Clinical Decision Support
M

Medows

Medows is a clinical workspace for doctors on ward rounds and on call shifts, designed alongside junior doctors in Indian hospitals. Each patient gets a card with vital signs, complaints, active orders, lab values, medications, notes and outstanding tasks, and color flags mark numbers that need attention. The list follows the doctor across devices.

The AI assistant, built on Google Gemini, reads the selected patient's vitals, recent labs and completed tasks before the doctor asks anything, then answers with differentials, dosing and suggested next steps, drawing on guidance from ICMR, WHO, AIIMS and national formularies. Each suggestion appears beside the patient context it used, and the doctor chooses which suggested tasks to add. At handover, Medows writes a two line summary per patient covering current issues and pending items, which can be copied or sent through WhatsApp. Doctors can share selected patients with colleagues and invite nurses with limited access.

Medows runs alongside the hospital's record rather than replacing it, and its terms describe it as an information tool without regulatory clearance, not to be relied on in emergencies. Individual clinicians use it free, with no card or trial clock, and hospitals and departments arrange rollout and pricing directly.

AI Health Index verifiedNovember 19, 2026
Compare Medows with other vendors
Founded
—
Headquarters
—
Website
www.medows.ai
Categories
clinical-decision-support, medication-safety-and-prescribing
Indexed Products
Clinical Workspace, AI Consult, Handover
Buyer Segments
Clinician, Hospital, Health System
Assessment

Capability Axes

An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read

AI Capability
BB on AI CentralityThe model is the engine of a core module. The platform carries other value, but this capability does not exist without it.
Vendor Published

The AI consult is the reason the workspace exists. Google Gemini takes the patient's entered vitals, complaints, lab results and completed tasks and returns contextual answers, differentials, dosing and handover drafts, so the intelligence goes straight at clinical interpretation and next steps, medication questions included. The two line handover for each patient is generated the same way, from current issues and pending items.

Patient cards, task tracking, color flags and controlled sharing also work as ordinary workflow software. Medows is a personal workspace for clinicians rather than an EHR with a chatbot attached.

BB on Autonomy and Oversight ModelThe oversight structure is described and one part is missing, commonly the threshold at which the system stops or what happens after it is wrong.
Vendor Published

Suggested tasks stay separate from active ones until the doctor adds them, notes can be edited, and every answer appears beside the patient context it used. Physicians make the decision and are told to check drug names, doses, intervals and other suggestions against their protocols.

The product also promises that no patient will slip through, a wider assurance than those review controls can give. No sign off is enforced for each clinical answer, no confidence threshold is set and no response path follows a missed risk, and the terms rule out relying on its alerts for emergency or time critical escalation.

BB on Model and Technology TransparencyThe approach or the suppliers are named without the version and update discipline behind them. Naming a supplier is the entry to this band both here and on Model Supply Chain Disclosure, which ask different questions of the same disclosure: who receives the data, and what produces the output.
Vendor Published

Google Gemini generates the clinical answers, summaries and task suggestions from the patient context the doctor enters: lab values, vital signs, complaints, medications, notes and the status of work already done. The patient context is shown with each suggestion, and the guidance sources named are ICMR, WHO, AIIMS and national formularies.

The Gemini version, the retrieval design that brings in that guidance, any tuning and how a model update is approved are not described. Answers built on a specific patient's data are still unvalidated answers, and nothing yet measures their accuracy.

BB on Model Supply Chain DisclosureSubstantial partial disclosure, or a chain that is structurally short: an in house build, a cleared model that cannot be quietly swapped, or a deployment where the transfer does not occur at all. Naming the model provider exits the band below into this one; the axis rises from here on the completeness of the party list and on the terms that govern data once it arrives.
Vendor Published

The named chain is Google Gemini for AI processing, Supabase for the database and sign in, and Vercel for hosting. Patient context goes to the model provider with patients' names as well as clinical details; leaving out government identifiers does not make that transfer anonymous. WhatsApp becomes another recipient whenever a doctor sends a handover there.

The Gemini account terms, inference region, retention period and training permissions are not stated. The main recipients are known, without a contract level account of how clinical content is treated after it leaves Medows.

