Suki vs TORTUS (2026)
The two products in this category that act inside the record rather than writing to it, and they take opposite routes there. Suki uses a voice command layer over deep bidirectional integrations with Epic, Oracle Health, athenahealth and MEDITECH, staging orders for clinician review. TORTUS uses vision and click based interaction to operate a record system through its own interface, which reaches systems that never agreed to an integration. The disclosure gap decides it. TORTUS publishes a hallucination removal rate, a peer reviewed error reduction and an error ontology, and filters unsupported statements before the clinician sees them. Suki publishes no accuracy figure for command interpretation, no escalation behaviour for a misheard command and no governance artefact at all, while its command layer touches orders. For a United States health system Suki is the available option; ask it for the numbers TORTUS already publishes.
- Availability and record system depth in the United States, with deep bidirectional integrations named across Epic, Oracle Health, athenahealth and MEDITECH plus partner routes to MEDENT, Azalea Health and WellSky, against a product concentrated in the NHS.
- The command layer is broader than documentation. Ordering, chart navigation, order staging and patient specific question answering by voice, plus coding assistance at the evaluation and management, HCC and ICD-10 levels.
- A developer platform that lets other healthcare software vendors embed the capability in their own products, which is a distribution route no other scribe in this pair offers.
- It filters before the human rather than after. Every generated statement is verified against the consultation and unsupported content is removed before a clinician sees it, with 92.7 percent of detected hallucinations removed published as a live metric.
- The evidence base is prospective, multi site, publicly funded and independently evaluated across nine clinical sites and more than 17,000 patients, against a competitor with no controlled evaluation or published accuracy result of any kind.
- Governance is documented rather than absent. An error ontology built from clinician labelled transcripts, accent testing performed by the deploying hospital, and a stated position of no model training and no data retention corroborated by that hospital to its own patients.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Suki and TORTUS are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
Side by Side
Each record in one paragraph
Written to be quoted whole. Each paragraph states what the AI Health Index verified about the vendor, with the caveats attached. Generated from this pair’s live capability grades, so it moves when a grade moves.
The AI Health Index awards Suki its top capability grade on AI Centrality and EHR and Interoperability Depth. Set against TORTUS, Suki grades higher on EHR and Interoperability Depth. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
The AI Health Index awards TORTUS its top capability grade on several axes, including AI Centrality, Autonomy and Oversight Model and Model and Technology Transparency. Set against Suki, TORTUS grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and Clinical and Operational Evidence. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
Questions buyers ask
Should we choose Suki or TORTUS?
On the axes where the AI Health Index separates them, Suki grades higher on EHR and Interoperability Depth, and TORTUS grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and Clinical and Operational Evidence. TORTUS leads on the greater share of scored axes, but the split means the decision turns on which constraint is binding rather than on an overall winner.
Where do Suki and TORTUS differ most?
The widest separation the AI Health Index records between Suki and TORTUS is on Model and Technology Transparency, where Suki grades C and TORTUS grades A. That axis sits in the AI Capability group, so it should carry the most weight for a buyer whose binding constraint is how much of the work the model itself is trusted to do.
Where do Suki and TORTUS grade the same?
The AI Health Index grades Suki and TORTUS the same on several axes, including AI Centrality, Model Supply Chain Disclosure and HIPAA and BAA Posture. Neither holds an advantage the index can evidence on those axes, so they should not carry weight in a selection between these two.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Ambient Scribes page.
Both products act on the record and neither publishes what this comparison most needs from Suki: an accuracy rate for interpreting a spoken instruction, an escalation behaviour when one is misheard, and a confidence threshold below which a human must intervene. A misinterpreted medication instruction is a clinical action rather than a text correction.
TORTUS asserts HIPAA alignment with no business associate agreement template located and holds a self certified UKCA Class I registration rather than a reviewed clearance. Neither vendor publishes a rate card, and Suki offers no free tier or trial.