AI-native revenue cycle automation
ClaimVise gives US medical practices, and the billing teams that serve them, seven AI agents and three secure connectors for eligibility, chart retrieval, coding and NCCI, MUE and payer-rule checks. AI that works under your team's review: your people approve every claim and decide what gets posted. Proven first in hematology and oncology, built for every specialty.
Live with a billing-agency client. What is in place today, and what is planned.
Human oversight
ClaimVise is built to support billing teams, not replace them. Here is where a person stays in control.
Nothing is posted into a practice's billing system until a reviewer approves it. A claim can also be exported as an 837P file instead.
The connector checks whether a document is signed. A draft is never coded from.
When a connector meets a screen it does not recognize, it stops and says what happened and who should fix it. It does not guess, and it never retries a failed row on its own.
The AI proposes codes and flags risks. Supervisors and coders review the exceptions, and every override is written to the audit log.
See how PHI is protected and what is still planned on the HIPAA page.
The agent team
Legacy RCM tools wrap software around a coding team. ClaimVise puts agents at the center of the work. They read the note, code the claim, check it against the rules, assess denial risk and log every decision. A human supervisor reviews every claim before it is exported or posted, and the agents flag the ones that need a closer look.
Reads clinical documentation in any format.
Typed clinical notes, PDF superbills, handwritten or scanned charts, and OncoEMR charts with their lab results and medication administration records (MAR). Extracts assessment diagnoses, documented procedures, time spent and infusion data into structured output ready for the Coding Agent.
Assigns ICD-10 and CPT codes with a confidence score.
General-purpose medical coding across specialties: E/M, procedures, preventive visits and infusion. Two-pass architecture: a fast model reads the structured extraction and a stronger model codes it against specialty-aware rules, backed by CMS reference data that covers every specialty. Proven in depth in hematology and oncology; for any other specialty we validate on your own claims before routine use.
Checks every claim against deterministic rules before AI gets a vote.
About 2.6M NCCI procedure-to-procedure pairs from the current CMS release, MUE unit limits, CMS modifier rules (JZ, JW, KP, KQ, Q0, Q1, XU), ICD-10-CM validity and HCPCS existence, plus payer-specific rules layered per agency, practice and payer. Reference data is refreshed every CMS quarter. A claim with a blocking finding is held until a person clears it.
Scores claim risk before submission.
Hybrid architecture. The rules engine scores known violations first. A second pass adds an AI risk adjustment. The final score places the claim in a low, medium, high or critical risk lane. It is a detector that helps reviewers prioritize, not a guarantee of payment.
Writes payer-specific appeal letters using the original clinical note as evidence.
Pulls the assessment diagnosis, documented procedure, medical necessity language, and payer's adjudication patterns. Generates a letter ready for supervisor review in seconds, complete with clinical citations and regulatory references.
Verifies every drug billing unit against CMS HCPCS and FDA labeling.
A dictionary of more than 135 drugs covering oncology infusions, IVIG, biologics and biosimilars. Multi-drug reconciliation from MAR data, waste and multi-vial modifiers, practice-supplied (IOD) drug rules, and NDC crosswalk matching for charge posting. When a billing unit cannot be sourced from authoritative data, the agent does not guess. It flags the line for human review.
Logs every PHI access and every agent decision with cryptographic integrity.
SHA-256 integrity hash on every event, verified on every read, supporting HIPAA §164.312(b) audit controls. Tamper-evident by design. Every change to a claim, supervisor override, approval, export and posting request is recorded with actor, timestamp and outcome.
Secure connectors
Most billing time is not coding. It is logging in to portals, pulling charts and re-keying charges. ClaimVise connectors do that work in the practice's own EMR, billing system and eligibility portal, one session at a time, with the agency's own credentials held in an encrypted vault. A connector never retries a failed row on its own: a person decides.
Pulls the signed chart for every billed visit.
Upload the practice's daily signed-charges export. The connector finds each patient in OncoEMR, opens that visit's documents for that date only, fetches the billed categories (lab results, the medication administration record, the follow-up or new-patient note), merges them into one PDF and hands it to the Coding Agent. A failed patient never poisons the next one: the session recovers or restarts.
Posts reviewed charges into the practice's billing system.
