MBBS student
Learn modeUnderstand why, not just what. Foundation, mechanism, then what the latest trials add, with exam traps and NEET-PG style MCQs with the reasoning behind each answer.
HUMAN CURIOSITY. EVIDENCE BEHIND IT.
Every answer.
A real paper behind it.
Explore clinical research with traceable sources, visible uncertainty, and human review. Take your thesis from the first question to submission, with a record of how AI was used.Designed for MBBS student, MD / MS / DNB resident, Medical researcher, & Practising Doctor
Your next chapterA question today.
A question today.
A clearer way forward.
For students, clinicians, and the research that matters to them.
- Europe PMC and PubMed Central
- Retraction-checked
- Verifiable AI-use record
From the creators of HiMirrorly, carried in English and Hindi media
Human judgment. Always at the center.
Research support, shaped around real people.Private by design. Source-bound by construction.
Citation Truth Check
Does each reference exist, and does it say what your sentence says it says?
Upload a manuscript. Every reference is checked against Crossref, PubMed and Retraction Watch, every in-text citation is matched to the list, and each cited sentence is compared with the paper's abstract, quoting the passage that supports it. A clean result can be sealed as a certificate link for your guide or journal.
The free check needs no account and covers existence, wrong DOIs and retractions. It reads abstracts only, never full text behind a paywall, and says "cannot tell" rather than guess.
From question to submission
Every check your guide, ethics committee and journal will run. Run it first.
- 01 · Plan
Thesis deadlines
Protocol by day 180, thesis by month 26, the exam cut-off it feeds. NBEMS rules and university dates, labelled.
Start free - 02 · Design
Sample size that holds up
Two means, two proportions, prevalence or diagnostic accuracy, with a warning when the inputs are implausible.
Start free - 03 · Write
Similarity pre-check
Paste a chapter. Copied sentences highlighted against 40 million+ abstracts and the web, read against UGC 2018 levels.
Start free - 04 · Submit
Journal check
Is it really in MEDLINE, PubMed Central or DOAJ? Predatory warning signs flagged before you pay a fee.
Start free - 05 · Prove
Integrity passport
What the AI did, what you approved, every source traced. A disclosure to paste and a link your guide can verify.
Start free
Your guide can follow along: share read-only access to deadlines, integrity scores and sign-offs, never your evidence or questions.
Built for where you are
Same evidence. Shaped for your exam, your journal club or your thesis.
MD / MS / DNB resident
Journal club modeThe anchor study chosen for you and appraised across eight domains, from PICO to applicability where you practise: India, UK, US, Middle East, Australia / NZ or Asia. Discussion questions included.
Medical researcher
Project workspaceGap check against the literature before you write a line, scored study ideas, a sample size and a protocol draft with numbered references.
Practising doctor
Practice briefBottom line, certainty of evidence in plain words, which population was actually studied, and department actions, on one screen.
Pick where you practise. World evidence first, then the local guidance, exam level, units and trial registry for your setting. Switch per question to compare.
IndiaICMR · NMC · CTRIUnited KingdomNICE · SIGN · ISRCTNUnited StatesUSPSTF · CDC · ClinicalTrials.govMiddle EastMOHAP · DHA · SCFHSAustralia / NZNHMRC · RACGP · ANZCTRAsiaNational MOHs · APASL · WHO SEARO / WPROInternationalWHO · Cochrane
Not sure about an answer? Check it: newer evidence, contrary evidence, a paper it missed, another region, retractions. Then ask again with the research you choose.
Start free, no cardEvery mode uses the same evidence and the same citation checks.
NEW / DECISION REHEARSAL · WORKING PREVIEWBefore the leap.
Before the leap.
Make room for proof.
The next extension of HiDoctorly's evidence-first thinking. Make assumptions visible, hear the people affected, compare alternatives, and plan a small, safe test.
Explore Decision RehearsalSeparate demo workspace. No patient information. Your existing research workflow stays exactly as it is.A METHOD, NOT A LEAP OF FAITH.
01 Discover02 Define03 Develop04 Deliver
New · Integrity passport
Your guide asks, "did AI write this?" Show them the record.
