The capabilities Chiron reaches for, by workflow.

490+ customer-facing capabilities, counted from the live codebase — 420+ user-facing features, 50+ AI capabilities, and 26+ background automations. Not a menu you operate by hand, but the toolkit Chiron reaches into as it runs the encounter — calling each through a visible, named tool-call on Eve-Healthcare™ F5/reasoner and drafting the result for attestation. The deep-dives below are the curated highlights, grouped by where they live in the consultation workflow, and the full inventory is published in full for machines so you can ask Eve about any of it. For specialty-depth treatment of any group, follow the specialty link in that section. The clinician remains the decision-maker on every output.

Eleven groups, one system.

The full inventory organizes into eleven groups — the same taxonomy the machine-readable corpus publishes. Group counts are per-group floors. The workflow deep-dives that follow walk the highlights of these groups through the consultation, intake to signed chart.

The capabilities Chiron reaches for, in one screen.

Each one links to the page that treats it in depth. Use this as the index to everything below.

The reasoning is visible, grounded, and never trusted blind.

• —Eve-Healthcare™ F5/reasoner — a compound five-model reasoning architecture augmented by a dedicated vision route, not a single model behind a prompt
• —Conversational clinical reasoning over the record — grounded question-and-answer with inline citations; in image-to-plan any citation that does not match retrieved case material is removed, and in Ask Chiron a citation that cannot be verified is labelled as such
• —Differential diagnosis support — Bayesian confidence with qualitative tiers, discriminating features named per differential; the clinician evaluates and selects
• —Symptom intelligence — from the chief complaint, the highest-yield symptoms to screen for next, each with the differentials it separates, where it is captured and the red flags; the system proposes what to ask, the clinician decides
• —Pre-existing condition intelligence — prior conditions ranked for this specific patient by clinical impact and risk category, with the screening questions that confirm or exclude each, surfaced at intake
• —Country tailoring (available in demo) — set the clinic’s country once and Chiron shapes its reasoning, medicines and safety text to it and to the patient’s sex, age, weight and pregnancy, showing a “Tailored for” line under its answers; set up for Pakistan, United States, United Arab Emirates, Saudi Arabia, India and Bangladesh
• —Risk stratification — Wells (PE), CURB-65, CHA₂DS₂-VASc, Alvarado and Fleischner computed from the record, each with the inputs behind the score
• —Confidence calibration — Bayesian likelihood bands with percentage ranges for differentials, and a four-tier evidence scale for imaging findings with "cannot exclude" as a first-class state
• —Clinical evidence synthesis — live synthesis of canonical guidelines and peer-reviewed literature, source-grounded with explicit guideline anchors
• —Honest reasoning stream — a live, step-by-step trace of the real work, engineered never to fake a progress bar; the chain-of-thought never leaks to the transcript
• —Glass-box tool-calling — one visible activity step per real operation (retrieve, reason, compose, persist), never a fabricated timer, never a foundation-model name
• —Must-review-before-final gate — every AI-drafted artifact carries a non-dismissible CA AB-489 review banner; the clinician attests and signs
• —Human-in-the-loop by architecture — decision support only; the clinician is the decision-maker on every output, and no regulatory-clearance claim is made

One workspace runs the encounter, intake to signed plan.

• —An eight-section consultation workspace that runs the encounter end to end — chief complaint through plan and coding
• —Visit scribe — the recorded encounter is transcribed and drafted into the visit’s sections for the clinician to review
• —A live reasoning surface embedded in the workspace, streaming the specialist reasoning as the case develops
• —Dictation for radiology reports and push-to-talk voice questions to Ask Chiron
• —AI-drafted assessment and plan, each item accepted, edited or rejected by the clinician before the note is signed
• —Encounter context carried across every section, so each draft sees the whole visit
• —Red-flag surfacing before the clinician opens the chart, drawn from the pre-visit interview
• —Orders, referrals and follow-up captured inline with the consultation
• —Each piece of evidence in a reasoning case shows its source at review time

Chiron organises the study and highlights what to check — the radiologist reads it and signs.

• —A dedicated vision route analyses the images through structured reasoning, streaming its reasoning as it works
• —One structured second-look covering five checks — structure, pathology, artifacts, missed zones, cross-window correlation — in a named order; the radiologist drafts and signs the impression of record
• —Standardized reporting categories — BI-RADS, LI-RADS, PI-RADS, TI-RADS, Lung-RADS and O-RADS — assigned by the radiologist, with Fleischner 2017 follow-up guidance computed from the reading
• —DICOM viewer — 2D, multiplanar reconstruction (MPR) and 3D rendering with annotation tools
• —Possible findings marked on the image and naming the images they were seen on, for the radiologist to check
• —Cognitive-bias counter-measures against satisfaction of search, anchoring and premature closure, built into the review
• —Critical findings — shown in their own section, on a distinct notification path, with the communication and read-back logged
• —A structured report form, pre-filled from the review, that the radiologist edits and signs

The values are extracted, not invented — then read for pattern.

