Robust expert work requires more than AI alone.
AI alone is too free. Pure rule systems are too rigid. UNOY combines both.
Workflows store logic. Skills and databases hold knowledge. COIA orchestrates AI. Governance ensures auditability. This turns an AI model into a controlled matter, and turns answers into accountable results.
Master Formula
Work in. Result out.
§ 02 · The AI Gap
Why AI alone is not enough.
Large language models respond. But they have no concept of responsibility, no file, no versioning. Three gaps that cannot remain open in expert work.
AI Response · no trace
Notice on Data Protection Request
AI does not know who may decide.
No responsibility assigned, no mandatory check, no audit trail. An answer is produced regardless of who is accountable.
! Record missing
Contract Müller GmbH
Handler: ?
Status: ?
AI does not know your files.
Standard models have general knowledge, not your contract, your policy, your member data.
Model Versions
AI changes silently.
Models are replaced, prompts drift, outputs vary: without a workflow as anchor there is no reproducibility.
AI alone responds. Robust expert work decides, documents and hands over.
§ 03 · The Rule Gap
Why pure rule systems are not enough either.
Classic rule systems and RPA work as long as a matter requires no language, no context, no reasoning. Expert work almost never qualifies. Three gaps that stop every RPA pilot eventually.
RPA Workflow · Run #2451
Email Classification
Rules do not understand language.
Classification, meaning extraction and language comprehension are not if-then logic. RPA fails at the first unstructured email.
Notice · #1287
Approved
Reasoning: [empty]
Oversight: ?
Rules justify nothing.
They execute but do not explain. Clients, regulators and audits need justifications, not code paths.
Rule Maintenance · Q2/2026
Claims Classification
Rules break under special cases.
Every new variant requires a new rule. Maintenance effort explodes, and the day it becomes unmanageable is foreseeable.
Pure rules execute. Robust expert work reads, writes and reasons.
§ 04 · The UNOY Synthesis
AI alone is too free.
Pure rules are too rigid.
UNOY combines both.
Accountable expert work does not arise from a single tool. It arises when four layers work together: rules carry the logic. Knowledge carries the content. AI carries the language. Governance carries the accountability. UNOY OS connects these four layers in one system.
AI Alone
Free. Fast. Non-binding.
Pure Rules
Stable. Auditable. Mute.
UNOY
Free. Stable. Accountable.
§ 05 · Layer 1 · Rules
Workflows as the robust core.
Workflows store logic independently of the AI model. AI models are replaced; the workflow remains. This makes UNOY interchangeable at the AI layer and stable at the business layer.
Matter · GDPR Access Request
From letter to verified response.
Step sequence, mandatory fields, sources and approvals are defined in the workflow before a matter starts. Once the access request arrives, it runs against this definition: what must be checked, who approves, what is recorded in the audit trail. AI only enters where language is needed; the logic stays in the workflow.
Interchangeable in the model. Stable in the matter.
§ 06 · Layer 2 · Knowledge
Skills, RAG and databases: your knowledge.
Standard models know the world. UNOY brings your world into play, in three ways: as reusable skills, as citable RAG sources, as structured facts.
Skill Library
Skills: reusable domain logic.
Defined once, usable in every matter. Versioned, auditable, transferable between teams.
RAG Sources · § 4 Access
RAG: citable knowledge base.
Contracts, legal texts, internal memos: directly in the matter with source reference. AI does not respond from general knowledge.
Member DB · 14,291 entries
Databases: structured facts.
Members, policies, deadlines, order data: readable, writable and verifiable inside the workflow. No hallucination possible.
§ 07 · Layer 3 · AI Within Bounds
COIA: AI handles the language part. Workflows handle the rest.
COIA is the orchestrator: it calls AI functions only where language is genuinely needed, and passes results to the next workflow node. AI remains the tool. The workflow remains in charge.
Matter · Orchestration
Clearly separated: what AI does, what the workflow does.
Classifying, drafting, reasoning: that is language, therefore AI. Mandatory checks, roles, audit trail, handover: that is logic, therefore workflow.
COIA switches the model without changing the workflow. Interchangeable at the AI layer, stable at the business layer.
AI remains the tool. The workflow remains in charge.
§ 08 · Layer 4 · Governance
Governance turns AI output into a decision someone can be accountable for.
Auditability is not a by-product: it is part of the matter. Every step, every source, every approval is retained.
Roles · Matter #2451
Roles & approvals.
Who may view, edit, approve? Four-eyes principle anchored in the workflow.
Audit-Trail
Audit-Trail.
Every step with timestamp, actor, source and model version. Reproducible.
Data Residency
EU data residency.
Data in EU data centres. Encrypted at rest and in transit. No training use.
Learning Loop · Q2/2026
Learning loop.
Corrections flow into skills and templates: controlled, with version record.
§ 09 · Proof in the Matter
Robustness is not claimed. It is delivered.
Three live matters, three different moat layers in use. Rules, knowledge and accountability in real cases.
WKO · live
600,000+ businesses
8 applications in production
since 2024
WKO: Many services. One system.
Chamber scale with workflow core. See case study →
FairPlane · Fall #2451
Delay 3h 20min
EU 261/2004 · € 600
✓ Claim confirmedFairPlane: Many cases. Clear rules.
Classification, review, letter. AI within the rule. See case study →
Skribe · Accountability
RA Dr. M. Skribe
Licensed in Vienna
Reg. No. R 008451
Skribe: UNOY OS processes. Skribe is accountable.
Qualified professionals accountable in the legal matter. See delivery page →
§ 11 · Next Step
Work in. Result out.
Robustness shows in a real matter. Bring recurring work and UNOY will identify which layers apply and which path fits.