Sovereign AI Platform
Data-sovereign AI platform. Auditability that meets the AI Act.
Verisa is a sovereign on-premise AI platform with graph-native reasoning — every conclusion traces back to a concrete reference. Aligned with EU regulation, built by Entel — a 36-year-old independent Hungarian deeptech vendor.
Two products on one sovereign infrastructure.
Verisa AI is the agent platform. Verisa Flow is the knowledge-management and AI orchestration tool.
Verisa AI
Sovereign AI with graph-native reasoning- On-premise. Air-gapped if you need it. Your data never leaves your infrastructure.
- Frontier-grade retrieval — Verisa's ARTIS module reaches 94.7% Hits@10 on the public MultiHop-RAG benchmark, the best published result to date.
- EU AI Act–ready auditability, hardware-key licensing, source code escrow.
Verisa Flow
Knowledge management and AI orchestration tool- Five domains, one engine — code, documentation, research, legal, process.
- Multi-model consensus and graph-backed structural verification.
- Legal AI support — graph-native legal reasoning, where every answer traces to a specific law, paragraph, or precedent.
Built for regulated work
Why Verisa?
Direct answers to the questions regulated buyers actually ask.
Your data stays in your infrastructure.
Fully on-premise or air-gapped. Vendor-bound automatic data transmission and telemetry (phone-home) is blocked entirely, and a user-side data loss prevention (DLP) integration is in place. The isolated operating and deployment mode is enforced in code, not promised in a sales slide.
Explainable AI (X-AI) and auditability.
Every answer's reasoning path is traceable, the inference is auditable, and the use of training data is recoverable through the graph-native representation.
Multiple AI models check each other.
Multi-model consensus with structured disagreement handling, human decisions in the loop, fully logged.
Built in the EU, regulation-aligned.
Multi-language UI and speech recognition. eIDAS-based identity, with national identity integrations on request. EU AI Act conformity. EU-sovereign foundation models when you need them.
Cryptographic audit trail.
TLS 1.3, mTLS between services, SHA-3-256 hash-chained audit log, hardware-rooted licensing, source code escrow.
Five domains, one orchestration engine.
Code, documentation, research, legal, process — the same knowledge-management methodology, used intuitively and securely on a single workspace, native desktop app, with a Microsoft Word add-in and further auxiliary tools.
How it works
From a complex requirement to a verified, delivered artefact.
Define
Pick the workflow mode. Verisa decomposes the work into sequenced tasks against an explicit spec when coding, or runs built-in pipelines and macros for knowledge-management tasks.
Generate
Each task goes to the right model — fast or capable, cloud or local, as your settings dictate. Multiple models run in parallel.
Verify
Cross-model consensus plus graph-backed structural verification. Tests, compliance checks, style standards. The system does not blend model disagreements into a single averaged answer: every divergence is flagged explicitly and routed to human decision.
Deliver
Verified artefacts move into your delivery pipeline — CI/CD, document publishing, approval workflows, compliance registries — with the audit trail attached.
Five domains, one engine
The same methodology, configured per domain. Tabs for parallel work, native desktop app, multi-platform messaging gateway for remote control.
Code
Spec-driven AI coding. Multi-model consensus, automated tests, CI/CD. Pre-commit checking rejects the commit if the AI modified files outside the active task's scope.
- Architect / Developer / Reviewer / QA agent roles
- Auto-generated unit tests
- Cryptographic audit log of every AI-generated change
Example
"A small team ships a full-stack API with architectural guidance, automated review, and deployment automation — without a senior engineer on every keystroke."
See it in action
Methodology-driven orchestration with multi-model consensus and graph-backed verification.
$ verisa-flow start --mode code --project my-api[Architect] Decomposing task into 4 subtasks...[Developer] Generating auth module...[Reviewer] Consensus review (cross-model)...[QA] Running 12 unit tests... All passed.[Pipeline] Pushing to staging via GitHub Actions...✓ Consensus: 3/3 agents agree (high confidence)✓ Validation: 12/12 tests passing✓ Pipeline: deployed to staging✓ Design sync: HLD updated (DESIGN-017)Ready for production deployment.