For critical access hospitals · Free and open
AI resources built for 25 beds, not 500.
Most AI guidance assumes a data team, a legal department, and a budget to match. Critical access hospitals have none of those to spare. This site collects open tools that run on public data, a plain-language map of the rules, and playbooks a small team can follow.
01 · Projects
Open tools, built on public data.
Each project starts from a question a rural hospital leader asked. The code is on GitHub. Each page here says what the project does, what data it needs, and where it stops.
-
Analysis · public data only
Where patients go, and what keeping them is worth
Starts from where a county’s Medicare patients are admitted, then prices each way to keep care local under critical access payment rules. Produces a one-page briefing and a workbook that sources every figure.
PythonNodeClaude CodeCMS public filesRead about the project → -
Security and compliance audit
Scanning hospital websites for hidden hacks
A passive scanner that reads hospital websites the way a visitor does, looking for injected gambling and spam links and for hijacked former domains. Run across all 1,382 critical access hospitals on the roster.
PythonInternet ArchiveDNS recordsMIT licenseRead about the project → -
Teaching tool · live demo
Watch an emergency department bottleneck form
An interactive 3D model of a 15-bed ED. Change arrivals, staffing, and inpatient bed waits, and see what happens to wait times and boarding.
three.jsOne HTML fileRead about the project → -
AI agent with an eval set
An AI agent that drafts weekly measles reports
Turns CDC’s weekly tables into a situation report for an epidemiologist to review. The arithmetic runs in code, not in the model, and an eval set checks the drafts.
PythonClaudepytestRead about the project → -
Research · not yet peer reviewed
When sheltering in place fails
A national study of hospitals in Atlantic and Gulf hurricanes since 1990, and of what happens when a hospital that stayed has to evacuate anyway.
PythonpandasNOAA and CMS dataRead about the project →
From the hospital website audits
What the open projects have found so far.
02 · Regulatory map
The rules on AI in health care, in plain language.
Federal agencies and a growing list of states now have rules that touch AI in care, billing, and patient communication. Few were written with a 25-bed hospital in mind, and several changed in the past year.
The map sorts them by who they bind: the hospital, the health plan, or the vendor. It is reviewed on a schedule, and every entry carries the date it was last checked.
Open the regulatory mapEvery entry tells youFour things, in this order
- Where it stands. In force, delayed, proposed, or withdrawn, with the dates.
- What it requires. Two or three sentences, without the legalese.
- What a small hospital should do. Often the answer is one question for a vendor.
- Where to read it. A link to the rule, the statute, or the agency’s own page.
03 · Data readiness
You have more data than you think.
An AI project fails on data long before it fails on the model. The guide is written for a hospital with one analyst, or none.
- A
What you already have
Your EHR, your billing system, your cost report, and your phone system already hold most of what a first project needs. The guide shows how to find out what you can get out of each.
- B
What’s free
A catalog of public datasets, each checked against its official page: what it contains, how often it updates, what it costs, and where small rural counts get suppressed.
- C
What to fix first
A short self-check on ownership, access, and quality. It separates the gaps that will stop a project from the ones that can wait.
04 · Playbooks
Plans a small team can follow.
Each playbook is a short route with numbered steps, a checklist for each one, and a note on where small hospitals usually get stuck.
Your first 90 days
Set up governance light enough to keep, pick one use case, and decide how you’ll know it worked.
ForThe CEO and leadership team Playbook 02A six-week pilot
Run a small, honest test of one AI tool with the staff you have. No data scientist needed.
ForA project lead and one department Playbook 03Ambient documentation
From vendor questions to go-live to finding out whether clinicians keep using it.
ForThe CMO, a clinic manager, and IT Playbook 04The board briefing
A twenty-minute session that gives trustees enough to ask good questions.
ForThe CEO and board chair05 · Training
A video series on AI, made for rural health.
If your team needs a shared starting point before a playbook, start here. The episodes run from an overview of AI and responsible use through change leadership, prompting, and AI agents.
-
Microsoft Elevate · January 2026
Microsoft’s AI Learning Path for Rural and Community Healthcare
10 self-paced episodes, about 25 minutes each. Written, produced, and presented by Tyler Wallace, who built this site.
Watch the series
Ep 01 AI Learning Path
Ep 02 AI Overview
Ep 03 Responsible AI
Ep 04 AI Change Leadership
Ep 05 AI for Tech Leaders
Ep 06 Generative AI and LLMs
Ep 07 Prompting
Ep 08 Gen AI in Operations
Ep 09 Gen AI for Projects
Ep 10 AI Agents
Have a question this site doesn’t answer?
Tell us what your hospital is trying to decide. If other hospitals are asking the same thing, the answer becomes a page here.