For a physician
Under the physician's guidance it assembles the case chronology and sources, and cites the origin alongside the data. It makes no diagnosis and proposes no therapy; the decision is the physician's.
ZDRAVKO · clinical decision support
Research prototype · in development
It assists the physician. The physician decides.
ZDRAVKO is structured clinical decision support for qualified healthcare professionals, on the SLAVKO core: it organizes reference information, guidelines and literature, remembers context and checks answers before delivery.
Not a medical device: it does not diagnose, does not treat and does not replace clinical judgement. An application of the same core that is in production for institutions and schools; the foundation is designed by a physician.
Transparent AI: the system always presents itself as AI, never as a physician.
What ZDRAVKO is
The same core, a healthcare layer.
ZDRAVKO is not a separate program but the SLAVKO core applied to healthcare: Metatron is the operating layer, SLAVKO is the assistant the user sees, and ZDRAVKO is the same system with a layer of rules and references for the clinical setting.
Its purpose is informational: it systematizes what already exists in the profession — guidelines, reference information and literature — and helps break a case down into what is known, what is missing and the checks that must never be skipped, in a form the physician reviews.
The boundary is part of the design, not an afterthought: the diagnosis and every decision are made and independently verified by the physician. The system does not diagnose, does not treat and does not replace clinical judgement.
For whom
For healthcare professionals who verify.
The audience is deliberately narrow: qualified healthcare professionals and institutions that want support on their own infrastructure.
For an institution
The core runs on the organization's infrastructure or, at the organization's choice, with a cloud model. Every user works in a separate space of their own: a job runs under their name and opens only their data.
Who it is not for
ZDRAVKO is not a service for patients and not a substitute for seeing a doctor. It is intended for qualified healthcare professionals who independently verify every outcome.
How it helps
References, structure, memory, verification.
Four things the core does for the physician — and none of them is a decision.
References and guidelines in one place
It organizes reference information, guidelines and literature relevant to the case and cites the origin of every item — domestic guidelines take precedence, then European and international ones.
A structure for thinking
It breaks a case down into the known, the unknown and the checks that must never be skipped; it offers reminders and reference frames that the physician reviews and confirms.
Remembers the context
Memory lives in files outside the model: rules, work history and references remain even when the model is swapped, so the next conversation starts where the previous one stopped.
Checks before delivery
The model's output is a candidate, not a result: it passes a check of structure, rules and an independent review. An answer that fails goes back for repair or is discarded.
How it works
The path of a single question.
From a physician's question to a verified answer, in six steps — the same path the SLAVKO core takes.
Question
The physician asks a question about the case by text or voice message, through a channel already in use. Speech is turned into text on the organization's infrastructure, not at a third party.
Who is asking, and what is allowed
The system establishes who sent the question and opens the job under their name, in their own separate space; for that job it knows how much may be spent and which tools may be run.
Context
It assembles context from persistent memory: rules, work history and references that belong to that physician or institution — not just from one session.
Candidate
The chosen model — local on the institution's infrastructure or in the cloud — proposes an answer. Calls to models go through a single point of access that alone holds the keys and keeps the usage ledger. The proposal is only a candidate.
Check
The candidate is checked: structure, rules and an independent review. An answer that fails goes back for repair or is discarded; an action that cannot be undone waits for a human to confirm.
The physician decides
The verified answer reaches the physician, as text or Serbian speech; the physician independently verifies it and makes the decision. What was learned along the way is written to memory.
Boundary and responsibility
The decision stays with the physician.
ZDRAVKO is an informational tool and decision support for qualified healthcare professionals who independently verify every output; it is not a medical device, does not diagnose, does not treat, and does not replace clinical judgement.
Always AI, never a physician
The system always presents itself as AI; the interface makes it clear when the other party is not a human.
Sensitive data stays local
By the core's design, health data is sensitive data that stays local; only what the organization approves goes outside. This site collects no data at all.
Entry and interpretation are the profession's responsibility
Entering and interpreting clinical data remains the responsibility of the healthcare professional and the institution, in line with regulations and the institution's rules.
Nothing irreversible without a human
An action that cannot be undone waits for a human to confirm; risky topics do not pass without oversight.
Maturity
A research prototype, in development.
No understatement and no overstatement: ZDRAVKO carries the label “in development” and is not in public production. The core it is built on is.
The SLAVKO core
Persistent memory, a separate space per user, a single point of access to models, Serbian voice and answers checked before delivery — in production for institutions and schools.
core in productionZDRAVKO — the healthcare layer
A layer of rules and references for the clinical setting on the same core: a research prototype, not a medical device, not in public production.
in developmentDirection of development
Organizing health sources with the origin of every item cited, under the physician's guidance. No promised dates.
direction of developmentA demonstration of the system by arrangement, on infrastructure of the organization's choosing.
About the author
The foundation is designed by a physician.
ZDRAVKO and the SLAVKO core are designed by Dr Ognjen Vučurević — a medical doctor and radiology resident who, since late 2024, has led the AI domain at an IT company in Belgrade: system architecture, specifications, acceptance criteria and the bridging of clinical, business and engineering teams.
Clinical discipline — differential diagnosis and the checks that must never be skipped — has been carried over into software architecture, where the same things are called validators, safety gates and the rule that a model's output is a candidate for a result.
That is why ZDRAVKO remains strictly a support tool: when building for healthcare, privacy and caution are not optional but obligatory. The author's role is architectural — frame the problem, design the system, define the acceptance criteria and prove that it works.
Frequently asked questions
Direct answers.
Answers to the questions asked most often.
What is ZDRAVKO, and does it replace a doctor?
ZDRAVKO is clinical decision support for qualified healthcare professionals and does not replace a physician. It organizes references and guidelines, while the diagnosis and every decision are made and independently verified by the physician; it is a research prototype that is not a medical device.
Who is ZDRAVKO for?
For qualified healthcare professionals and institutions that want support on their own infrastructure. It is not a service for patients and not a substitute for seeing a doctor.
Is ZDRAVKO a medical device?
No. ZDRAVKO is an informational tool and decision support: it does not diagnose, does not treat and does not replace clinical judgement. Every output is independently verified by a healthcare professional.
Does the data leave the institution?
In local mode it does not: the model runs on the organization's infrastructure and the data stays where it was created. In cloud-model mode a request goes to the model vendor, with personal data removed when the organization requires it; the choice of mode rests with the organization.
How does the system handle model errors?
A model's output is treated as a candidate and is checked — for structure, rules and by an independent review. An answer that fails goes back for repair or is discarded, instead of reaching the user. The final check is always the physician's.
Can the model be swapped?
Yes, the system does not depend on a single model vendor. The model is changed through configuration, while accumulated knowledge, work history and rules remain intact, because they are kept outside the model.
How do ZDRAVKO, SLAVKO and Metatron Production relate, and how does a collaboration start?
Metatron Production is the company that designs, builds and runs the systems; SLAVKO is its product, and ZDRAVKO is the same core applied to healthcare. A collaboration starts with a conversation by e-mail; by arrangement, a demonstration follows on infrastructure of the organization's choosing.
Contact
A conversation is the first step.
For questions and to arrange a demonstration: e-mail below. The company behind the product: Metatron Production.
ognjen.vucurevic@gmail.com