DeepCura

The agent network is the product and there is no non AI business underneath. The architecture goes further than most in this category by decomposing the work into eight separately scoped agents rather than one model producing a note, which is a design choice with real consequences for how failures surface and where a buyer can intervene.

Wide autonomous reach with no published limits. The orders agent drafts laboratory tests, imaging, durable medical equipment and prescriptions; the billing agent generates CPT codes with linked diagnoses; the referrals agent drafts letters and handles prior authorisation; the receptionist answers calls unattended; and the scribe writes back per field into structured EHR data rather than dropping text for a clinician to place.

Per field write back is the deepest form of automatic entry in this category and it removes the natural pause that transfer based products preserve. No confidence threshold, accuracy rate, abstention behaviour or review gate was located for any agent. Same call as Oracle Health, Sunoh.ai and Knowtex on the order drafting question.

Architecture is described clearly, with each of the eight agents given a defined scope and per field write back specified rather than implied, which is more structural detail than most vendors publish. What is entirely absent is measurement: no accuracy figure, no model card, no named models, no error rate and no evaluation methodology for any of the eight agents, including the ones generating prescriptions and billing codes.

Nothing identifies any party in the chain: no model or model family, no foundation model provider, no hosting arrangement and no sub processor list was located in two passes. The architecture is described in more detail than most, with eight agents carrying defined scopes and per field write back, so a buyer can see the shape of the system while learning nothing about what runs it or who else touches the content moving through it.

An eight agent design also implies more model calls per encounter rather than fewer, so whatever unnamed parties are involved are involved repeatedly, and the agents generating prescriptions and billing codes are handling the most consequential content in the product. End to end encryption is stated and a business associate agreement is offered to all covered entities, which bounds obligations without naming anybody. Ask which models the agents invoke, whether any are third party, and for a sub processor list.

A 4.6 out of 5 rating on a software review site is the only third party signal located. No study, controlled evaluation, accuracy benchmark, clinical outcome data or named health system deployment. Note also that a large volume of comparative content about this category is published by DeepCura itself, reviewing and ranking its own competitors, which is the self interested source pattern this index flags; to its credit those pages carry a dated disclaimer telling readers to verify with the vendor, which is more responsible than most comparison marketing.

End to end encryption is stated and a business associate agreement is offered to all covered entities rather than only to enterprise accounts, which matters for a self serve product an individual clinician can adopt. No retention schedule, de identification practice or statement on whether customer data trains models was located, and those are the decisive disclosures on this axis.

States HIPAA compliance and provides a business associate agreement to all covered entities, available through a self serve path rather than requiring enterprise negotiation, which is a genuinely lower barrier than most of this category offers a small practice. Held at B because the agreement terms are not published for inspection before signup.

One phrase here should be read carefully, because it is doing work it has not earned. DeepCura describes SOC 2 ALIGNED security practices. Aligned is not certified, attested or audited: it describes an intention to resemble a control framework, and any organisation can claim it without an auditor ever being involved. It is not comparable to the SOC 2 Type II reports held by Tali AI or the ISO 27001 certification held by S10.AI.

Against that, CASA certification is claimed and is a real external application security assessment, though narrower in scope than SOC 2. Graded C for holding one genuine but narrow assessment while using language that implies a broader one. Watch for SOC 2 aligned, SOC 2 ready and HIPAA compliant infrastructure across this category; none of the three is an attestation.

No clearance claimed and none required for the ambient note itself. The flag raised in the earlier assessment is confirmed, and it understates what is shipping, because these agents do not draft for review, they write.

The platform deploys eight agents around the scribe. Diagnoses are extracted, mapped to SNOMED and ICD-10 and written to the problem list. Allergies are captured with severity, coded and written to the allergy section. Medications are coded and written to the medication list. Orders covering labs, imaging, durable medical equipment, vaccines and prescriptions are placed through the record system's order interface. Billing codes are pushed to the charge slip. Referrals including prior authorisation are automated, and follow up appointments are booked during the visit.

Writing structured clinical data into the chart is a different object from producing a narrative note a clinician signs. The signature is a clear control point for a note. It is far less clear what the control point is for a coded allergy already written to the allergy list, and a buyer should establish where human confirmation sits for each agent rather than assuming the review step governing the note governs the rest of them.

