Tyla

The engine that keeps facts with their source and date.

Tyla stores facts with their source and the period in which they were valid. Rules a person can read derive the answers, and every answer shows the facts and rules behind it. It runs in your data centre or in the EU.

What you build with Tyla

Three applications you can build with Tyla.

Contracts and prices

Which terms applied on a given date?

Every contract, amendment and price list with its validity period. You get the terms that applied to an order on its date, with the document that set them.

Compliance and deadlines

Which obligations are due, and since when?

"Report within 30 days of an incident" becomes a rule with a time window. Tyla lists every case that meets it on a given day.

Suppliers and sanctions

Which partners are critical today?

Lists, registers and ownership data change. Tyla keeps every version and flags a supplier that was on a sanctions list in the last 90 days.

Data comes from your databases, files and documents. A language model can read documents. Where rules exist for a kind of fact, Tyla validates the extracted facts against them before it stores them.

How it works

Tyla builds every answer from stored facts.

A language model holds implicit knowledge: tendencies in its weights, without a source or a date. Tyla works with explicit knowledge: every fact with its source and the period in which it was true. In 2028 you can show an auditor exactly what you knew in 2026.

  • Cited. Every fact links to the document or record it came from.
  • Dated. "What did we know on 14 March?" is an ordinary query.
  • Corrections keep their history. A corrected fact is stored as a new version with its date. The old version stays, so earlier decisions remain explainable.
One fact in TylaSupplier Nordtek
  1. Not on any sanctions listValidUntil 9 January 2026SourceEU sanctions list, as of 2 January 2026
  2. On the EU sanctions listValid10 January to 28 February 2026SourceOfficial Journal of the EU, 10 January 2026
  3. Removed from the listValidSince 1 March 2026SourceOfficial Journal of the EU, 1 March 2026

Example with an invented supplier. A new version never overwrites the old one.

Technology

Time is part of the rules.

Rules in Tyla can refer to time. From the validity periods of the facts, Tyla calculates how long a conclusion holds. Here is one rule, applied to the supplier from above.

The rule

A supplier is critical if it was on a sanctions list at any time in the last 90 days.

The answer on 15 April: Nordtek is critical, until 29 May.

Nobody entered the date 29 May. Tyla calculated it from the last day on the list and the 90-day window, and gives both as the reason.

Example with an invented supplier

How Tyla compares.

A language model answers from its training data. Retrieval-augmented generation (RAG) adds documents found for the question. Graph-memory libraries such as Graphiti or Cognee attach timestamps to a graph database. Tyla stores time in the data model itself, so an answer can be replayed and cited for any date.

Four approaches compared
AspectGeneral language model (LLM)RAG pipelineGraphiti / CogneeTyla
How time is handledFixed at the training cut-offOnly what was retrieved for this questionValidity timestamps on edgesBitemporal, part of the data model
ReasoningPredicts the next wordRetrieval onlyGraph lookup; entities extracted by a language model on importDeductive, with the temporal logic DatalogMTL
AuditabilityPractically noneReferences to documentsThe graph can be browsed; derivations cannot be replayedEvery derivation can be replayed for any date
DeploymentUsually cloud onlyDepends on the modelSelf-hosted or in the vendor's cloudIn the EU, on premises or air-gapped
Research

The research behind Tyla.

The rule language is DatalogMTL: Datalog, a rule language from database research, extended with metric temporal logic (MTL). Tyla continues the Temporal Vadalog System, a DatalogMTL reasoner whose principal developer was Markus Nissl during his doctorate at TU Wien.

The rule from the example, written in DatalogMTLcritical(S) :- ◇⁻[0,90d] sanctioned(S).
Questions

What buyers ask before they start.

No. Tyla answers from stored facts and rules. A language model is optional: it can turn a question into a query or read documents, and you choose which one.

Your experts decide what a rule says, and in the pilot we write the first rules with them. The rules are readable, so your team can check and change them later.

One question from your work and a sample of the data it needs. We write the first rules with your team and show you the answers with their evidence.

Per year, for your installation. After the pilot you receive an offer based on what the pilot covered.

Next step

Start with a pilot on your data.

We load a sample of your data into Tyla, write the first rules with your team and show you the answers with their evidence. After the pilot you decide: an annual licence, or a project with a fixed scope.

Runs
In your data centre or with EU hosting
Your data
Not used to train models
Language model
Your choice
Built in
Vienna, Austria
Optional. For example: which contract terms applied on a given date, or which rules a case meets.