DD on Clinical and Operational EvidenceNo named deployment and no performance claim a reader can check. A figure published with no source sits here rather than higher.
Vendor Published

Medows was designed with junior doctors in Indian hospitals and offers a public demo of ward lists, notes and suggested tasks. Clinical case writing associated with pediatric resident Dr. Susmita Maji appears on the site, but it shows clinical reasoning rather than an institutional deployment or a measured benefit from the software.

No prospective results, patient counts, error rates or time savings are reported for the assistant. The demo shows how the interface works; how accurate its patient specific suggestions are, and whether handovers improve, remain untested.

CC on AI Safety and PHI StewardshipGeneral assurances of privacy and security that do not answer the questions artificial intelligence raises: what is retained, what reaches a model, and what happens to it there.
Vendor Published

Patient records stay while the account exists, discharged patients remain for reference until the user deletes them, and deleting the account removes its records, though encrypted backups may persist until an unstated rotation completes. Clinical context, including patient names, goes to Google Gemini to generate answers.

Medows limits its own rights over content to running the service, but the model provider's training and retention limits are not given. Doctors control sharing with colleagues and invited nurses, and seeing the context behind an answer helps catch a wrong one. No model safety incident process, investigation deadline or remediation commitment exists.

Regulatory and Compliance
CC on HIPAA and BAA PostureA status is stated but not supported: compliance is claimed, or business associate status stated, without the underlying document, including where the only privacy notice published covers the website rather than the service that handles patients. The mirror case grades here as well: a substantive privacy document that reaches the service, with no statement of business associate status anywhere and no scope position taken. One of the two elements the band above asks for is present, which is a grade below it and not a grade at the floor.
Vendor Published

The service privacy policy covers the patient names, demographics, vital signs, lab values, medications, clinical notes and task lists that clinicians enter, and explains sharing, transfers to the model provider, retention and deletion.

Medows is aimed at licensed professionals, with Indian law governing its terms, but it states no HIPAA business associate role or equivalent healthcare privacy position, and no standard agreement is offered. Clinical data handling goes beyond a website notice, without a contractual status that tells a hospital how the service fits its own obligations.

DD on Security Certifications and Trust CenterControls are asserted with nothing independent behind them, or nothing is published. Read the note before concluding anything: this is the grade most often corrected on a second pass, because assurance material frequently sits on a parent domain or inside an old announcement rather than on the product pages.
Vendor Published

Supabase storage is encrypted at rest and in transit, and row level security keeps each doctor's records apart from other users'. Doctors choose which colleagues can see a patient, invited nurses get limited, mostly read only access, and infrastructure maintenance can require access by the Medows team.

Those are basic access controls. No SOC 2, ISO 27001 or HITRUST assessment of the company, penetration testing schedule or trust portal is offered, and checking that invited colleagues are who they say they are is left to the inviting doctor.

CC on FDA and Regulatory StatusNo device claim is made and the product is scoped accordingly. Most administrative and operational products sit here and are not penalized for it, because this axis grades the appropriateness of the positioning rather than possession of a clearance. A stated limit on use, such as research use only or a clause that the product gives no medical advice, beside marketing that sells the product for clinical decisions also sits here, with both quoted, because the buyer has to ask which one governs.
Vendor Published

The terms say Medows has not been reviewed, cleared or certified by any medical device or health IT regulator, rule out its use as an approved decision support system, and call AI answers information rather than diagnosis or treatment advice.

The product itself returns differentials, drug doses, next steps and escalation criteria built on a specific patient's findings. That gap between disclaimer and function is left open, with no regulatory pathway or software exclusion offered to close it. The service is not an emergency system and does not replace the hospital record.

DD on AI Governance and Bias DisclosureNothing published on how model behavior is governed or tested. Multilingual operation with no subgroup performance sits here when the vendor markets recognition quality as a strength, because a caller the system failed to understand leaves no complaint and no record.
Vendor Published

Patient context appears beside each suggestion, and notes, orders and handovers are attributed to the signed in clinician. The terms acknowledge failure modes such as wrong units, invented citations and assumptions carried forward in a conversation.

Those make some errors easier to spot, but no model governance framework, evaluation method or monitoring process is described. Results across ages, specialties, languages or patient groups are not reported, and neither clinical references nor input from doctors amounts to a bias assessment or a controlled way to approve changes to the underlying model.

CC on AI Liability and RecourseMechanisms exist that let someone challenge an output, such as audit trails, source traceability or review before commit, with nothing standing behind the output and no route for the harmed party.
Vendor Published

Clinicians can check suggestions against the visible patient context, edit notes and decide which proposed tasks to add, which gives them a chance to challenge an output before acting. The service promises no answer accuracy, support response time or uptime, and its terms put clinical decisions with the treating physician.

