Platform

Predict, decide and act, with every decision held to your business rules

The Archisus platform gives you one view of the operation, predicts what happens next, recommends the best action and lets you test it before you commit. Underneath, your rules are encoded as a formal ontology, and every prediction, recommendation and action is checked against them before it leaves the system, with a record of which rule decided what.

Book a DNA Audit What the DNA Audit delivers

The architecture

Three layers, one reasoning machine

The platform turns the rules, relationships and data of your organisation into something an AI system must respect, not just read.

01

The constitution

Ontology layer

An OWL knowledge graph that models your entities, rules, relationships and constraints as formal logic: a purchase order requires an approved supplier; an approved supplier requires a valid certificate; a certificate is valid only before its expiry date. It is not a document index or a vector store, it is a model of how your domain works.

OWL 2 ontology designBusiness rule formalisationVersion-controlled
02

The engine

Reasoning engine on your graph store

The Archisus engine runs OWL 2 inference and consistency checks, SHACL validation and SHACL rules, and query-based rules in SPARQL, or in Cypher through neosemantics on Neo4j. Outputs that break a rule are blocked, logged with the rule that failed, and escalated.

OWL 2 inferenceSHACL validation & rulesSPARQL · Cypher (n10s)
03

The reach

Federated data layer

Semantic adapters connect SAP, SCADA historians, ERPs, maintenance systems and document stores, and query each one in place. Data is not copied to a new platform: only query results move, inside your security perimeter.

No data migrationSAP / SCADA / ERP adaptersData sovereignty

Capabilities

See, predict, decide and govern

The three layers are the foundation. On top of them, the platform does the analytical and decision work your teams need, and because it all runs on the ontology, every result already knows which rules apply to it.

See

Monitoring and alerts

The KPIs that matter, computed across systems that never shared a data model, and watched continuously. Alerts fire when a trend is heading for a threshold, a limit or a contractual date, with the reason attached.

KPI monitoringProactive alertsTrend detection

Predict

Predictive analytics

Forecasts of equipment failure, demand, delays and risk, plus anomaly detection. Each prediction is judged against the specification, contract or regulation it affects, so you see what it means, not only a probability.

Failure & demand forecastingAnomaly detectionRisk scoring

Decide

Guided decisions

The next best action for a situation, with the options ranked and the reasoning shown: the data used, the rules that apply and the trade-offs. People stay in charge of the decision; the platform makes it faster and better informed.

Next best actionRanked optionsExplanations

Decide

What-if scenarios

Change a price, a supplier, a schedule or an operating limit and see the effect on cost, risk, compliance and KPIs before you commit. Scenarios that break a rule are flagged with the rule they break.

Scenario simulationImpact analysisCompliance check

Decide

Optimisation

The best maintenance schedule, stock level, crew roster or resource allocation for your objective, found within your real constraints: regulations, contracts, capacities and safety limits come straight from the ontology.

SchedulingInventoryResource allocation

Govern

Governed action

Digital Experts act on the results inside your systems, and every output is checked against your rules before release. Violations are blocked, logged with the rule that failed and escalated to a person.

Rules checked before releaseAudit trailHuman escalation

Connectors

Connects to the systems you already run

The federated layer reads your ERP, asset, engineering, clinical and data platforms in place, through their standard APIs (OData, REST, JDBC, OPC UA, FHIR), so the data stays where it is and only query results move, inside your security perimeter.

  • S/4HANA · ECC · PM
  • Fusion · E-Business Suite
  • Microsoft Dynamics 365
  • Salesforce
  • IFS
  • Snowflake
  • Databricks
  • Google BigQuery
  • Redshift
  • Synapse
  • Microsoft Fabric
  • PostgreSQL
  • Microsoft SQL Server
  • Database
  • Apache Kafka
  • Microsoft SharePoint
  • Google Drive
  • Jira
  • Confluence
  • Maximo
  • AVEVA PI System
  • OPC UA (SCADA and historians)
  • DeltaV
  • Esri ArcGIS
  • Autodesk Revit · ACC
  • iTwin · ProjectWise
  • Primavera P6
  • Aconex
  • Procore
  • Epic (FHIR)
  • Oracle Health (FHIR)
  • HL7 FHIR
  • Vault
  • Neptune
  • Ontotext GraphDB
  • Neo4j
  • Google Cloud

Logos are trademarks of their respective owners and are shown to name the systems Archisus connects to; they do not imply endorsement.

Graph stores

Runs on the graph store you already use

The knowledge graph is persisted in your existing store. The reasoning runs in the Archisus engine, not in the database, so the same rules and the same validation apply whichever store holds the graph.

AWS Neptune

Your graph stays in your AWS account. The engine queries it with SPARQL and applies OWL 2 inference and SHACL validation on top.

RDFSPARQL

Ontotext GraphDB

For organisations already standardised on GraphDB, the ontology and the validation shapes run against your existing repositories.

