CMS RAI Manual 2026: A Working Guide to MDS 3.0 v1.20.11 for SNF Teams
Last updated October 5, 2026 · By Hathr.AI
The RAI Manual is the CMS Long-Term Care Facility Resident Assessment Instrument 3.0 User's Manual, the rulebook for coding, scheduling, and correcting the MDS. Version 1.20.11 took effect October 1, 2026. Hathr.AI checks source records against RAI Manual look-back windows under a signed BAA, and its customers save 45 to 90 minutes per Medicare Part A admission on average.
Check one assessment's look-back windows in Hathr.AI, free for 7 days →
Key takeaways
- CMS posted the final RAI Manual v1.20.11 on September 17, 2026, effective October 1, 2026. Code each assessment from the manual version in effect on its assessment reference date.
- Chapter 2 sets the assessment schedule, Chapter 3 holds the item-by-item coding rules, Chapter 4 runs the CAA process, Chapter 5 governs corrections, and Chapter 6 covers Medicare SNF PPS.
- The assessment reference date (ARD) closes each look-back window on the assessment, and one MDS can carry 3-day, 7-day, 14-day, and 60-day windows at once.
- Hathr.AI reads hospital packets and nursing notes, scanned and handwritten pages included, and lists each documented event with its date and page for the MDS coordinator to test against the item's look-back window.
- Hathr.AI customers save 45 to 90 minutes per Medicare Part A admission on average when an MDS coordinator uses Hathr.AI for the review. At 20 admissions a month, that equals 15 to 30 hours per coordinator, with a planning estimate of about 22 hours.
- Hathr.AI runs Anthropic's Claude models on AWS GovCloud (US) inside a FedRAMP High boundary, with a signed BAA on every web app account, for $47 per user per month with no seat minimums and a 7-day free trial.
RAI Manual meaning: what the CMS RAI Manual governs
RAI stands for Resident Assessment Instrument. Federal rule 42 CFR 483.20 requires each nursing home to assess each resident with a comprehensive, accurate, standardized, reproducible assessment, and the CMS RAI Manual sets out how a facility meets that duty. CMS publishes the manual, the item sets, and the change tables on its MDS 3.0 RAI Manual page.
The RAI has three parts: the Minimum Data Set (MDS 3.0), the Care Area Assessment (CAA) process, and the RAI utilization guidelines in the manual. The MDS is the form. The manual is the rulebook for the form, and it decides what a coordinator may code, from which source, inside which dates.
The manual settles MDS coding disputes. Vendor help text, conference handouts, and the binder at the nurses' station age with each release, and coding habits passed from one coordinator to the next drift until an audit or a version change exposes them.
Readers training for an MDS role can start with our MDS coordinator guide, and readers after PDPM payment mechanics can go to What Is PDPM? To download the manual itself, use the CMS page above. This page serves the MDS coordinators, directors of nursing, and compliance leads who code from the RAI Manual each week.
RAI Manual 2026: what changed in version 1.20.11
The last two manuals took effect October 1, and CMS posts corrections between releases. The table lists the versions that matter for assessments coded in 2026 and 2027, as posted on the CMS manual page.
| Version | Posted | Effective | Status on October 5, 2026 |
|---|---|---|---|
| Manual v1.20.1 (October 2025) | August 29, 2025, updated September 24, 2025 for item J1900 | October 1, 2025 | Governs ARDs from October 1, 2025 to September 30, 2026 |
| Manual v1.20.11 (October 2026) | September 17, 2026 | October 1, 2026 | Current; governs ARDs from October 1, 2026 |
| Draft MDS 3.0 Item Sets v1.21.1 | October 2, 2026 | October 1, 2027 | Draft, for planning |
CMS lists these refinements in v1.20.11:
- Chapters 1, 2, and 3: state or payer requirements do not replace, modify, or add to CMS coding requirements for items outside Section S.
- Chapter 2: resident transfers during a public health emergency. Section A: ethnicity and race reassessment.
