Hospital & Unit Operations
C

Cognosos

Cognosos, based in Atlanta, sells a real time location system for hospitals built around LocationAI, a machine learning engine that places tagged equipment at room level by comparing Bluetooth signals against a reference map learned at installation. Beacons go in ceilings, tags pass readings to gateways sitting in existing IT closets, and the cloud service does the locating, so each room does not need wiring. Staff use the Luminate portal to find infusion pumps, wheelchairs and other equipment, and ProPAR sets par levels for clean and soiled storage with alerts when stock falls short. The suite adds Cognosos Guardian for staff duress, temperature monitoring for refrigerators and freezers with reports for accreditation surveys, hand hygiene compliance and automated bed turnover.

Encounter sensing tags, launched at HIMSS in March 2026, use staff badges, bed tags and disposable patient wristbands that talk to each other without the location engine, logging when each visit starts and ends and sending a report to the EHR when the nurse leaves.

Jamaica Hospital Medical Center, part of MediSys Health Network, mapped about 600,000 square feet and tagged roughly 2,500 items, and its biomedical engineering lead reported annual equipment loss down 92% against the prior five years. Cognosos acquired the hospital location platform Cox Prosight in October 2024, and Siemens Healthineers chose it for asset tracking. Installation takes eight to ten weeks, the service is sold as a subscription through a demo, and the privacy policy tells customers not to submit protected health information.

AI Health Index verifiedNovember 20, 2026
Compare Cognosos with other vendors
Founded
2014
Headquarters
Atlanta, Georgia, United States
Categories
hospital-operations
Indexed Products
Cognosos Healthcare RTLS, LocationAI, Luminate, Cognosos Guardian, ProPAR, Encounter sensing tags
Buyer Segments
Hospital clinical engineering teams, Hospital operations and equipment managers, Health system security and facilities teams
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

LocationAI is the part that learns: during installation the team samples signals zone by zone, the engine builds a reference model, and incoming tag readings are classified into rooms with what the company calls room level precision. Asset tracking, utilization reports and par level alerts all depend on that estimate.

Much of the suite works without it, though: tags, beacons and gateways are hardware, Guardian duress alerts and temperature monitoring are sensor workflows, and the 2026 encounter tags log proximity peer to peer with no location engine at all. Machine learning is central to locating equipment and absent from several other modules.

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

Hospital teams set minimum inventory levels by zone, choose which assets to monitor and manage notifications in Luminate, and staff decide what to do when a replenishment alert fires. Guardian sends duress alerts to security, which then switches to high precision tracking for the incident. The encounter tags act more on their own: when a nurse leaves the room a report goes to the EHR automatically, rooms are marked ready for turnover and equipment is flagged as soiled. No confidence threshold holds back a doubtful location or encounter, and no step lets staff review an automatic EHR entry before it posts.

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

LocationAI, launched in 2022, is described in a healthcare white paper: installers sample the signal environment, label readings by zone, and the engine builds a reference model that new tag signals are compared against to classify the room. Training at installation is separated from ongoing detection, and the company explains how the model is updated when construction or layout changes would otherwise degrade accuracy, a common failure of older systems. The algorithm family, software versioning and retraining results after a facility change are not given, and the encounter tags' proximity logic is not described.

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 architecture is first party from end to end: Cognosos tags and beacons collect Bluetooth readings over its patented long range wireless network, gateways forward them, and the company's own LocationAI engine estimates location in its cloud service, with no outside language model involved. The privacy policy mentions third party providers for hosting, analytics and support without naming them, and the cloud host for LocationAI and Luminate is not identified. No processor list covers location history, staff data or encounter records with retention terms for each party, which matters most for the patient linked encounter path.

BB on Clinical and Operational EvidenceNamed deployments with dated outcome figures and enough method to test them, or published research short of independent validation.
Vendor Published

Jamaica Hospital Medical Center, part of MediSys Health Network, ran a proof of concept, mapped about 600,000 square feet in its 2023 rollout and tagged roughly 2,500 items in the first phase. Its biomedical engineering lead told RFID Journal that annual equipment loss fell 92% against the five years before installation, and the article reports visibility into 1,700 assets at the time.

The company also claims a return on investment in about nine months against 16 or more for other systems, without a method. The encounter tags have internal validation only, and no study measures clinical or rounding outcomes.

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

The location model runs on radio readings from tags and the facility's reference survey, not patient records. The privacy policy, which reaches the subscription service, covers customer personnel data including geolocation, keeps personal information while there is a business need or for backup and audit, and allows anonymized or aggregate usage data for analytics. Encounter tags report visits rather than following staff continuously.

What identifies a patient on a disposable wristband, how long encounter records and patient associations are kept, whether any of that data trains models, and how a misclassified encounter is caught are not described.

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 privacy policy reaches the subscription service and says Cognosos does not knowingly collect protected health information, asking customers not to submit any through the site or the service. It also mentions a set of terms that apply only to protected health information submitted through the services, but that section is not on the page, and no business associate agreement is mentioned anywhere.

Meanwhile the encounter tags associate equipment with the current patient on disposable wristbands and send encounter reports to the EHR. The no protected information position and the marketed patient linked workflow do not meet, and nothing explains which applies.

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

The company describes monitoring its hosted platform, releasing security updates and protecting personal information under its privacy policy, and the temperature module produces audit reports for The Joint Commission, DNV, CDC and Vaccines for Children inspections, which concern the hospital's compliance rather than Cognosos's own controls. No SOC 2 report, HITRUST or ISO certification, penetration test cadence or trust center is offered for the healthcare platform. Gateways sit inside hospital IT closets and Guardian carries duress alerts, so customer security teams have only the company's own description of its controls to go on.

