Droxi vs Epic In Basket Art (2026)
The specialist against the feature that is already switched on, and the honest answer is that they solve different halves of the inbox. Art drafts replies to patient medical advice messages, is deployed at roughly 150 health systems, and is the only product in this category with independent peer reviewed evidence behind it. Droxi does not draft replies for a clinician to send so much as work the inbox: it reads each inbound item against the patient's full record and dispositions laboratory results, refills and clinical documents in primary care. A health system running Art still has a physician opening every result and every refill request. That is the gap Droxi is aimed at, and it is the reason both can be justified in the same organisation, which is not something you can say about most pairs in this index.
- The oversight architecture is the strongest in this category, reading each item against the full record before proposing an action, with the boundary of what it will act on stated rather than implied.
- It is native to the record system with no separate login and no parallel application, listed on a major marketplace rather than only asserting integration.
- Scope is deliberately narrow and disclosed, primary care and three item types, which is an honest position against a feature that reaches every message type at once.
- Independent peer reviewed evidence exists for it and for nothing else in this category, and that evidence is candid about the limits of what drafting achieved rather than promotional.
- Deployment at roughly 150 health systems and medical groups, orders of magnitude beyond anything else here, so the failure modes are documented somewhere before you meet them.
- No new vendor, no new security review, no additional data processor, and the model named by the vendor rather than left unstated, which is more than most pure plays disclose.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Droxi and Epic In Basket Art 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 Droxi its top capability grade on AI Centrality. Set against Epic In Basket Art, Droxi grades higher on AI Centrality and AI Liability and Recourse. 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 Epic In Basket Art its top capability grade on several axes, including Model Supply Chain Disclosure, Clinical and Operational Evidence and EHR and Interoperability Depth. Set against Droxi, Epic In Basket Art grades higher on several axes, including Model and Technology Transparency, Model Supply Chain Disclosure and Clinical and Operational Evidence. Its thinnest published disclosure sits on AI Liability and Recourse. 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 Droxi or Epic In Basket Art?
On the axes where the AI Health Index separates them, Droxi grades higher on AI Centrality and AI Liability and Recourse, and Epic In Basket Art grades higher on several axes, including Model and Technology Transparency, Model Supply Chain Disclosure and Clinical and Operational Evidence. Epic In Basket Art 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 Droxi and Epic In Basket Art differ most?
The widest separation the AI Health Index records between Droxi and Epic In Basket Art is on AI Centrality, where Droxi grades A and Epic In Basket Art grades C. 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 Droxi and Epic In Basket Art grade the same?
The AI Health Index grades Droxi and Epic In Basket Art the same on several axes, including Autonomy and Oversight Model, AI Safety and PHI Stewardship 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.
What have Droxi and Epic In Basket Art not disclosed?
At the last review, at least one of Droxi and Epic In Basket Art published thin or absent detail on AI Liability and Recourse. The AI Health Index treats an absent disclosure as a gap in the public record rather than a failure of the product, so these are the axes to get in writing during diligence instead of inferring from the grade.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Clinical Inbox & Messaging AI page.
Epic publishes no fairness, subgroup, reading level or language performance disclosure for a feature drafting patient facing text at national scale, which is the largest single gap in this category because a reply pitched at the wrong reading level or register fails without anyone noticing. Droxi publishes no model name, model card, accuracy figure or subgroup analysis, and its only security claim is a compliance assertion rather than an attestation.
Published research on drafted portal replies has generally found the benefit in cognitive burden rather than in minutes saved, so treat any time savings business case cautiously. In both products the clinician signs the reply, so attribution and licensure exposure sit with the signer.