- Sections C and D: coding when staff conduct more than one BIMS or PHQ mood interview in the look-back period.
- Section M: pressure ulcers and injuries present on admission that heal and then reopen, plus advanced wound care dressings, skin substitutes, and adhesive bandages.
- Section O: refined isolation criteria and skilled respiratory therapy guidance.
- Chapter 6: revised terminology for depression signs and symptoms.
The Chapter 1 to 3 change reaches furthest: a state Medicaid rule or a payer form can ask for more documentation, and it cannot change how you code a CMS item. The change tables in the CMS download list each edit by chapter and section.
The version rule: code each assessment from the RAI Manual version in effect on its ARD. Archive each manual version instead of replacing it, since an audit two years out tests the assessment against the rules in force on its ARD, and 42 CFR 483.20(d) requires the facility to keep 15 months of assessments in the active record. After CMS posts a new manual, list the changed items your residents trigger and re-check each coding habit that lives as oral tradition.
RAI Manual chapter map: where to look
| Chapter | Contents | Go here when |
|---|---|---|
| 1 | The RAI, its purpose, and its three parts | Orienting new staff |
| 2 | Assessment types, schedules, ARD rules, completion and transmission timing | Deciding which assessment is due and when |
| 3 | Item-by-item coding instructions, section by section | Most coding questions |
| 4 | CAA process and care plan linkage | A care area triggers and needs documented analysis |
| 5 | Submission, correction, and inactivation | A transmitted assessment holds an error |
| 6 | Medicare SNF PPS rules | PPS scheduling and payment-related assessment rules |
| Appendices | Glossary, state RAI and automation coordinator contacts (Appendix B), CAA resources, interview guidance, item matrix, forms | Definitions, contacts, and item lookups |
Chapter 3 holds most of the working day. Each section gives the item's intent, definitions, steps, coding instructions, tips, and examples, and the examples settle the edge cases that start most arguments.
RAI Manual Chapter 2: the assessment schedule
Two schedules run side by side. OBRA assessments serve care planning for each resident. PPS assessments serve Medicare Part A payment. A facility may combine an OBRA and a PPS assessment where the manual permits, so one MDS can meet both duties.
| Assessment | Schedule rule | Source |
|---|---|---|
| OBRA admission (comprehensive) | Complete within 14 calendar days after admission | 42 CFR 483.20(b)(2)(i), Manual Chapter 2 |
| OBRA quarterly | At least once every 3 months; ARD within 92 days of the prior OBRA ARD | 42 CFR 483.20(c), Manual Chapter 2 |
| OBRA annual (comprehensive) | At least once every 12 months; ARD within 366 days of the prior comprehensive ARD | 42 CFR 483.20(b)(2)(iii), Manual Chapter 2 |
| Significant change in status | Complete within 14 calendar days after the facility determines, or should have determined, that the change occurred | 42 CFR 483.20(b)(2)(ii) |
| Significant correction of a prior assessment | Required when a prior comprehensive or quarterly assessment holds a significant error | Manual Chapters 2 and 5 |
| OBRA discharge | Return anticipated or return not anticipated; ARD on the discharge date | Manual Chapter 2 |
| 5-day PPS | ARD on days 1 to 8 of the Part A stay; sets the PDPM classification for the stay | Manual Chapters 2 and 6 |
| Interim Payment Assessment | Optional; pays from its ARD forward when classification-relevant characteristics change | Manual Chapters 2 and 6 |
| Part A PPS discharge | ARD on the last day of the Part A stay | Manual Chapter 2 |
After completion, the facility encodes the assessment within 7 days and transmits it to CMS within 14 days, under 42 CFR 483.20(f). Under PDPM, the 5-day assessment carries the payment for the whole stay unless an IPA follows. The PDPM guide explains the classification, and the SNF billing guide covers the claim that follows.
The assessment reference date and its look-back windows
The ARD, item A2300, marks the last day of the observation period for each item on the assessment. Look-back windows count backward from it, and the ARD day counts as day one of the window. A 7-day item covers the ARD and the six days before it.