After a reviewer clicks Post, the connector opens the right batch for the date of service, finds the patient, enters each charge line with provider, facility, authorization and diagnosis, and verifies the result. Drug lines are built from the practice's own dispense record and NDC crosswalk. Every attempt keeps screenshots, and a retry never re-posts a group that already went in.
Verifies eligibility straight from the practice's worklist.
Upload the eligibility worklist. The connector signs in to the eTactics portal (a person types the one-time code when the portal asks for it), verifies each patient one at a time, and writes status, effective date, co-pay, deductible, co-insurance, out-of-pocket maximum, plan type and remarks into a verified copy of the same workbook. Medicare and commercial payers follow different procedures, set per practice.
Connectors live today: OncoEMR, AdvancedMD and eTactics. Notes from any other EHR can be uploaded as PDF or image. Planned integrations: Availity, eClinicalWorks, OmniMD and Meditab (see the roadmap).
The problem
Medical billing agencies and in-house billing teams are asked to do more for each client at a lower price per claim, while payer rules, drug billing and prior-authorization requirements keep getting more detailed. Most of the labour is not clinical judgement. It is repetitive work that follows rules.
Eligibility look-ups, chart retrieval and charge entry mean logging in to three or four systems per patient and re-typing what is already on screen. It is slow, and a typo becomes a denial.
Infusion practices bill by the milligram, with waste, multi-vial and practice-supplied rules and a modifier for each. One wrong unit or code is a rejected line or an over-bill.
An agency running many practices needs to see, per practice and per person, what was retrieved, coded, reviewed, approved and posted, and prove it later.
Fixed headcount is expensive in a slow month and short in a busy one. Work that the software does should be priced and capped per practice, with overage only when volume really rises.
How it works
Six stages. Agents and connectors do the repetitive work. A person reviews every claim before it is exported or posted, and nothing is posted until someone clicks Post.
The eTactics connector works through the eligibility worklist and returns a verified copy of the workbook with benefits filled in.
The OncoEMR connector pulls each billed visit's signed documents, or the Scribe Agent reads an uploaded note, superbill or scanned chart.
The Coding Agent assigns ICD-10 and CPT with a confidence score. Below the threshold it escalates to a stronger model instead of guessing.
Scrubbing, drug reconciliation and denial prediction check units, modifiers, bundling and payer rules. Blocking findings hold the claim.
A supervisor reviews the claim, reorders or edits lines if needed and approves. The original AI output is always kept beside the human change.
The AdvancedMD connector posts the charges, or the claim is exported as an 837P file. If a claim is denied, the Appeal Agent drafts the letter.
Specialties
ClaimVise was not built for one specialty. The coding engine and the CMS reference data cover every specialty. We started where billing is hardest, infusion-heavy hematology and oncology, and we extend to each new specialty the careful way: validated on real claims before routine use.
Infusion and injectable drug billing is where most errors hide: units by the milligram, waste and multi-vial rules, practice-supplied drugs, biosimilars, chemotherapy administration codes and NDC matching. This is where ClaimVise is tested hardest and runs with a live customer.
E/M, procedures and preventive visits are coded by the same two-pass agent. NCCI and MUE edits, the physician fee schedule, ICD-10-CM and HCPCS are loaded for all specialties and refreshed each CMS quarter. Payer rules are layered per agency, practice and payer.
For a new specialty we run a supervised batch on your own claims, measure the result together, tune the rules and only then move the practice into routine use. Every claim is still reviewed by a person before it is exported or posted.
Platform depth
Under the agents and connectors sit the parts that make a billing agency able to run many practices on one system: true multi-tenancy, a configurable rules engine, current CMS reference data, and checks that refuse to invent a number.
Each agency sees only its own practices. Each practice has its own plan, prepaid wallet, module access, providers, locations and billing rules. Users are scoped by role (agency admin, supervisor, coder, AR caller) and a practice switcher keeps screens, dashboards and the claims queue on the practice you are working in.
A team report shows, per person, how many charts they retrieved, coded, reviewed, approved and posted.
System, Agency, Practice, then Payer. Different agencies bill differently, practices within an agency differ, and payers reject different things. ClaimVise resolves all four layers into one billing decision per claim.
Example: Anthem rejects KP and KQ modifiers, so the payer layer bills Anthem claims in combined-vial mode while the same practice's Medicare claims still use KP and KQ.
