces — by meaning, not just matching words.

Mandatory citations

Sources are injected by the system, not invented by the model. Every answer carries a verifiable file-and-page reference you can open in one click.

Multilingual by design

Language-agnostic embeddings let users query in their own language across corpora written in another — Italian questions over English standards, and beyond.

Contextual ingestion

A two-pass pipeline extracts document structure, then enriches every passage with section-level context before indexing — dramatically sharpening retrieval on dense technical material.

Role-based governance

Project-scoped access control means users only ever retrieve what they're cleared to see — enforced at the data layer, not painted over in the UI.

Structured-data agent

Beyond documents, a natural-language agent queries your relational project databases — cost sheets, equipment registers, inspection logs — under the same interface.

The pipeline

From raw corpus to grounded answer

An operator-supervised pipeline that turns an unstructured document store into a precise, governed retrieval index.

1

Ingest & stage

Source documents are scanned, diffed against the index, and queued for operator review before anything changes.

2

Structure & contextualise

A two-pass pass extracts hierarchy and section context, then enriches each passage for unambiguous retrieval.

3

Embed & index

Contextualised passages are vectorised into a high-performance index alongside a parallel keyword index.

4

Retrieve & generate

Hybrid search, fusion and re-ranking feed a language model that answers strictly from the retrieved evidence.

The architecture

A layered platform, deployed on your terms

Cleanly separated layers — each independently deployable and scalable — with your documents and indexes held entirely on-premise.

Access & identity
Signed-token authentication and role management gate every request before it reaches your data.
Interface
A unified workspace — knowledge assistant, document browser and structured-data agent under one session.
Core & ingestion services
On-premise retrieval, generation and indexing engines, reachable only over a mutually-authenticated encrypted channel.
Knowledge store
A vector + keyword index over your corpus, sized for terabyte-scale libraries and team-wide concurrent access.
Single-tenantyour own isolated deployment
On-premisecore, indexes and files stay local
Model-flexibleswap language models per deployment
Domain-agnosticconfigurable metadata per project

Security & governance

Grounded, governed, and yours

The platform is built to keep answers anchored to your evidence and your data inside your perimeter. If the documents don't support an answer, it says so rather than inventing one.

Every answercarries a verifiable source citation
Project-scopedaccess enforced at the data layer
Files never leaveonly retrieved excerpts are processed
Encryptedservice-to-service and secrets at rest

See kroons running on your own corpus

We're preparing the platform for wider deployment. Reach out for a technical walkthrough, a tailored evaluation, or to discuss early access.

Contact us →