Setting the ARD is a clinical and financial decision. It decides which documented events fall inside each window. Chapter 2 has the coordinator set the ARD in advance for each assessment except the discharge assessment, whose ARD equals the discharge date, so the coordinator plans the window before the days pass.
| Item or section | Look-back or observation window | What the window decides |
|---|---|---|
| Section GG, admission performance | First 3 days of the Part A stay | Admission function scores for PDPM and quality measures |
| Section I, active diagnoses | Physician-documented diagnosis in the last 60 days, active in the last 7 days | Comorbidities for NTA and nursing classification |
| Section D, PHQ mood interview | Last 14 days | Depression indicator for the nursing component |
| Section N, high-risk drug classes | Last 7 days, or since entry if shorter | Medication use reported on the assessment |
| Section O, special treatments | Last 14 days, split into while not a resident and while a resident | Extensive services for nursing and NTA classification |
| Section O0500, restorative nursing | Last 7 days, 15 minutes a day minimum | Restorative count for the nursing component |
| Section J1800, falls | Since admission, entry, reentry, or the prior assessment, whichever is most recent | Fall history for care planning and quality measures |
Two rules prevent most look-back errors: read each item's window in the manual's Chapter 3 before coding it, and leave out an event that sits outside the window, however relevant it feels. Section GG detail sits in our Section GG guide, and O0500 detail sits in the restorative nursing guide.
The CAA process under RAI Manual Chapter 4
MDS responses trigger 20 care areas, including cognition, mood, falls, nutrition, pressure ulcers, and psychotropic drug use. For each triggered area, the interdisciplinary team completes a Care Area Assessment, documents its analysis, and records whether the area moves to the care plan. Surveyors read that analysis to judge whether the assessment drove the care plan. A summary that says the team reviewed the area documents nothing. The analysis needs the cause, the contributing factors, the risks, and the reason for the decision.
Corrections under RAI Manual Chapter 5
Chapter 5 governs a transmitted assessment that holds an error:
- Modification corrects item-level errors on an accepted record.
- Inactivation removes a record that the facility should not have submitted: the wrong resident, the wrong assessment type, or an event that did not occur.
- Significant correction assessments are new comprehensive or quarterly assessments that replace a prior assessment with a significant error in the clinical picture.
Corrections carry a payment side. A modification that changes a PDPM item changes the HIPPS code, so the claim needs a matching adjustment, or the mismatch triggers a rejection.
What is Hathr.AI?
Hathr.AI is a HIPAA-compliant AI platform that runs Anthropic's Claude models on AWS GovCloud (US) inside a FedRAMP High authorization boundary. Hathr, LLC, based in Springfield, Virginia, sells it as a web app at $47 per user per month and as an API for developers. The U.S. Department of Health and Human Services, prominent universities, healthcare organizations, and RCM teams trust Hathr.AI. Our page on HIPAA-compliant AI for skilled nursing facilities shows the full facility offer.
MDS coordinators use Hathr.AI to match each documented event in an assessment's source records to an RAI Manual look-back window before coding. Directors of nursing use it to check CAA narratives against the record, and compliance leads use it to audit completed items before transmission.
Can SNF staff put MDS source records into an AI tool?
Yes, under a signed Business Associate Agreement with a vendor built to handle PHI, and Hathr.AI accepts that BAA online at signup on every web app account. Under 45 CFR 164.502(e) and 164.504(e), a covered entity needs a written BAA before it shares PHI with a business associate. A hospital packet pasted into a chat tool without one counts as a disclosure, however useful the output.
We sell the alternative, so weigh this on the merits: you can de-identify a record before pasting it anywhere. That takes time and breaks down on scanned packets, where identifiers sit in headers, fax stamps, and handwritten orders.
Hathr signs as the business associate, so these terms are our obligations:
- Hathr, LLC acts as the business associate, and your facility is the covered entity.
- You accept the BAA online at signup, and Hathr signs BAAs within 24 hours.
