Predictive and analytical AI on your enterprise data
UNID AI Predict: predictions and analysis straight from your enterprise data
UNID AI Predict connects an AI assistant to a company’s tables (customers, contracts, invoices, ledger entries). The assistant writes queries, checks data for anomalies and delivers predictions from a relational foundation model. The numbers always come from data and models, never from the language model. If required, everything runs on the customer’s infrastructure.
Last updated:
Animated sample view: a worklist shows the policies with the highest cancellation risk in the next 90 days, sorted by premium at risk. Clicking a policy shows the reasons from the data and the next best products. A backtest shows how the insurer checks the prediction themselves.
Animated sample view: a controller asks the AI assistant for the top five customers and the query is shown. The assistant then checks invoices for VAT errors and shows the ledger line behind each finding. Finally a prediction model lists customers likely to stop ordering, using a local language model.
Three capabilities
Ask in plain language
The assistant turns your question into a database query, runs it and shows it. You see where every number comes from.
Check
Rules and anomaly detection, such as wrong VAT rates, duplicates or missing details, each with the evidence rows.
Predict
Rankings such as “who is likely to cancel” or “who buys what next”, with reasons from the data.
Explained
What is a relational foundation model?
A relational foundation model is an AI model pre-trained on many linked tables that predicts directly from your database structure: customers, contracts, invoices and how they relate. Instead of months of hand-built features, you describe what should be predicted. A well-known example is KumoRFM, described in a published research paper.
How you check the prediction yourself
Hidden cut-off date
You give us data up to a cut-off date. What happened afterwards (who cancelled) you keep.
Ranking
We deliver a ranking for the period after the cut-off without knowing the outcomes.
Your comparison
You compare: our list against reality and against your existing model or a simple rule.
Agreed criterion
Agreed up front: which result makes a pilot worthwhile.
Important: a backtest shows how good the ranking is, not how much you save. Savings only show in a pilot with a control group.
Deployment
| Deployment | Where the data sits | Language model |
|---|---|---|
| On your infrastructure | In your data centre, without outside connection if required | Local model |
| On a dedicated server | On a server operated for you | Local or cloud, as agreed |
| With cloud models | Data stays in your database; only query results go to the model | Cloud model with processing agreement |
Use cases
Cancellation early warning for insurers
A weekly ranking of the policies most likely to be cancelled, weighted by premium at risk, with reasons and the next best product.
Learn more →Finance & controllingAI assistant for finance data
Ask your ledger and sales data in plain language, run VAT and anomaly checks with evidence rows, and forecast things like customer churn.
Learn more →Predict compared
| UNID AI Predict | Classic data-science project | BI dashboard | Chat assistant with CSV upload | |
|---|---|---|---|---|
| Predictions | from linked tables | yes, after feature engineering | no | unreliable |
| Plain-language questions | yes, query shown | no | limited | yes, small files |
| Origin of every number | query and model | model | report | often unclear |
| Time to first result | weeks | months | weeks | minutes |
| On-premise possible | yes | yes | depends on product | usually no |
General assessment, not a test of specific products.
What it does not do
- It needs clean keys and time columns in the tables. We check that at the start.
- It makes no decisions about individuals and is not meant for pricing; people decide.
- Against a well-tuned existing model the margin can be small. That is why we test first.
Governance
- A person decides (human in the loop)
- Log of every query
- Read-only access to your data
- Model card and fairness report
- Processing agreement under Art. 28 GDPR, or fully on-premise
FAQ
Frequently asked questions
What is predictive AI on enterprise data?
How does a relational foundation model differ from a language model?
Do we need a data science team?
What data do you need?
Does data leave our premises?
How do you explain a single prediction?
Does the EU AI Act apply?
See it working on your own material.
In a 30-minute call we show the products live and work out which use case makes sense for you first. No obligation, in German or English, in Vienna or online.
UNID AI · Leonard-Bernstein-Straße 10 · 1220 Vienna · +43 660 476 30 89