We are building reinforcement-learning agents to run US healthcare. They start in post-acute care, inside the buildings where the work actually happens.
01 / Intake
They start at the front door, watching every admission a facility makes: who was referred, what the packet said, who got a bed and who did not. Nobody hands them a policy manual. They learn this building's rules from this building's decisions.
~3 min
average referral review, down from about 40
They start at the front door, watching every admission a facility makes: who was referred, what the packet said, who got a bed and who did not. Nobody hands them a policy manual. They learn this building's rules from this building's decisions.
~3 min — average referral review, down from about 40
The moment a referral is accepted, Magicare assembles the clinical packet the payer is going to ask for, submits it, and tracks it. Your team watches a status, not a fax confirmation page.
Submitted at accept — packets assembled from the referral you already have
Continued-stay reviews arrive on the payer's schedule, not yours. Magicare watches every authorized through-date, pulls the current clinical picture, and puts the next review in front of the UR nurse before the days run out.
Every through-date — tracked across every payer, every resident
Orders, assessments, therapy minutes and progress notes live in one plan. When something changes on the floor, the plan, the payer story and the documentation change with it — in front of nursing, therapy and admissions at the same time.
One live plan — shared by every discipline in the building
Eligibility verified at intake. Authorization on file. PDPM coding supported by documentation that already exists. Denials get prevented upstream instead of appealed downstream.
+$525,000 — average additional annual revenue per facility
Every surface above is a reinforcement environment. Agents watch real decisions inside a real building, learn that building's policy, and then take the work over — with the people who taught them still in the room.
100+ facilities — running Magicare in production today
Why now
In 2022 there were fifteen working-age adults for every American over eighty. By 2045 there will be seven. The demand for post-acute care roughly doubles against the labour available to deliver it, and no amount of hiring closes that gap.
There is no version of the future where a forty-minute referral review scales to meet it. The work has to be done by something that learns the building and then does the job — which is why this is an agent problem and not a software problem.
Working-age adults per person aged 80+
~3 min
Average referral review, down from about 40
+$525,000
Average additional annual revenue per facility
100+
Post-acute facilities running Magicare today
“With Magicare, all our homes are now full.”
Mary Jean Cappabianca
Corporate Admissions & Social Services Director, Inspira Health Group
“Magicare increased my facility's revenue by $1M.”
Jonah Weiss
Owner, Tacoma Nursing and Rehab
“With Magicare we are never alone. They are true partners.”
Anaili Rendon
Chief Marketing Officer, Excelsior Care Group
The agents
Each agent is trained inside one facility’s real workflow, on that facility’s real decisions. They do not arrive knowing your building. They learn it, and the people who taught them stay in the loop.
INTAKE
Reads every inbound packet, verifies eligibility and ranks fit against the criteria that building actually admits on.
AUTHORIZATION
Assembles and submits prior auth from the referral you already have, then tracks every through-date for continued stay.
PLAN OF CARE
Keeps orders, assessments, therapy and progress notes in one plan that nursing, therapy and admissions all see.
REVENUE
Carries eligibility, authorization and PDPM support into the claim so denials get prevented instead of appealed.
The environment
Post-acute administration is unusually well suited to reinforcement learning: the decisions are frequent, the outcomes are measurable, and the reward is unambiguous. A bed filled or empty. An authorization approved or lapsed. A claim paid or denied.
Magicare runs that loop inside 100+ live buildings, which is why the agents behave like staff who have worked there for years rather than a model that read a manual.
And it compounds. What one agent learns, all of them know. Every building that comes online makes the next one cheaper to win and faster to run — no manual retraining, no starting over. The environment is the asset, and it is not something a competitor can buy.
The agent sits inside the real workflow — the same queue, packets, payer rules and through-dates your team works from.
It proposes the decision it would make and shows the reasoning, next to the human who is about to make it.
Accepted, corrected or overruled: every outcome is signal about how this building actually operates.
Once it matches your team on a task, it takes that task over — and the team supervises instead of typing.
Fifteen minutes, no slides. We will connect your referral sources live and walk one real admission from packet to authorization to claim.
HIPAA · SOC 2 · BAA available