One consequence deserves separate attention and is the sharpest safety question on this record. The vendor states that coding allergens to standard vocabularies and validating them against the record system's own database ensures every allergy entry works with that system's built in clinical decision support and drug interaction checking. Machine generated allergy data therefore becomes the input to a downstream safety system the clinician treats as authoritative. An error in capture does not stay in the note. It propagates into interaction checking, and nothing in the workflow marks that entry as machine derived.

Markets appear to be United States only on the evidence located.

Two governance relevant designs, no governance disclosure. The billing agent produces CPT codes with linked diagnoses and the platform markets billing integrity, which places it on the milder end of the coding gradient this index tracks from MarianaAI through Sayvant and S10.AI. Patient intake is offered multilingually, with patients completing forms in their preferred language, yet no fairness statement, subgroup analysis or performance disclosure by language was located. Marketing a multilingual patient facing intake without any evidence of cross language performance is the specific gap.

Two passes located no accuracy or error figure, no published limitations and no warranty, indemnity or remediation commitment, and the scope of that absence is what makes this grade sit lower than the architecture might suggest. The product is described as eight agents with defined scopes and per field write back specified rather than implied, which is more structural detail than most vendors publish and is genuinely useful.

No measurement exists for any of the eight, including the agents that generate prescriptions and billing codes. Those two outputs carry the highest consequences available in this category: a wrong medication or dose reaches a patient, and a wrong code shapes what is billed and creates federal false claims exposure for the practice submitting it. A vendor precise enough to specify which fields each agent writes back to could be precise about how often each one is right.

One genuine credit belongs on the record. A business associate agreement is offered to all covered entities rather than reserved for enterprise accounts, which matters for a product an individual clinician can adopt, because it is the instrument that makes their use of it lawful and many self serve vendors gate it. It governs the handling of protected information rather than the correctness of output, so it does not move this grade, but it is the right default. Ask for an error rate on the prescription and coding agents specifically.

Deeper than the price point suggests and honestly bounded. Bidirectional per field write back is supported for seven named systems, Epic, eClinicalWorks, athenahealth, OptiMantra, AdvancedMD, Veradigm and CharmHealth, and per field structured write back is the distinction that separates real integration from dropping a block of text into a note.

The vendor also states plainly that providers on any other EHR can still use the product but must copy notes manually, which is the kind of limitation most competitors bury. Held at B because seven integrations is narrow against vendors claiming dozens, and no certification programme membership or integration architecture was verified in this pass.

This record answers the question this index asks first of any ambient scribe, and it answers it by name, which almost no vendor in this lane does.

Encounter processing runs on a third party model service, and the vendor not only says so but lets the provider choose which one from inside the platform, naming the major commercial model families as the options. Speech recognition uses a named commercial medical speech engine. The platform is described as running on a major public cloud, with a completed Google CASA Tier 2 security assessment and business associate agreements available to covered entities.

Naming the model providers is a real transparency and is credited here. Most competitors in this category leave a buyer to infer whether encounter audio leaves the vendor's environment at all, and several imply that it does not while generating structured notes from consultation audio.

Two things hold the grade short of the top. No hosting region is named, no residency option is offered, and no subprocessor list carrying retention terms was located, so a buyer knows which companies process the encounter but not what those companies retain, for how long, or under what enterprise terms this vendor holds with them. And the model choice, useful as it is, moves that question onto the customer without giving them the answer: selecting a different model changes which company processes the consultation, and the retention posture that follows is not published per option.

Ask for the enterprise terms held with each named model provider, whether zero retention is configured on those accounts, and where audio and transcript sit at rest.

The most complete commercial disclosure located anywhere in this category. The full per seat volume ladder is published rather than implied: 129 US dollars a month for seats one and two, 116 for seats three to five, 110 for six to ten and 101 for eleven and above, with each seat billed at its own tier so the blended average is explained rather than left to the buyer to work out, plus an annual alternative at 999 dollars per seat.

A free trial requires no credit card, cancellation is self service with no fees, and checkout is direct. Most notably, when the vendor compares its bundle against buying the components separately it names the comparator products and dates the estimate, which is a disclosed methodology rather than an unsourced savings claim. That is exactly what this axis rewards.

Ambulatory across a claimed 40 to 50 specialties, sold to physicians, therapists and practice managers, with multilingual patient intake extending coverage to non English speaking patients at the front of the encounter rather than only during it. Held at B because the specialty count is asserted without enumeration and no inpatient, emergency or acute capability is documented.