Journals now require an AI-use disclosure, and universities and ethics committees are asking the same of theses. Chat tools keep no record you can show. HiDoctorly kept it from the first question: what the AI produced, what you approved and when, which sources were traced and checked for retraction.
- A disclosure written from facts, in the shape ICMJE and the CDC ask for, ready to paste.
- An integrity score per project, with the exact items to fix before you submit.
- A sealed verify link your guide, IEC or editor can open. It shows provenance and your decisions, never your protocol or data.
Start free, no cardIncluded in every plan.
93
Ready to seal. 18 sources, 10 with a DOI, all checked, 0 retracted.
Diagnostic accuracy study · N = 395
Evidence
AI: searched and read 18 sources, classified 6 claims.
You: approved 05 Oct
Protocol
AI: drafted the protocol, 2 versions.
You: approved v2, 05 Oct
"Portions of this work were prepared with HiDoctorly Research… The author reviewed and approved each stage… The AI tool is not an author."
Evidence integrity · visible from the first session
A prompt can describe a process. HiDoctorly stores and enforces it.
Every private question becomes an accountable research artifact: scoped to you, grounded in retrieved evidence, checked claim by claim, and recorded as it moves through the chain.
Private scope
Your owner and project boundary is established before research begins. No cross-owner or cross-project synthesis.
Evidence trail
Retrieval tier, source, date and licensed-content handling stay attached to the research run.
Claim validation
Claims bind to sources and pass the HI-EI-AI checks before an exportable record is issued.
Accountable history
Artifact hashes, approvals and audit events make the path reviewable after the answer is written.
The practical difference. General assistants optimise for an answer. HiDoctorly helps you produce a private, source-bound and reviewable evidence artifact.
How you actually use it
One clinic session in, one protocol out. Here is what that looks like.
You do not need to know how to phrase a MeSH query, and you do not need a research methodologist sitting next to you. You need forty minutes and one observation you cannot let go of.
Start the way you would tell a colleague
Open a project, and type the observation in ordinary clinical language, “younger MI patients in the last two years seem to be presenting later than they used to.” No template, no keywords, no structured fields. Strip the identifiers before you paste; the system checks and stops you if you forget.
Let it tell you if it has been done already
Run the cascade. You get papers with design and year, and a synthesis where every claim shows the source behind it. This is the step that either kills your idea in twenty minutes or tells you the gap is real, and either outcome is a good use of your afternoon.
Teach it your literature
Star the papers you already trust. They become Tier 1, searched first, every time, and never sent anywhere. After two or three projects the cascade starts from your own reading list rather than from cold.
Choose a study you can genuinely run
Ideas come scored for feasibility in your setting, not in an ideal one. A design needing 400 cases a year is marked as such if your unit sees 90. Pick against your real case volume and your real follow-up rates.
Take the draft to your IEC
Export the protocol with the governance record attached, objectives, population, outcomes, sample-size assumptions, statistical plan, bias table, limitations. Edit it as a clinician. It is a strong first draft, not a submission.
Nothing you write leaves your control
Your corpus is yours alone. No cross-owner flow, no cross-project synthesis, nothing sent to an external model. The only thing that ever leaves for outer-tier search is a derived query string, never your case text.
What it will not do. It will not tell you what to prescribe, start or stop. It will not diagnose. It will not tell you your idea is the first in the world, it cannot know that, so it says “based on searches through this date, limited evidence was found” instead. If you want a tool that flatters your hypothesis, this is the wrong one.
The HI-EI-AI chain
Five stages. Every one of them gated by you.
Human-in-the-loop by construction. Nothing advances to the next stage without your signed approval, and every approval is written to an audit trail with the artifact hash it signed over.
01
Observation intake
Write what you saw, the way you would tell a colleague in the corridor, “the last dozen or so post-CABG diabetics on empagliflozin seemed to mobilise faster than I expected.” No structured form, no keywords. De-identify it: no names, no UHID/MRN, no dates of birth, no phone numbers. A PHI scanner runs before anything else and, if it finds one, intake stops and points at the exact text so you can strip it. HI-EI-AI then hands back your observation as a PICO, population, intervention/exposure, comparator, outcome, plus a three-sentence paraphrase in plain clinical English.
