IT Let’s talk

Digipa AI · 04

Ask your data. In plain language.

Natural-language questions on your management software, CRM and databases: answers with numbers, charts and the query that produced them.

Book a 30-minute call What you get

The problem

The data is there, but every new question needs someone to build a report. An AI layer on top of the systems you already have lets decision-makers ask directly, in plain language.

Every answer shows the query that produced it, so anyone can check it. Access is read-only and follows the permissions of each role.

Example questions

  • “Revenue by region in the third quarter, compared with last year.”
  • “Which projects are running over budget?”
  • “The 10 customers who cut their orders the most in the last 6 months.”
  • “Send me a summary of the sales KPIs every Monday.”

How it works

From question to answer, verifiably.

  1. Question

    Decision-makers ask in plain language, as they would ask a colleague.

  2. Translation

    The system translates the question into a query on the authorised data.

  3. Check

    The query is visible and can be checked, results are tracked in the logs.

  4. Answer

    Numbers, a chart and a summary in natural language.

  • Your data stays yoursHosting in Europe or on your own servers. No model training on your data.
  • Sources always citedEvery answer shows the document or query it comes from. If there is no source, the assistant says so.
  • A human in the loopHand-off to a person when needed, human approval for anything that commits the company.
  • Measured, not promisedA set of real questions agreed at the start and re-run after every change.

What you get

Six deliverables, no black boxes.

  1. 01

    Source map

    Management software, CRM, databases and spreadsheets: what is there and what it means.

  2. 02

    Semantic layer

    Company glossary and shared metric definitions.

  3. 03

    Question → query engine

    Read-only, role-based access, with the query always visible.

  4. 04

    Chat and dashboards

    Web interface with exportable charts and summaries.

  5. 05

    Alerts and summaries

    Anomalies flagged and KPIs by email on a fixed schedule.

  6. 06

    Quality tests

    Real business questions re-run after every change.

Where it runs

Three hosting levels, your choice.

  1. Level A

    API under contract

    Commercial models via API, with a data processing agreement. The quickest to get started.

  2. Level B

    European cloud

    Models running on dedicated infrastructure in EU data centres. A balance of power and control.

  3. Level C

    On your servers

    Open-weight models installed on premise. No data leaves your perimeter.

How we start

From the first meeting to ongoing management.

  1. Discovery call

    30 minutes, free: use cases, available data, constraints.

  2. Pilot

    One or two real use cases, with an agreed test set and success criteria.

  3. Roll-out

    Integration with your systems, permissions, logs and user training.

  4. Management

    Monitoring, content updates and periodic re-evaluation of the models.

Who builds your AI

Engineers who run real data, in production.

We don’t show AI case studies we don’t have. We show what we run every day: DroneDB, our open-source platform for geospatial data, where we index, search and protect terabytes of files with multi-level permissions.

Discover DroneDB
1,300
active users on DroneDB
2,500
organisations
4.5 TB
of data managed
290★
on GitHub, MPL-2.0 code

Figures published on dronedb.app and GitHub, October 2026.

FAQ

Before we start

Does it replace our BI tool?

No: it is a layer that sits on the data and tools you already have, to answer the questions that don’t have a report yet.

How do you avoid wrong results?

With a shared metric glossary, queries that are always visible and a set of test questions re-run after every change.

Does our data leave the company?

It depends on the hosting level you choose: with on-premise models no data leaves your infrastructure.

Other Digipa AI solutions

01

Custom AI

Open-weight models on your servers or in a European cloud, with search across company documents (RAG), permissions respected and sources always cited.

02

AI training

Hands-on courses on the tools your team actually uses, tailored to each role and documented as an AI literacy measure under the AI Act (Art. 4).

03

AI for customer care

An AI assistant on your website, WhatsApp and helpdesk that answers from your official information and hands over to a person when needed.

Free introductory call

Let’s talk about AI for business intelligence.

A free 30-minute call with an engineer: use cases, available data and a concrete idea of timings and costs.

Book the call +39 02 9166 5401