- The BAA covers the HIPAA Privacy and Security Rules and the HITECH Act.
- Hathr reports breaches and security incidents to you within 20 business days of discovery.
- On termination, Hathr returns or destroys your PHI within 30 business days.
- The BAA supports access, amendment, and accounting of disclosures under 45 CFR 164.528, and Hathr flows the same duties down to its subcontractors.
The MDS carries its own rules. Under 42 CFR 483.20(g), the assessment must reflect the resident's status. Under 483.20(h) and (i), a registered nurse conducts or coordinates each assessment and certifies its completion, and each person who completes a portion certifies the accuracy of that portion. Under 483.20(j), willful falsification of an assessment carries civil money penalties. Surveyors cite accuracy failures under F641, Accuracy of Assessments, in Appendix PP of the State Operations Manual. An AI tool can supply evidence. The RN keeps the signature. Our security and privacy page documents the boundary, and Why Hathr.ai compares it with general-purpose tools.
How do you check an MDS against RAI Manual look-back windows with AI?
You upload the assessment's source documents to Hathr.AI, give it the planned ARD, run one structured prompt, and have the MDS coordinator verify each cited page against the manual before coding. Hathr.AI customers save 45 to 90 minutes per Medicare Part A admission on average with this review. The steps:
- Set the planned ARD and note the assessment type, the admission date, and the RAI Manual version in effect on that ARD.
- Gather the source set: the hospital transfer packet, the H&P, the medication record, therapy evaluations, and nursing notes covering the longest window.
- Upload the files to Hathr.AI. Built-in OCR reads scanned pages, fax stamps, and handwritten orders, so nothing needs retyping.
- Run the prompt below. Hathr.AI lists each documented event with its date, its page, and whether the date falls inside the 3-day, 7-day, 14-day, or 60-day window you named.
- Open each cited page, apply the manual's Chapter 3 instructions for the item, and code what the record supports inside the window. Note any event that falls outside the window for the care plan instead.
The prompt:
The planned assessment reference date is [ARD] and the admission date is [admission date]. Read the attached hospital transfer packet, medication records, therapy evaluations, and nursing notes. List each diagnosis, treatment, medication class, fall, mood interview, and functional observation the record documents. For each item, give the date, quote the record's wording, and give the page number. Mark whether the date falls inside a 3-day window from admission and inside 7-day, 14-day, and 60-day windows ending on the ARD. Mark an item uncertain when the record gives no date or hedges. Do not assign MDS codes, and do not add any event the record does not state.
Your first session: pick one assessment you transmitted last month, run the prompt on its source set with the ARD you used, and compare the list with the coded items. More templates sit in our HIPAA-compliant prompt library, and How It Works shows the upload flow.
Run this prompt on one assessment, free for 7 days →
Where RAI Manual coding breaks
The costliest manual errors share a pattern. The facility codes from memory instead of the current manual, or the facts sit in the record outside the assessment:
- Coding from a cheat sheet or a prior version instead of the manual in effect on the ARD.
- An ARD set without checking which events each window will hold.
- Events coded from outside the item's look-back window.
- Comorbidities in the hospital packet that stay out of Section I.
- CAA summaries that name the care area and give no analysis.
- A modification that changes a PDPM item with no matching claim adjustment.
How does the ARD change what an assessment captures?
The ARD decides which documented events fall inside each look-back window, and Hathr.AI's review lists each event's date so the coordinator can see the effect before setting it. Hathr.AI wrote the example below for this page. It is illustrative, it is not a resident record, and it does not benchmark Hathr.AI output. We computed each window for a resident admitted October 1, 2026, counting the ARD as day one of each window, and compared a 5-day PPS ARD on day 5 with one on day 8.
| Window | ARD October 5 (day 5) | ARD October 8 (day 8) |
|---|---|---|
| Section GG admission window | October 1 to 3 | October 1 to 3 |
| 7-day look-back | September 29 to October 5 | October 2 to 8 |
| 14-day look-back | September 22 to October 5 | September 25 to October 8 |
| 60-day look-back | August 7 to October 5 | August 10 to October 8 |
Now place four documented events against the two choices. We picked the dates to show the edges.