• —Lab interpretation that looks for patterns across analytes, with results grouped by panel
• —Ground-truth value extraction — lab values read from the source report by a deterministic layer, separate from the reasoning engine; the model may label a value, it cannot invent a digit
• —Critical values flagged before a result reaches the ordering clinician, with a communication clock that escalates an unacknowledged critical result
• —Clinic-configured reference ranges matched to the patient’s age, sex and pregnancy status when the report prints none
• —Trend recognition across serial results

Coded to the pharmacology. Checked before it is signed.

• —Medication reference — RxNorm names with FDA label sections (indications, dosing, contraindications, interactions, specific populations)
• —Four-tier interaction severity — critical (contraindicated), major (monitor closely), moderate (caution), minor (informational) — with mechanism disclosure and a recommendation per interaction
• —Drug-disease and dose-adjustment checks run against the patient’s own record
• —Pharmacology evidence anchoring — each interaction cites the canonical source that warrants its severity tier and recommendation

The whole history, reasoned over together.

• —Reasoning across the whole chart — Ask Chiron and the reasoning case read records, documents, labs and imaging together
• —Patient chart — demographics, problem list, medications, allergies and vitals, each with add/edit/resolve lifecycles
• —Encounter and visit history — typed intake, visit context and completion evaluation
• —Medical-records upload read into page-level text with its provenance, available to Chiron’s reasoning
• —Full-chart review and multi-document synthesis as a one-shot query
• —Reconciliation of patient-reported medications and problems against the chart
• —Appointment management with status lifecycle and check-in

The intake is done before the clinician walks in.

• —Pre-visit patient interview — structured intake of history, review of systems, social and environmental factors and red-flag triggers, output structured for the consultation
• —A patient-facing portal — pre-visit interview, post-visit follow-up, patient education and consent capture, mobile-first
• —Patient education written to a grade 6–8 reading level, with the measured reading level shown
• —Patient handouts in 7 languages and plain-language patient versions of signed reports in 15, right to left preserved; Punjabi, Sindhi, Pashto are AI translations and are labelled as such
• —Patient consent to AI use recorded against the exact wording shown, with withdrawal
• —Automated Decision-Making Technology notice and opt-out for clinicians per CCPA / CPRA

Every line of the note traces to where it came from.

• —AI-drafted notes in the clinician’s chosen language — English, Arabic, German, Spanish, French, Hindi, Italian, Japanese, Korean, Portuguese, Urdu and Chinese; right to left for Arabic and Urdu
• —Document versioning — an immutable SHA-256 hash at signature time; amendments recorded as new versions, the original signed version stays verifiable
• —Signature integrity — document hash plus signing-clinician identity, timestamp and audit-chain entry; any later modification fails verification
• —A signing queue that steps through each draft for individual review and signature
• —On-demand PDF export of every document; radiology report PDFs carry the CA AB-3030 disclosure

Purpose-built clinical views — that refuse to draw a false picture.

• —Practice and clinical dashboards over encounters, throughput and outcomes
• —Physician-agreement tracking as an operational trust metric
• —Workflow insight surfaces — worklists of what the system read, flagged and drafted
• —Documentation and turnaround analytics
• —Every chart carries a text equivalent

Run the organization, not just the encounter.

• —Clinic and organization provisioning, user and role administration
• —A role-based access-control kernel with session management and MFA reset
• —A platform console for creating and managing organizations, cross-tenant user lookup and platform statistics
• —Notifications — in-app and push, with per-user preferences
• —In-product problem reports, reviewed and resolved by the platform team
• —Tenant configuration — locale, specialty context and feature enablement
• —Usage visibility per organization — lab reports and radiology uploads counted for the current month, so a plan is managed against what was actually used rather than what was estimated
• —The organization’s plan and renewal date visible to its administrators
• —Clinician profile — name, photo, credentials, specialty and AI-drafting language

Every signature is provable. Every tenant is isolated.

• —Fail-closed tenant isolation — deny-by-default PostgreSQL row-level security defined at the database layer, independent of the application layer
• —AES-256-GCM field-level encryption on PHI; PHI de-identified in the reasoning pipeline, which works on the minimum it needs
• —An append-only, tamper-evident audit trail — HMAC plus previous-hash on every clinical action, verified hourly; a database trigger blocks edits and deletes even by the record’s owner
• —Fixed-threshold clinical alerts (home readings, triage) that reach Today independent of the model’s judgment
• —Server-authoritative CA AB-3030 disclosure on every AI artifact, non-dismissible by design
• —AI-use disclosure per CA AB-3030 / AB-489 — the clinician attests and no clinical licensure is implied
• —Immutable document verification — a SHA-256 hash binds each attestation to the exact rendered PDF
• —Automated-decision preferences — a clinician can opt out of automated AI decision-making under California consumer-rights law and require the reasoning to be shown on every output; each preference change is logged for compliance
• —Platform status and incident notices shown in-product