HI-EI-AI gateRead the paraphrase. If that is not what you saw, reject it and rewrite, everything downstream is built on this framing.
02
Evidence workspace
The cascade runs a query ladder built from your framing, tightest search first, broadening only until it has enough to stand on. You get a source list with study design, year and where it came from, and a synthesis in which every sentence is bound to the papers it rests on. Expect a genuine answer to “has this already been done?” If the honest answer is “partly”, it will say partly.
HI-EI-AI gateYou know your literature. Star the landmark paper the cascade missed, it joins Tier 1 and is searched first from then on.
03
Research idea radar
Candidate studies you could actually run, each with a proposed design, retrospective cohort, case-control, prospective, registry, diagnostic accuracy, prediction model, and each scored three ways: how new it is against what Tier 1–2 found, how feasible it is in your own unit given your case volume and what you can realistically measure, and how publishable it looks. The feasibility score is the one that saves you a wasted year.
HI-EI-AI gatePick the one you will pursue. The rest stay in the project, archived not deleted, for when your case mix changes.
04
Protocol builder
A draft in the shape your ethics committee expects: objectives, population with inclusion and exclusion criteria, exposure, comparator, primary and secondary outcomes with how each is measured, sample size with every assumption written out where you can argue with it, statistical plan, bias risks with mitigations, ethics section, limitations. It is a first draft for a clinician to edit, not a submission-ready document, and it does not pretend to be.
HI-EI-AI gateSign off on population, exposure, outcomes and the statistical plan. Those four are where IEC queries come from.
05
Claim & citation check
Before anything leaves the system, a full validator chain sweeps the whole project, stance, evidence composition, cross-stage consistency, gate completeness, ownership and citation binding. This is the pass that catches the protocol that has quietly drifted away from the observation that started it, and the sentence with no paper behind it.
HI-EI-AI gateEvery unsupported claim must be resolved or removed. Until then no governance record is issued, the export is refused outright, not flagged with a warning you can click past.
The retrieval spine
A cascade, not a search box.
You will recognise the problem: a plain-English clinical question typed into a biomedical index returns almost nothing, because indexes match terms and not sentences. So retrieval here runs in four tiers, in order, working a query ladder from your framing, tightest first, broadening only until it has enough to stand on, then stopping.
Cascade guaranteeThe Private Secured Search Engine is withheld entirely unless the indexed tiers produced grounding first. When it does run, egress is query-only, the derived search string and nothing else.
Tier 1
Your starred corpus
The papers you have already read and kept, held inside your own project. Searched first, always, and never sent anywhere.
Tier 2
Biomedical index
Peer-reviewed biomedical indexes, queried through a query ladder that walks from specific to broad until the corpus is grounded. A plain-English framing returns almost nothing from an index; the ladder exists because of it.
Tier 3
Full text on request
Retrieved only for papers you ask for by name. Bandwidth and attention are both finite; neither is spent without your instruction.
Tier 4
Private Secured Search Engine
Society guidelines, trial registries and health-authority sources, reached through a private secured search engine that receives nothing but the derived search string. No case text, no patient-adjacent detail, no part of your corpus. Withheld entirely unless Tiers 1–3 produced grounding.
Absolute privacy
Your clinical thinking is yours. Absolutely, and by construction.
You are being asked to put your unpublished observation, the thing you have not told anyone yet, into a piece of software. So this is stated plainly rather than buried in a policy page.
Nobody reads your corpus. Not another clinician, not another department, not us. Every row is anchored to your owner id and every query is scoped to it. There is no admin view of your project text.
No external model ever sees it. Your observations, sources, ideas, protocols and claims are never sent to any third-party model. Reasoning runs against the endpoint your instance is configured with, in Private self, one inside your own estate.
No cross-project synthesis. Your projects are not mined against each other, and never against another doctor’s. Nothing you write becomes training data, an aggregate statistic, or a “similar research” suggestion to someone else.