| Documented event date | Inside the 7-day window? | Inside the 14-day window? | Inside the 60-day window? |
|---|---|---|---|
| August 8 (hospital record) | No / No | No / No | Yes / No |
| September 23 (hospital stay) | No / No | Yes / No | Yes / Yes |
| October 1 (admission day) | Yes / No | Yes / Yes | Yes / Yes |
| October 7 (day 7) | No / Yes | No / Yes | No / Yes |
Each cell reads ARD October 5 / ARD October 8. Moving the ARD three days later picks up the day 7 event and pushes each of the three earlier events out of one window. Both ARDs sit inside the day 1 to 8 range CMS allows. The manual's Chapter 3 instructions for each item decide whether a pre-admission date counts, since many items count days since entry when the stay is shorter than the window. The coordinator chooses the window, so the coordinator needs the dates in hand before choosing.
What should the MDS coordinator check before AI findings reach the MDS?
The coordinator checks six points before any Hathr.AI finding reaches the assessment:
- Confirm the RAI Manual version in effect on the ARD, and read that version's Chapter 3 instructions for the item.
- Open the cited page and confirm the wording and the date match the source.
- Confirm the date falls inside the item's look-back or observation window, counting the ARD as day one.
- Confirm the source meets the item's rule, such as a physician-documented diagnosis for Section I or a resident interview for the BIMS and PHQ.
- Score Section GG from the full 3-day admission window, with input from the staff who provided care.
- After any correction to a PDPM item, match the HIPPS code on the claim to the corrected assessment.
Hathr.AI surfaces evidence, and the registered nurse who signs the MDS makes each coding decision. We do not describe Hathr.AI output as clinical judgment.
What should an SNF require from an AI tool for RAI Manual work?
An SNF should require what Hathr.AI provides: a signed BAA before the first upload, a named hosting boundary, OCR for scanned packets, dated page citations, and output that leaves coding with the RN. The table lists each requirement, the question to put to a vendor, and the Hathr.AI answer.
| Requirement | Ask the vendor to | Hathr.AI answer |
|---|---|---|
| BAA | Sign before the first upload, and state the turnaround. | The web app accepts the BAA online at signup on every account. Hathr signs BAAs within 24 hours. Breach notice within 20 business days. |
| Hosting boundary | Name where PHI runs. | AWS GovCloud (US), inside a FedRAMP High authorization boundary, on government-approved models. |
| Security tier | Name the security framework and tier. | FedRAMP High boundary, a tier the US federal government verifies. Controls conform to NIST 800-53 and NIST 800-171. |
| Encryption | Name the encryption for data in storage and in transit. | FIPS 140-2 encryption and TLS 1.3. |
| Data use | Confirm whether the model retains or trains on resident records. | The models retain nothing at the model layer and never train on customer data. Documents stay in your account, segmented, until you delete them. |
| Scanned packets | Confirm support for scans, faxes, and handwriting. | Built-in OCR with handwriting recognition. PDF, Word, Excel, and plain text. |
| Dates and citations | Show the date and page behind each finding. | Each listed event carries its date, the record's wording, and a page number. |
| Capacity | State the document and page limits per account. | Up to 100 documents and 100,000 pages per account. Single documents of more than 500,000 words. |
| Coding accountability | Confirm the tool leaves MDS coding and sign-off with the RN. | Hathr.AI lists evidence with page citations. It does not code the MDS. |
| Price | State the seat price and any seat minimum. | $47 per user per month, no seat minimums, 7-day free trial. |
| EHR fit | Confirm whether setup needs an integration project. | The web app works alongside any EHR through upload and copy-paste. The API is REST. |
NIST 800-53 and NIST 800-171 are the baselines behind SOC 2 and HITRUST. Hathr.AI's controls conform to both, and its control set maps to the HITRUST CSF and SOC 2 criteria. Ask any vendor you evaluate to name its security tier and show the evidence.