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 suite is sold for hospital operations: finding equipment, managing par levels, staff duress response, temperature monitoring, hand hygiene compliance and documenting staff visits. Many tracked items are medical devices, but locating them is not a device function, and no product makes a diagnosis or treatment decision about a patient. No device claim is made and no exclusion is cited. Encounter records that flow into the EHR describe when care staff were present rather than a patient's clinical state, which keeps the positioning administrative and matches what is sold.

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

Location accuracy is presented as room level with high confidence, and the white paper explains that radio conditions vary with walls, equipment and layout, which is why the model is trained for each facility. No governance process names who approves model changes or how accuracy is evaluated across facility types, floor plans, construction changes and dense equipment areas.

The encounter tags, which judge whether a nurse visited a patient and feed a rounding compliance view, entered launch after internal validation without results by unit, shift, staff role or room type. How errors are distributed across the spaces and people the system monitors is not measured anywhere a hospital can see.

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

Customers raise problems through a Product Support ticket in the Luminate portal or by email, choosing an issue type such as the portal, gateways or asset tags, and a field services engineer follows up. No response time is stated, and the support guide says nothing about reporting a wrong location or a missed encounter, or about correcting location history once recorded. Hospitals can inspect location history and operational reports themselves. The website terms disclaim warranties, and no service commitment, accuracy guarantee or remedy appears for a device sent to the wrong room or a rounding record that misstates a visit.

Integration and Deployment
CC on EHR and Interoperability DepthIntegration is claimed through standards or a middleware layer with no system named and nothing to verify.
Vendor Published

Encounter tags send a report to the EHR automatically when a staff member leaves a patient's room, and bed turnover notifies the EHR that a room is ready, while bed tags associate telemetry units and other equipment with the current patient. Staff duress connects to public address and security systems. No EHR is named for these entries, no interface specification or marketplace listing exists, and no deployment shows the encounter writes running in production. The Jamaica Hospital Medical Center case concerns equipment tracking, so the EHR path rests on product description alone.

BB on Deployment Model and Data ResidencyOptions and residency are stated with isolation or the processing path left open.
Vendor Published

Beacons sit in ceilings and tags report to a gateway placed in an existing hospital IT closet, which sends readings to the cloud where LocationAI runs and Luminate is hosted. The privacy policy states that Cognosos stores its data in the United States and acts as data processor for customer data. The encounter tags work peer to peer without fixed infrastructure, a separate path from the location service. Tenant isolation, backup regions and the route encounter data takes to an EHR are not described, so residency is committed for personal data while the patient linked path is left open.

Commercial
CC on Commercial TransparencyNo price is published and the posture is discoverable: a buyer can establish how the product is sold and what drives the cost before contacting the vendor. Most of the index sits here.
Vendor Published

The hospital product is a subscription service bundled with tags, beacons, gateways, facility mapping, installation and training, sold through a demo. An eight to ten week installation runs in five phases, the first of which needs no entry into patient care areas, and account reviews and named support continue after go live. No price appears per tag, bed, building, user or year, and hardware, module and implementation charges are not listed. A hospital can see the components and the timeline of the purchase, while the cost depends on coverage area and the modules chosen.

BB on Setting and Specialty CoverageCoverage is named with validation behind part of it.
Vendor Published

Hospitals and health systems are the healthcare buyer, with asset tracking across wards, emergency departments, intensive care units and clean and soiled storage, and Guardian staff safety covering campuses indoors and out. Jamaica Hospital Medical Center validates the equipment workflow for infusion pumps, defibrillators and other mobile devices at a large urban hospital, and Ochsner Lafayette appears among customer logos.

Temperature monitoring, hand hygiene and the encounter tags each have a defined hospital setting but no comparable case. The same location technology also serves automotive and logistics customers through separate offerings.

Alternatives

Alternatives to Cognosos

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

Kontakt.io sells a care operations platform that connects room level location data with hospital records and work queues, used by more than 200 hospitals including Beth Israel Lahey Health, Sentara, Kaweah Health, Mercy Health and Northeast Georgia Health System.

SureCost sells pharmacy supply software that brings purchasing, inventory and drug shortage forecasting into one workflow, under the Smart Supply name.

LeanTaaS sells iQueue, cloud based capacity management software that predicts demand for scarce hospital assets and helps staff use them. iQueue for Operating Rooms predicts which block time will go unused, releases it earlier and matches open time with surgeons, and adds patient…

Aimbient, known until July 2026 as Surgical Safety Technologies and the maker of the OR Black Box, sells the Aimbient Suite: room cameras, operative video, audio and device telemetry captured from every procedure, read by more than 25 purpose built AI models that turn the recording into…

Copient Health, based in Atlanta, sells ARDEN, software for the perioperative leaders who manage operating room block time at hospitals and ambulatory surgery centers.

CalmWave combines bedside monitor signals with medications, interventions and EHR events to help hospital teams manage alarm burden.

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
Contact sales
Hospital location software is sold as a subscription with facility hardware, mapping, installation and training, scoped by site, coverage area and modules. The privacy policy asks customers not to submit protected health information and refers to separate terms for it, and no business associate agreement is offered. An eight to ten week installation covers hardware, mapping, device setup and training, with no fee stated. Vendor Published

No amount appears per tag, bed, building or subscription period, and hardware and module charges vary by deployment.