PHI is refused, not stored. The de-identification gate blocks patient identifiers at the door, checked before the text is written anywhere. The safest posture is to hold no PHI at all, so that is the posture.
The outer ring gets a query string, nothing else. When Tier 4 runs, the Private Secured Search Engine receives the derived search terms and nothing more. No case description, no patient-adjacent artifact, no part of your corpus. That boundary is in code, not in a promise.
You can take it all with you. Every artifact is exportable with its governance record. There is no lock-in on your own research, and deletion means deletion of the artifact, the append-only audit ledger keeps only the fact that an action occurred.
What HiDoctorly is not
Not a diagnostic aid. Not clinical decision support. Not a novelty oracle. Not a generic chatbot with a stethoscope. HiDoctorly supports the design of research, and the clinician remains the scientific decision-maker at every stage.
Pricing
Start free. Stay only if it earns its place.
Everything is included from day one. No card to start, and nothing is ever charged automatically.
Free until 3 Nov
Free
Everything, for everyone. No card needed
- Unlimited questions in all four modes
- Research projects and protocol drafts
- Similarity pre-check, journal check, integrity passport
- Every download format
Monthly
AED 18
≈ $4.90
per month, under AED 0.60 a day
- Everything in the free plan
- Your library and history kept
- Pay month by month
Annual Save AED 36
AED 180
≈ $49
per year, two months free
- Everything in monthly
- Covers final year, NEET-PG prep or a residency year
- One payment, no renewals to remember
Card, Apple Pay or Google Pay through Ziina. Department or cohort invoice? Ask us.
Charged in AED through Ziina. Other currencies are shown for reference only (1 USD = AED 3.6725, pegged; 1 AED = ₹26.24, 6 Oct 2026; GBP, EUR and AUD at 8 Oct 2026 central bank rates). Your bank converts at its own rate on the day and may add a small foreign-transaction fee.
Questions before you sign up
Is it really free?
Yes. Every feature is free for every account until 3 November 2026, with no card asked for when you sign up.
What happens after 3 November?
Nothing is charged. You see the option to continue at AED 18 (about $4.90) a month or AED 180 (about $49) a year. If you do not pay, your work is kept and you can still sign in and download it.
How is this different from a general AI chatbot?
A general AI chatbot answers from memory and can invent references that do not exist. HiDoctorly answers through the Private Model by HiDoctorly. It searches the literature first and answers only from the papers it retrieved. Systematic reviews and RCTs rank first, every claim shows its source, and anything without a source is labelled unsupported.
Who can see my questions?
Only you. Your questions, projects and answers are not visible to other users or to us, are not pooled with anyone else’s work, and do not train a shared model. Patient identifiers are blocked before anything is searched.
Is it clinical advice?
No. It is research and learning support. It will not diagnose, prescribe or dose for a patient, and it says so. You remain the decision-maker.
Will this pass my university's plagiarism check?
The similarity pre-check finds sentences copied from published abstracts, open-access papers and the web, so you can rewrite them early. It is not your university's DrillBit or Turnitin report, which also holds past theses and paywalled journals, so your official score can be higher.
How do I disclose that I used AI?
Each project builds an integrity passport: what the AI produced, what you approved and when, and which sources were checked. It writes an AI-use statement in the shape ICMJE and the CDC ask for, and gives a sealed link your guide or journal can open. The link never shows your protocol or data.
Can my guide see my work?
Only if you share, and only the process: deadlines, integrity scores, sign-offs and checks. Never your observation, evidence, protocol text or questions. You can remove access at any time.
Can I use it for my thesis or a journal club?
Yes. Download an answer or a whole project as PDF or Word with Vancouver-style numbered references, or send the references straight to Zotero, Mendeley or EndNote. Always read the key papers yourself before you cite them.
Walk into your next viva, journal club or thesis submission with the references and the record.
Everything is free for everyone until 3 November 2026. Sign up in under a minute and ask your first question straight away. After that, AED 18 (about $4.90) a month or AED 180 (about $49) a year, only if it has earned its place on your phone.