Which SNF teams use Hathr.AI for RAI Manual work?
MDS coordinators, directors of nursing, therapy leads, business office staff, and compliance teams use Hathr.AI on the records each manual rule tests.
| Team | Starts from | Produces |
|---|---|---|
| MDS coordinators | Hospital transfer packets, H&P, medication records, nursing notes | Dated event lists with page citations, sorted by look-back window for the planned ARD |
| Directors of nursing | Triggered care areas, nursing notes, care plans | CAA analysis drafts grounded in the record for the team to edit |
| Therapy leads | PT, OT, and SLP evaluations from the first 3 days | Notes where documented function differs from the coded Section GG score |
| Business office and billing | Corrected assessments, HIPPS codes, claims | Checks that each modification has a matching claim adjustment |
| Compliance and QA | RAI Manual change tables and samples of completed assessments | Changed items your residents trigger, and audit lists of unsupported items |
For the full facility picture, start at our hub on AI in nursing homes. The guide to MDS coordinator duties and requirements covers the role and its staffing, the PDPM cheat sheet covers the payment model, and the survey readiness checklist covers what surveyors pull. Hathr.AI reviews records 10x faster in documentation and chart review.
What does Hathr.AI cost, and how does the API work?
The web app. Hathr.AI costs $47 per user per month with no seat minimums, unlimited queries, uploads, and downloads, and a 7-day free trial. Pricing is current as of August 2026. See pricing.
The API. The API has separate pricing. HIPAA-compliant API plans run $225, $700, or $1,200 per month by token volume, and each includes a signed BAA. The $45 Base plan is not HIPAA-compliant and serves non-PHI use. Software teams that build MDS or EHR tools on PHI need a HIPAA-compliant plan. Details sit on the API page.
Hathr builds enterprise automations for Medicare quality assurance, coding and billing, and documentation review, and hosts customer applications inside the same boundary. Hathr prices those engagements by quote.
The math on one $47 seat for MDS review
Hathr.AI customers save 45 to 90 minutes per Medicare Part A admission on average when an MDS coordinator uses Hathr.AI for the review. Put a nurse's wage on those minutes and compare the result with the seat price. We used the U.S. median wage for registered nurses in nursing and residential care facilities, $84,300 a year in May 2025 per the Bureau of Labor Statistics, which comes to $40.53 an hour over 2,080 hours.
| Part A admissions per month | Hours saved per month | Nurse time recovered per month | Return on one $47 seat |
|---|---|---|---|
| 10 | 7.5 to 15 (planning figure 11) | $304 to $608 | 6x to 13x |
| 20 | 15 to 30 (planning figure 22) | $608 to $1,216 | 13x to 26x |
| 40 | 30 to 60 (planning figure 45) | $1,216 to $2,432 | 26x to 52x |
At 20 admissions a month and the 22.5-hour planning figure, one coordinator gets back about $912 of nurse time each month for a $47 seat, about 19 times the price, and 270 hours a year. The math counts wages before benefits and leaves out the cost of a correction, a claim adjustment, or an F641 citation.
Each $47 seat for RAI Manual work includes:
- Source review that lists each documented event with its date and page number
- A window check against the 3-day, 7-day, 14-day, and 60-day look-backs for the ARD you name
- OCR for scanned, faxed, and handwritten pages
- Up to 100 documents and 100,000 pages stored per account, with unlimited queries, uploads, and downloads
- A signed BAA from the first login, on AWS GovCloud (US) inside a FedRAMP High boundary
You test the review on your own assessments during a 7-day free trial, with no seat minimums, so a single coordinator can prove the hours before the facility adds anyone.
Frequently asked questions
What is the RAI Manual?
The RAI Manual is the CMS Long-Term Care Facility Resident Assessment Instrument 3.0 User's Manual. It sets the rules for completing, coding, scheduling, transmitting, and correcting the MDS 3.0, and nursing homes code each assessment from it.
