Lumen Analytics

A new category

Built for autonomous analysis.

AI-ready BI and data governance.

Governed AI Analytics — every BI and data governance contract in 2027 will be evaluated on whether it's ready for what comes next: AI on top of your data, autonomous analysis, agents doing the plumbing your analysts hate. Lumen does that. It is built from the ground up governed AI analytics.

Fig. 1 One path, one policy.
no bypass
Lumen architecture Two consumer rails (knowledge worker via conversational analytics, and agents over MCP or REST) converge into the Substrate trust layer, then into DataSource and existing data. knowledge worker consumer agents MCP · REST conversational analytics Lumen Substrate trust layer policy · audit · refusal DataSource governed SQL existing data warehouse · lake
Every query is compiled into governed SQL by the Substrate layer — whatever the consumer.

01What we are

An analyst notebook on top of a trust layer.

The surface

Lumen

The analyst notebook. Ask in natural language, get an answer with the query, the chart, the narrative, and the sources attached. The AI does the plumbing the analyst hates; the human owns the judgement. Every cell is reproducible, every chart links to its query, refusal is honest when the data won't support a claim.

The trust layer

Substrate

A semantic model curated by your information manager — definitions, joins, sensitivity classes, access policies — compiled into governed SQL on every query, with audit attached to every answer. The same enforcement chain runs whether the consumer is Lumen, an agent over MCP, a REST client, or a future BI tool. There is no bypass.

02Why this works when “talk to your data” did not

Three architectural commitments most pilots fail.

The pilot that dies at the DPO's desk bypass
User AI tool raw data leak policy bolted on top — bypassable prompt sees what it shouldn't
The pilot that ships no bypass
User Lumen Substrate trust layer data policy in the query layer — in the path refusal is a typed output, not a hallucination
  1. No raw sensitive values leave the controlled backend.

    Pseudonymisation happens before the prompt is built. The external LLM never sees what it should not see.

  2. Policy lives in the query layer, not the UI.

    Row-level access, masking, disclosure thresholds are compiled into the SQL. No client can bypass.

  3. Refusal is a real answer.

    “I cannot answer this from the available sources” is a typed output with a named category, not a hallucinated number. The system would rather decline than guess.

03The reference

Proef — the first deployment, live.

Flemish dept. of Culture, Youth & Media

The Flemish department of Culture, Youth, and Media is shipping AI-assisted analytics for their policy analysts. The architecture committee approved it earlier this year. A five-year procurement is in flight.

Their DPO signed off on the architecture before the first line of policy-enforcement code shipped — because the architecture made the answer to her objections legible. They run on the same kernel you would run on. The semantic pack they built for the cultural sector will be in the open repository.

04How we sell

The DPO is in the first conversation.

The first technical conversation includes your DPO and one of your security people. Most analytics vendors hide from compliance until contract review and then lose. We invite them in early because the architecture is written to be read by them, and a DPO who has read it and agreed to it before procurement starts is the difference between a pilot that ships and a pilot that dies.

The 60-minute conversation is free.

· 60 minutes
· Free
· DPO + security in the room
· Architecture, not slides

05About

Solo founder. Two government contexts. One live deployment.

Lumen is built by Luk Verhelst. Eighteen years in data engineering and architecture across the banking sector, the Flemish public sector, and regulated-industry consulting. The information-manager role we centre the product on is one I have been, in two different government contexts. The first deployment (Proef, with CJM) is live; the second deployment is the next twelve months of conversations.

· 18 years — data engineering & architecture
· Banking sector
· Flemish public sector

06Next step

A 60-minute architecture conversation, with your DPO in the room.

luk@lumen-analytics.com
No form. No newsletter. One reply, from Luk, within two working days.