NCCI procedure pairs and MUE limits, the Medicare physician fee schedule RVUs, ASP drug payment limits, HCPCS Level II and ICD-10-CM, plus a dictionary of more than 135 drugs and biosimilars sourced from CMS and FDA labelling. Each quarterly refresh is loaded as a versioned, reversible run, and the platform reports how current each dataset is.
Where a unit or code cannot be verified, it is left empty and flagged, not estimated.
A charge comes only from the practice's contracted rate for that payer. With no authoritative rate, the line is marked unresolved and the export is blocked, never filled with a Medicare rate, zero or a default. The same rule covers place of service and date of service.
When a connector cannot continue, the screen says what went wrong and who should fix it, in plain language.
Engineering rigor
Healthcare billing AI is not the place for "ship fast, fix later." Every change to the coding pipeline runs against a full regression suite and real clinical notes before it ships. Every decision is logged. Every connector action leaves evidence.
Changes to the coding agent, validators or scrubbing engine must pass the full automated suite and a behavioral run against real oncology infusion notes with medication administration records before they merge. Releases that touch connectors are proven against the real portal pages the connector saw.
The function that applies the CMS modifiers (JZ, JW, KP, KQ, Q0, Q1, XU) is hash-anchored, so any change to it fails three independent tests. Every audit event carries a SHA-256 integrity hash that is re-verified whenever it is read.
AWS Business Associate Addendum executed May 22, 2026. All AI inference runs on AWS Bedrock under that BAA, and the platform refuses to start unless the AI provider is set explicitly. Connector credentials live in an encrypted vault that agency administrators manage. Logins are rate-limited, uploads are validated by file signature, and tenants are isolated by agency and practice.
When a billing unit cannot be verified, the drug line is flagged, not billed. When confidence drops below the threshold, the case escalates. When no contracted rate exists, the export is blocked. When a connector meets a screen it does not recognize, it stops and tells a person. Detectors help reviewers, and a human decision is always the last step.
How we compare
ClaimVise is not a faster coding floor and not a workflow tool with an AI assistant added. It is built for billing agencies: you keep the client relationship, the agents and connectors take the routine work, and your supervisors take the exceptions.
| Dimension | Traditional billing operation | Legacy RCM software | ClaimVise |
|---|---|---|---|
| Who does the routine work? | Coders and billers, by hand | The same people, with software organizing their queue | AI agents and connectors, with a supervisor reviewing every claim |
| Eligibility checks | Manual portal look-ups | Often a separate product or clearinghouse feature | Connector works the worklist and returns a verified workbook |
| Chart retrieval and charge entry | Manual, patient by patient | Re-keying into the practice system | Connectors retrieve from OncoEMR and post to AdvancedMD, after a human clicks Post |
| Drug billing (infusion) | Depends on the coder | Generic edit rules | Unit, waste, modifier and NDC checks from a sourced drug dictionary |
| Pricing model | Per-claim labour or headcount | Subscription plus a share of collections | Per practice per month, volume included, overage from a prepaid wallet |
| Multi-practice operation | Spreadsheets and shared inboxes | Varies by product | Multi-tenant: per-practice plans, wallets, modules, roles and team report |
| Audit trail | Manual logs | Often partial | SHA-256 integrity-checked log of every decision and action |
| Availability | Business hours | Software 24/7, support in business hours | Platform and connectors run around the clock |
Pricing
Choose the model that fits each practice. A unit is one claim (coding) or one verification (eligibility). A smaller practice with a few hundred claims a month usually does best paying per unit. A busier practice does best on a monthly plan with volume included. An agency can mix models across its practices. No per-seat fees.
Per practice, per month · best above about 1,000 claims a month
Per practice, per month · best above about 2,400 verifications a month
Per claim · best below about 1,000 claims a month
Per verification · best below about 2,400 verifications a month
Roadmap
ClaimVise today covers the front and middle of the revenue cycle: eligibility, chart retrieval, coding, validation, review and charge posting. The next stages add more integrations and extend toward claim submission and payment follow-up. Items marked planned are not yet live.
eTactics connector for Medicare and commercial payers, with a verified workbook returned per worklist.
OncoEMR connector retrieves the signed documents for every billed visit.
AdvancedMD connector posts reviewed charges after a person clicks Post.
837P file download, plus a remittance (835) parser built and tested ahead of the first live file.
Moving the full platform onto AWS. Target: 15 October 2026.