RDFSPARQLSHACL

Neo4j

On Neo4j, the ontology is mapped through the neosemantics (n10s) plugin and query-based rules run in Cypher.

Property graphCypherneosemantics

Digital Experts

How a Digital Expert works

A Digital Expert is an AI agent for one business process, such as procurement compliance or regulatory reporting. It runs continuously inside a limited set of permitted actions, in four steps:

01

Perceive

Takes in live data from connected systems: ERP transactions, sensor readings, documents, workflow changes and API events.

02

Reason

Queries the knowledge graph to find which rules apply to that data and what they require.

03

Act

Carries out the permitted action in your systems: raises a record, starts an approval, drafts a filing or issues a work order.

04

Validate

Every proposed output is checked against the SHACL constraints before release. Anything that breaks a rule is blocked, logged with the rule and escalated to a person.

What it looks like

An answer you can audit

Procurement Digital Expert

“Rule 47.3: Supplier ACME-12 blocked. ISO 9001 certificate expired 3 days ago. PO-2024-887 halted pending re-certification. Compliant alternative: Supplier ACME-07 (certificate valid until 2027-03).”
Illustrative example. A generic assistant would say the supplier “may have compliance concerns”. The Digital Expert names the rule, the data it checked and the decision, and that record is what goes into the audit trail.

Compared

Ontology reasoning, RAG and a plain LLM

Retrieval (RAG) and language models are good at finding and writing text. Governed decisions need something they do not provide on their own.

Plain LLMRAGArchisus
Where the rules live In the prompt, as suggestions In retrieved documents, as context In a version-controlled ontology, as formal logic
Can an output break a rule? Yes, on edge cases Yes: the model reads the rules but is not bound by them It is checked before release; violations are blocked and escalated
Relationships between facts Not modelled Similar text, not relationships Modelled and reasoned over (e.g. a clause superseded by an amendment)
Predictions and recommendations Plausible text, not forecasts Summaries of past documents Forecasts, ranked actions and what-if scenarios, each checked against your rules
Audit trail None Source citations Rule, data and decision recorded at the moment of decision
When a policy changes Rewrite prompts Re-index documents Update the ontology once; every Digital Expert follows it

The approaches combine: Archisus can use document retrieval inside an ontology-governed pipeline, and it works with the language model you already use.

Questions

Frequently asked questions

Is Archisus only a governance layer?

No. The platform also does monitoring and alerts, predictive analytics, guided decision-making, what-if scenarios and optimisation. Governance is what makes those results safe to act on: each one is checked against your rules before it is released.

Can we test a decision before we make it?

Yes. What-if scenarios show the effect of a change on cost, risk, compliance and your KPIs, and flag any scenario that would break a rule, before anything is changed in your systems.

Does Archisus replace our language model?

No. The ontology layer is model-agnostic. It governs whichever model you use, including one you already run, and the checks still apply when you change or upgrade that model.

Do we need to migrate our data?

No. The federated layer queries your systems in place. No operational data is copied to Archisus, and the models run on-premise or in your private cloud.

Which graph databases are supported?

AWS Neptune, Ontotext GraphDB and Neo4j. The graph is stored in the one you already use; the reasoning runs in the Archisus engine.

What kind of reasoning does the engine do?

OWL 2 inference including consistency checks, SHACL validation and SHACL rules, and query-based rules in SPARQL, or in Cypher through neosemantics on Neo4j.

What happens when a rule changes?

The ontology is updated and the change applies to every Digital Expert that uses it, with no retraining and no prompt rewriting.

Do we need clean data first?

No. Data is only "clean" relative to the rules it has to meet. The DNA Audit defines those rules and shows which data issues actually matter for the process you want to start with.

Keep exploring

ROI calculator Estimate the annual value of seeing, predicting, deciding and governing in one platform. The DNA Audit A fixed two-week start: your rules mapped, the gaps found, a pilot roadmap. Energy, nuclear & petrochemicals Safety-critical decisions with reasoning you can audit.
Let's Start

The DNA Audit Is Your First Step. And Your Lowest Risk.

In two weeks we map every critical reasoning dependency, broken data link, and governance gap in your current AI or data workflow. You leave with a draft ontology model, a prioritised use case roadmap, and a clear decision on whether - and how - to proceed. No commitment beyond the audit.

Knowledge architecture map

Every logic dependency, data relationship, and constraint your AI needs to reason correctly - visualised and documented.

Gap & risk report

Broken data links, contradictory rules, and governance gaps that are invisible today - surfaced and prioritised by business impact.

Draft ontology & pilot roadmap

A working ontology model for your highest-priority domain, plus a ranked shortlist of pilot use cases with estimated ROI and delivery timeline.

[email protected]

Book Your DNA Audit

2-week engagement · Fixed scope · No ongoing commitment required

ROI calculator