What is the current CMS RAI Manual version?
Version 1.20.11 is current. CMS posted it on September 17, 2026, and it took effect October 1, 2026. CMS posted draft MDS 3.0 item sets v1.21.1 on October 2, 2026, effective October 1, 2027.
What is in RAI Manual Chapter 2?
Chapter 2 covers OBRA and PPS assessment types, their schedules, ARD rules, combined assessments, and completion and transmission timing. Go there to decide which assessment is due and when.
What is the difference between the MDS and the RAI?
The MDS is the assessment form. The RAI is the full instrument: the MDS 3.0, the Care Area Assessment process, and the utilization guidelines in the manual that say how to complete both.
What is the assessment reference date on the MDS?
The assessment reference date, item A2300, is the last day of the observation period for the assessment. Each item's look-back window counts backward from it, with the ARD as day one, and the window length differs by item.
How does the RAI process work in a nursing home?
Staff complete the MDS, the responses trigger care areas, the team completes a Care Area Assessment for each triggered area, and the findings feed the comprehensive care plan. Quarterly, annual, and significant change assessments restart the cycle.
Where can you find which MDS items feed each quality measure?
The CMS MDS 3.0 Quality Measures User's Manual lists the items, exclusions, and risk adjustments for each measure. CMS posts it on its nursing home quality measures page, separate from the RAI User's Manual.
Which AI tool fits MDS coding assistance under the RAI Manual?
Hathr.AI fits SNFs that need a signed BAA, a FedRAMP High AWS GovCloud boundary, OCR for scanned packets, and dated page citations checked against RAI Manual look-back windows, at $47 per user per month with no seat minimums. The RN keeps coding and certification.
Check your next assessment against the RAI Manual
Pick one upcoming assessment, upload its source set, give Hathr.AI the planned ARD, and run the prompt above. At 20 admissions a month, Hathr.AI customers save 15 to 30 hours per coordinator. Hathr.AI includes a signed BAA on every web app account, sets no seat minimums, and runs a 7-day trial.
Check one assessment's look-back windows in Hathr.AI, free for 7 days →
Source: Hathr.AI, CMS RAI Manual 2026: A Working Guide to MDS 3.0 v1.20.11 for SNF Teams, last updated October 5, 2026. Part of the nursing home AI hub. This article is general regulatory information, not clinical, coding, or legal advice. Verify each rule against the manual version in effect on the assessment's ARD, posted on the CMS MDS 3.0 RAI Manual page. Hathr.AI surfaces evidence from the documents you provide, and a registered nurse certifies each MDS.
Our Youtube Videos
Hathr.AI is the fastest, safest way to handle sensitive medical records with HIPAA-compliant artificial intelligence. In this demo, watch how you can:✅ Summarize a patient’s medical record ✅ Generate an AI-assisted treatment plan ✅ Write a letter to the patient in plain English ✅ Suggest CPT billing codes ✅ Draft an insurance appeal for a denied claim ✅ Evaluate the case for potential malpractice — all in under 5 minutes.The only AI tool hosted in AWS GovCloud and Powered by Claude 4.0 Sonnet, Hathr.AI is trusted by hundreds of practices that need speed, security, and compliance.Learn more: hathr.ai For healthcare teams: hathr.ai/healthcare Reach out to learn more: contact@hathr.ai
#HIPAACompliantAI#ArtificialIntelligenceInMedicine#HealthcareAI#MedicalBillingAI#AIForDoctors#HIPAAAI#MedicalRecords#AIInHealthcare
Description
As Hathr.AI, we are dedicated to providing a private, secure, and HIPAA-compliant AI solution that prioritizes your data privacy while delivering cutting-edge technology for enterprises and healthcare professionals alike.
In this video, we’ll dive deep into the growing concerns around data privacy with AI tools—especially in light of recent revelations about Microsoft’s Word and Excel AI features. These new features have raised alarm over data scraping practices, where user data could be used without clear consent, leaving individuals and organizations exposed to potential privacy breaches. What makes this especially concerning is the "opt-in by default" design, which could lead to unintended data sharing.
