One patient record across every line your practice runs
MedOp is the AI-native system of record for five lines of care — behavioral health, rehab therapy (PT/OT/SLP), medical aesthetics, functional medicine, and primary care including direct primary care and concierge memberships — all on one patient record. It is built line-deep, priced per provider with everything included, and run by a governed workforce of 43 AI agents that draft and propose while a person approves. This paper sets out the platform, the market, the economics and the evidence, and says plainly where a capability is planned rather than shipped.
Version 2.9 · prepared by Rachael Pereira, Paul Pereira and Dr Paul Alexander · every platform figure anchored to a tagged production build · every market figure cited · no form to fill in.
The paper makes six claims
The problem is labour, not software features.
The lines of care are large, growing and structurally under-served — and in MedOp’s October 2026 review of about 30 vendors’ public documentation, none documented the five-line combination MedOp is built for. Not documented is not proof of absence.
One patient record across every line is the wedge: each line stays visibly distinct, the AI sees only the line of the visit it serves, and 42 CFR Part 2 records never reach an AI agent.
MedOp is a system of record, not an AI overlay. The overlay is a commodity now, and it is terminable by the EHR it sits on.
The differentiator is the machinery, not the agent count: minute bands from the session clock, the 8-minute rule as a tested function, an enforced Good Faith Exam, Part 2 accounting, a CoCM registry — on a governed agent substrate.
The commercial model restores expansion revenue and removes the reasons practices distrust their vendor: a published $169 per provider list ($149 for a practice’s first 12 months) with the AI receptionist included, an AI line of vendor usage at exact cost plus a fee per completed task under a monthly cap the practice sets, a 0% platform fee on payments, and a Fair Terms Charter in the contract.
Twelve sections, two appendices, every figure sourced
Section 01
Executive summary
Six claims, each with evidence: the problem is labour; the lines of care are large and under-served; one record across every line is the wedge; system of record, not overlay; mechanics over agent count; a commercial model built on expansion and fair terms.
Section 02
The problem
13 hours a week on prior authorization (AMA, 2026). 11.8% of claims denied on first submission (Kodiak, 2025). 86% of rehab therapists burned out, 59% naming documentation (Ensora, 2026). Software that meters every add-on and charges to export your data.
Section 03
The market
61.5M US adults with a mental illness and half untreated (SAMHSA). 457,000 people employed in PT/OT/SLP offices (BLS). 10,488 med spas averaging $1.40M (AmSpa). Behavioral health, therapy and aesthetics alone are roughly 110,000 US establishments (Census County Business Patterns 2023 and AmSpa) — establishments, not practices. Functional medicine and primary care, including direct primary care and concierge memberships, both launched 16 October 2026. And the under-served segment: integrated practices.
Section 04
The platform
Scheduling, intake, ambient documentation, grounded coding, claims and RCM, e-prescribing with EPCS, portal, payments, engagement, telehealth, reporting and a public API — one system, one record. Lines of care visibly distinct on every visit, note and calendar; line-aware AI; provider performance; every staff screen on a phone.
Section 05
The AI workforce
4 pods, 43 agents (19 conversational), and the substrate underneath: memory and retrieval, reflection, calibrated confidence, one approval inbox, kill switches, cost attribution in CI, closed-loop improvement. Every agent drafts or proposes; a person approves. A denied claim, step by step.
Section 06
What sets MedOp apart
Seven checkable differentiators — from one record across every line and line-aware AI that never sees 42 CFR Part 2 records to database-enforced tenancy and fair terms as contract language — and the competitive landscape in one paragraph.
Section 07
Benefits
For clinicians, the front office and the owner, and how the value is measured: on the practice’s own work, task by task, against the staff time each task replaced — not on a modelled hours-saved figure.
Section 08
Revenue model and economics
A flat $169 per provider per month list with the AI receptionist included and no per-call fee, the only platform price, and a dated launch offer of $149 for a practice’s first 12 months; the AI line — AI vendor usage at exact cost plus a fee per completed task, under a monthly cap at which paid agents pause; worked examples, why per-provider matters, unit economics, and the seven-clause Fair Terms Charter.
Section 09
Security, compliance and trust
Engineered controls — Postgres row-level security with 290+ policies, verified on production; a tamper-evident PHI audit chain; MFA; Part 2 gating; AI governance — and an honest statement of attestation status.
Section 10
Engineering
The engineering record behind platform build v7.446.0, measured 19 October 2026: 21,600+ automated tests, more than 900 tagged releases, 57 architecture decision records and the CI gate suite.
Section 11
Roadmap
With all five lines available: member billing for primary care, the AI line on the invoice, first records imports, then deeper behavioral health, aesthetics, therapy and functional medicine, and the trust surface through Q2 2027.
Section 12
The company
Who builds MedOp, who is responsible for security, and the operating principle behind the paper: state what is true, cite it, and say “not yet” where that is the answer.
Appendix A lists the 42 agents available to every practice at build v7.446.0 (the registry holds 49; the rest are built and off by default) — 19 conversational — with pod and job. The live list, now 43 agents, is on the AI agents page. Appendix B lists every third-party source. Capabilities described as planned, scheduled, or built and switched off are not yet generally available.
The market and the rules behind the record
Two companion papers: one on how fast the five lines are growing and merging, one on the rules each line must follow. Free PDFs, no form to fill in.
White paper
The Converging Practice
Paul Pereira · 24 October 2026 · 24 pages
Why outpatient care is merging across behavioral health, therapy, aesthetics, functional medicine and primary care; how fast each line grows in the United States (about 6.4% a year combined, against 5.4% for all health spending) and worldwide; the criteria a line of care must meet to share one record; the rising regulatory load; and the clinical evidence that integrated care improves outcomes, with its limits stated.
Regulatory analysis
Five Lines, Five Rulebooks
Rachael Pereira, Paul Pereira and Dr Paul Alexander · 19 October 2026 · 17 pages
More than 65 federal and state rules across the five lines, each regulated at a different object on a different clock; six places where those rules collide in a practice that runs more than one line; and a test of four software set-ups against the six requirements of a multi-line practice. Analysis, not legal advice.
Read it, then check it
Every platform claim in the paper can be verified in a demo or a sandbox. Every market claim can be verified at its source.