Liability exclusions keep the exceptions that cannot lawfully be waived, including the provider's own negligence in specified cases. No output indemnity, error rate commitment or correction process is offered, and a general contact address is not a remedy for harm from an algorithm.

Integration and Deployment
DD on EHR and Interoperability DepthNo integration evidence. A connector described as available on request grades here until one exists.
Vendor Published

Everything in the workspace comes from what its users type in, and the patient list stays separate from the hospital's official documentation. A handover can be copied or sent to WhatsApp, and colleagues can share selected patients inside the service, which moves working information between people rather than between systems.

No EHR connector, standards based data exchange or chart writeback is offered, and Medows says plainly that it is not an EHR or hospital information system. Orders, lab results and medication administration are not synchronized with the record.

CC on Deployment Model and Data ResidencyA single hosted option with location implied rather than committed.
Vendor Published

Medows is a hosted web workspace, with Supabase for the database and sign in and Vercel for hosting, and Google Gemini processes clinical questions outside the application platform. Row level permissions separate records by account and allow deliberate sharing with colleagues or nurses.

Storage, backup and inference regions are not stated, and Indian governing law is not a commitment to keep data in India. No customer managed, dedicated or on premises option is offered, and reaching the list on several devices reflects a hosted account rather than local processing.

Commercial
AA on Commercial TransparencyPublished tiers with figures, a stated unit of charge, and a route to start without a sales conversation.
Vendor Published

Individual clinicians start free, with no card, no trial clock and no seat count, and the free tier includes the patient list, contextual AI answers and handover. No paid individual tier is planned while the product is still finding its shape.

Hospitals and departments arrange rollout through a direct conversation about the ward and its staffing, with no standard enterprise price. The terms let features and availability change and promise no service level, so implementation scope, organizational fees and any institutional support need a separate agreement.

CC on Setting and Specialty CoverageCoverage is claimed broadly without specifics, or stated clearly with nothing validating it yet.
Vendor Published

The workspace is built around hospital rounds, on call work and shift handover, with separate emergency, ward and discharged patient views. It is meant for licensed doctors and authorized clinical staff, including nurses, with trainees working within supervised attachments.

Clinical examples cover respiratory illness, cardiac problems, lab interpretation and medication questions, and some involve children, without any validated specialty, acuity or pediatric boundary. The terms rule out emergency reliance even though the interface includes emergency views and suggests escalation criteria.

Alternatives

Alternatives to Medows

Other products that do the same kind of work as Medows, and what each one does.

Diagnosis Pad is an offline clinical assistant for doctors that listens to a consultation and, as the conversation develops, offers the top three differential diagnoses, the top three recommendations with suggested questions to ask, and a clinical note summarizing the transcript at the end.

Avo is a clinician built decision support platform whose foundation is content rather than a model.

VUNO, a Seoul medical AI company founded in 2014, leads with DeepCARS, which predicts in-hospital cardiac arrest within 24 hours for patients on general wards from four routinely charted vital signs: blood pressure, heart rate, respiratory rate and temperature.

Glass Health is a clinical intelligence platform whose reasoning engine is the product.

Creyos, formerly Cambridge Brain Sciences and briefly Creyos Health, is a Toronto company selling digital cognitive and behavioral health assessment to clinicians.

Pymander Health is a free AI doctor that adults in the United States reach by text message, over SMS or iMessage, with no app to install and no account needed for a first consult.

Commercial

Pricing

Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.

Entry Price Pricing Basis BAA Tier Implementation Source
Free for individual clinicians
$0 baseline
Individual access costs $0 and includes the patient list, contextual AI answers, and handover. No card, trial deadline, or individual seat charge applies. Hospitals and departments arrange deployment and pricing directly, with scope shaped around the unit and its clinicians. No HIPAA business associate role or standard agreement is stated. No individual setup fee is stated. Hospital deployment, onboarding and integration charges are not listed and require a separate discussion. Vendor Published

The free individual offering is available while the product remains under active development, with no paid individual tier currently planned. Features and availability can change, and the standard terms promise no uptime or support response level. Organizational pricing, minimum commitments and the scope of institutional deployment are not set by the individual offer.