Artificial
Intelligence
Foundation models, reasoning, and human-centered AI.
Research for a more human-centered world
We advance fundamental research and build real-world systems where artificial intelligence, intelligent systems, and human-centered applications meet — with a focus on healthcare, multi-agent collaboration, research infrastructure, and knowledge systems.
Lab facts
Research areas
Foundation models, reasoning, and human-centered AI.
Multi-agent systems, human–AI collaboration, and complex systems.
Runtime safety, coordination, and verification for systems with multiple agents.
AI for health, biomedicine, and clinical decision support.
Knowledge representation, scientific AI, and information systems.
Employee-facing AI bots, approved runbooks, separated consents, and action receipts.
Featured research programs
AI for healthcare and Vietnamese traditional medicine.
Applied healthcare AI that puts medical knowledge and intelligent assistance to safe, real-world use.
Public platform — live
Explore the AIMed programRuntime safety and verification for multi-agent systems.
A self-hosted enforcement kernel that intercepts tool calls between agents and the systems they act on — evaluating each call against policy before allowing, pausing for approval, or blocking.
v1.2.0 “Quiet Open-Core” — shipped, self-hosted
Explore the ActantOS programSecurity and runtime-safety agents on the ActantOS kernel.
The WorkDesk bot family for employee IT support: guided troubleshooting from approved runbooks, requests filed through three separated consents, and security reports taken in a private channel — every write decided by the ActantOS kernel.
WorkDesk — shipped with ActantOS
Explore the ActantBot programResearch infrastructure for open science and collaboration.
The platform for academic life: Research Agent, Teaching Studio, and Business Collaboration on one shared foundation of sources, review, rights, and provenance — agents prepare, people retain authority.
Pre-launch — access by request
Explore the ScienzaOS programGoverned AI agents with clear permissions and an auditable record of every action.
An operating layer that connects channels, agents, people, and systems — enforcing rules and scoped permissions, pausing for human approval when needed, and recording every action and outcome.
In development
Explore the Agent Platform programAI-assisted document-to-data workflows with human review.
Turns scanned documents into structured data, keeps source pages beside extracted results, and supports review, editing, and export in one workflow.
Staging showcase — live
Explore the AgenticOCR programHow the research connects
Each long-term program grounds fundamental research in a real domain — turning methods into working systems for people.
From research to reality
Research at ERA Lab does not stop at a paper or a prototype. Each program moves through the same 5 stages, and every stage is published where it can be checked.
Research question
What should an autonomous system be allowed to do, and who decides?
ActantOSMethods
Runtime enforcement, policy evaluation, evidence lineage, and measurement — the engineering that makes an answer testable.
ActantOS v1.2.0Working systems
Five long-term programs turn those methods into software that runs: platforms for healthcare AI, agent safety, open science, governed agents, and document understanding.
ProjectsVerification before assertion
A public platform, a shipped release, a published record, or a documented source — every claim on this site resolves to one of them, and in-development work is labelled as such.
Research recordsIntended impact
Agentic systems that hospitals, universities, and research teams can adopt without giving up control or accountability.
CollaboratePatents
A selection of recent patent entries in LiFi, smart lighting, positioning, and IoT.
View patent recordsVietnam Intellectual Property Office
Patent / application number: VN1-0053734-000
Inventors / authors: Nguyễn Văn Tràng
Search the official Vietnam patent databaseVietnam Intellectual Property Office
Patent / application number: VN1-0053706-000
Inventors / authors: Nguyễn Văn Tràng
Search the official Vietnam patent databaseVietnam Intellectual Property Office
Patent / application number: VN2-0004110-000
Inventors / authors: Nguyễn Văn Tràng
Search the official Vietnam patent databaseVietnam Intellectual Property Office
Patent / application number: VN1-0053216-000
Inventors / authors: Nguyễn Văn Tràng
Search the official Vietnam patent databaseOur people
General contactcontact@eralab.sihello@eralab.si
AI & Platform Architecture
Connects AI-agent research and communications engineering with platform architecture, policy, and runtime systems.
View profile HSB email: kiennt@hsb.edu.vnERA Lab email: kiennt@eralab.siHealthcare AI & Practical AI Solutions Expert
Develops practical AI products and solutions for healthcare and related technology domains.
View profile HSB email: nhannd@hsb.edu.vnERA Lab email: nhannd@eralab.siGovernance Policy & Business
Researches LiFi, optical camera communication, smart lighting, and connected urban systems.
View profile HSB email: trangnv@hsb.edu.vnERA Lab email: trangnv@eralab.siReliability & Production Operations
Brings energy-systems and quantitative research experience to reliability and production operations.
View profile HSB email: quangnt@hsb.edu.vnERA Lab email: quangnt@eralab.siSelected member work
“AI is a general-purpose technology. Our goal is to make it more useful, more reliable, and more human-centered in the worlds that matter most.”
2026 · 10
WorkDesk documents employee IT support bots that answer from approved runbooks, route requests through separated consents, and return receipts from the ActantOS kernel.
2026 · 09
ERA Lab launches its public website
2026
ActantOS v1.2.0 “Quiet Open-Core” ships with a frozen /v1 API
Source: actantos.com/v12026
Multi-agent safety program publishes its first research hypotheses
Source: actantos.comCollaborate
We work with researchers, clinicians, industry partners, and public institutions to build AI that is trustworthy and beneficial.
Discuss a collaborationOpen to collaboration across disciplines.
Official program links.