Planned: real-time eligibility and direct 837 claim submission with acknowledgment tracking through Availity.
Ingest real 835 remittance files, post payments and flag underpayments against contracted rates.
Planned: eClinicalWorks, OmniMD and Meditab, in the order customers need them.
Aging-bucket monitoring and payer-specific follow-up actions.
Detect requirements before scheduling, draft the necessity letter and track approval.
Verify and record secondary coverage on the same worklist.
Find underpaid claims and prepare the supporting data package.
Roadmap items are plans, not commitments, and are subject to change. Active customers receive target dates directly.
FAQ
There is a real difference between a product that adds an AI assistant and a product where AI agents prepare the routine work. In ClaimVise, seven AI agents read the note, propose the codes, check the claim, assess denial risk and draft appeals, and three secure connectors work inside the EMR, billing system and eligibility portal. The platform routes work between them. A person reviews every claim before it is exported or posted, and nothing is posted until someone clicks Post. The AI prepares the work, and your people make the decisions.
Medical billing agencies that run billing for several practices, whether they operate from India, the United States or elsewhere, and in-house billing teams at larger practices. ClaimVise is multi-tenant, so one agency account holds every practice it serves, each with its own plan, wallet, module access and users.
No. ClaimVise is a general-purpose platform. The coding engine handles E/M, procedures, preventive visits and infusion, and the CMS reference data (NCCI and MUE edits, fee schedule, ICD-10-CM, HCPCS) covers every specialty. We started with hematology and oncology because infusion billing is the hardest, and that is where we have the deepest testing and a live customer. For any other specialty we recommend a supervised pilot on your own claims, so we can measure the results together before the practice goes into routine use.
Every claim carries a confidence score. Below the threshold it escalates from a fast model to a stronger one, and deterministic checks for units, modifiers, bundling and payer rules run after the AI. Every claim is reviewed by a person before export or posting, and the original AI output is kept beside any change. We do not publish a single accuracy percentage, because accuracy depends on specialty and documentation quality. We prefer to measure it with you on your own claims during a supervised pilot.
ClaimVise signs a BAA with every customer that processes PHI. All AI inference runs on AWS Bedrock under our executed AWS Business Associate Addendum (May 22, 2026), and PHI is not sent to any provider outside that BAA. Every claim change, override, export and posting request is written to a SHA-256 integrity-checked audit log. Tenants are isolated by agency and practice, connector credentials are held in an encrypted vault, and uploads are validated by file signature. The HIPAA page lists the controls and what is still planned.
It replaces the repetitive work, not the people. You keep a supervisor seat: reviewing flagged claims, clearing holds, clicking Post, and managing configuration. Most of the time saved comes from not logging in to portals, pulling charts and re-keying charges. Your team spends more of its day on exceptions and client service.
Those products manage the workflow, and people still do the coding and the portal work. ClaimVise adds agents that do the coding and checking, and connectors that work inside the EMR, the practice-management system and the eligibility portal. It is also multi-tenant by design for billing agencies, with per-practice plans, wallets, module access and a per-person team report.
Live today: OncoEMR for chart retrieval, AdvancedMD for charge posting and eTactics for eligibility. Notes from any other EHR can be uploaded as PDF, image or file import. Planned integrations: Availity (eligibility and claim submission), eClinicalWorks, OmniMD and Meditab. Planned means not yet live, and the order follows what customers need. If you use another system, tell us during the demo.
Coding & Claim Readiness includes all seven agents, the OncoEMR retrieval and AdvancedMD posting connectors, claim review, 837P export, dashboards, the team report and the audit trail. Eligibility Verification includes the eTactics connector and the verified worklist. Each can be bought two ways: a monthly plan per practice with volume included (1,200 claims or 3,000 verifications), with overage drawn from the practice’s prepaid wallet, or pay as you go per claim or per verification, which usually suits smaller practices. See the pricing section for the figures. A monthly server hosting fee of ₹7,000 / up to $175 per practice also applies, in addition to the plan price.
Onboarding is configuration, not an implementation project: the practice profile and billing rules, the practice’s system logins in the encrypted vault, and the modules switched on for that practice. We will confirm a realistic timeline for your practices in the demo.
See it live
Book a 30-minute call. Bring a clinical note or an eligibility worklist, and watch the platform work through it in front of you.
Book a Demo →