In contrast, Hathr.AI ensures that your data stays yours. With a firm commitment to HIPAA compliance, we take the protection of sensitive healthcare data to the highest level. Our platform is built with the understanding that privacy is not an afterthought but a fundamental pillar of our design. We don’t collect, store, or sell user data, and we employ state-of-the-art encryption, secure access protocols, and clear user consent processes to keep you in full control.
We’ll also touch on why Hathr.AI, powered by advanced LLM (Large Language Models) like Claude AI, offers a secure and private alternative for businesses looking to leverage AI technology without compromising sensitive information. While some AI tools may collect or expose data through ambiguous or hard-to-find opt-out settings, Hathr.AI puts transparency and security at the forefront, offering peace of mind in an era of increasing digital vulnerability.
If you’re concerned about your privacy or looking for a HIPAA-compliant AI solution that respects your data, Hathr.AI provides the robust security, transparency, and ethical design that you need.
Key Points:
- HIPAA Compliant AI: Built for healthcare professionals, ensuring compliance with privacy regulations.
- Privacy-first: No data scraping, no data selling, full user control over information.
- Claude AI: Secure, powerful LLM tools for advanced capabilities without compromising security.
- Data Transparency: Say goodbye to hidden opt-in/opt-out toggles—Hathr.AI gives you clear, easy-to-understand privacy settings.
Tune in to learn how Hathr.AI ensures your AI tools remain private, secure, and trustworthy, while still delivering the performance and accuracy you need to thrive in a fast-evolving digital landscape.
Don't forget to like, comment, and subscribe for more insights on secure AI solutions and how to protect your organization from emerging privacy risks!
Description
Discover how Hathr AI's advanced AI tools transform federal acquisition processes with unparalleled security and efficiency. Designed for government professionals, this video showcases Hathr AI’s capabilities, including secure AI data analysis, HIPAA-compliant tools, and AWS GovCloud integration, to help streamline decision-making and document management. Perfect for agencies seeking private, compliant, and powerful AI solutions, Hathr.AI delivers tools tailored for healthcare and government needs.
Key Topics Covered:
AI-driven data analysis for governmentHIPAA-compliant, secure AI tools for federal agencies
Private deployment options with AWS GovCloud
Learn more about Hathr AI’s secure, high-performance solutions at hathr.ai and transform your agency’s acquisition process with cutting-edge AI.
Description
Discover how Hathr.AI simplifies NSF grant evaluations with advanced AI-driven compliance and proposal review tools. This video showcases Hathr.AI’s capability to streamline grant compliance checks, enhance accuracy, and save time for evaluators and applicants alike. Ideal for research institutions, government agencies, and proposal writers, Hathr.AI offers secure, HIPAA-compliant AI solutions tailored to meet the complex requirements of NSF and other grant processes.Highlights:AI-powered compliance checks for NSF grant proposalsFast, accurate, and secure evaluations with Hathr.AITailored solutions for research, government, and healthcareOptimize your grant proposal process with Hathr.AI's private, secure AI tools. Learn more at hathr.ai and transform how you handle grant evaluations and compliance.
Description
Join Hathr.AI at the Defense Information Systems Agency (DISA) Technical Exchange Meeting to explore innovative AI solutions tailored for federal and defense applications. In this session, we highlight Hathr.AI's secure, private AI tools designed for efficient data handling, HIPAA compliance, and seamless integration within government systems, including AWS GovCloud. Perfect for agencies seeking reliable AI for data analysis, document summarization, and secure decision-making, Hathr.AI provides cutting-edge technology for defense and healthcare needs.Highlights:AI tools for federal and defense data managementSecure, HIPAA-compliant AI solutions with AWS GovCloudEnhancing operational efficiency with private AI deploymentsDiscover how Hathr.AI's solutions empower government and defense agencies to stay at the forefront of innovation. Visit https://hathr.ai to learn more about our services.


.png)

