AI pre-auth packets for ABA clinics
Pre-auth packets payers actually approve.
Drafted in 3 minutes, not 90, to each payer's medical-necessity criteria, citing only your real assessment scores and goals. Your BCBAs review and submit; compliance is enforced server-side.
Sample client + draft packet seeded on signup. No card charged for 30 days.
Real output, not a mockup
What your BCBAs review before they submit.
Mand cites only facts from your treatment plan and assessment. No invented goals. No fabricated scores. No history that wasn't already in your records.
The client, a 6-year-old individual with a primary diagnosis of Autism Spectrum Disorder (F84.0), requires Applied Behavior Analysis services in a home-based setting to address significant behavioral and skill deficits across multiple developmental domains. The most recent VB-MAPP, administered on April 1, indicates substantial gaps in mand frequency, tact repertoire, and listener responding consistent with the client's current level of functioning. Treatment goals target measurable behaviors drawn directly from the authorizing assessment: vocal manding for preferred items (baseline 20% across 5 sessions, mastery criterion 80% across 3 consecutive sessions), labeling common household objects (5/20 items at baseline), and intraverbal exchanges. Discharge criteria are tied to demonstrated generalization across settings and consistent independent performance over the defined criterion period.
Real output from Mand's Magellan template. 1,247 chars total (card truncates ~600).
What clinics are saying
BCBAs who put Mand to work in their practice.
“We’ve reclaimed our time and slashed our denial rates.”
Navigating prior authorizations used to be the most draining part of our week at Lifespan Behavior Services. usemand.com has completely transformed that burden. The platform generates comprehensive, high-quality draft narratives in a fraction of the time it used to take us manually. Since putting it to work, we’ve seen a massive reduction in prior auth denials. If you want to save time and ensure your patients get the care they need without the bureaucratic headache, you need Mand.
“A game-changer for our administrative workflow.”
Before implementing Mand, our clinical team spent hours drafting narratives and battling insurance companies over prior authorizations. usemand.com changed everything. It has dramatically reduced our drafting time, allowing our clinicians to focus on patient care rather than paperwork. More importantly, the AI-generated narratives are so precise and robust that our prior authorization denials have plummeted. It’s an indispensable tool for Step Forward.
“Airtight cases insurance companies can’t argue with.”
Thanks to Mand, TheraKids has cut prior auth narrative drafting time to minutes while significantly dropping our denial rates. The AI builds airtight cases that insurance companies simply can’t argue with. It’s a must-have platform!
Why packets get approved
Speed gets the packet out the door. What's underneath gets it approved.
Payer-specific medical-necessity criteria, built in.
Mand doesn't just “write a narrative.” It knows what each reviewer demands and drafts to it, then fills the payer's own official form, field by field. Generic AI gets denials; payer-aware AI gets approvals.
Magellan, BCBS / Anthem, Cigna, Aetna, and Medicaid-MCO templates ship out of the box, and 22 payers' official forms are mapped field-by-field from their real PDFs. A generic PDF filler has to rebuild all of that, payer by payer.
What each reviewer wants
- Magellan
- explicit discharge criteria
- BCBS / Anthem
- evidence-based protocols (DTT, NET, PRT)
- Cigna
- ADL & communication outcomes
- Medicaid MCOs
- less-restrictive-alternatives analysis
Trust is enforced server-side, not promised.
Two guards a chatbot can't offer. The draft cites only facts from your plan and assessment. No invented goals, scores, or history. And every consequential action lands in a tamper-evident audit trail the app itself can't edit or delete.
Drafts with refusal tokens or unfilled placeholders are rejected before they're saved; audit events are append-only at the database layer. Your auditor gets a clean CSV.
Owns the whole renewal lifecycle, not just the first draft.
Mand tracks every authorization to expiry and re-arms it: reminders before it lapses, one-click renewals pre-filled from the approved packet, and a denial 'Amend' that re-drafts around the payer's exact reason.
Emails at 60, 30, and 7 days before expiry; renewal pre-fills client, payer, codes, and the next period; an amendment leads with whatever the denial cited.
Wedge alongside what you have. No migration.
Keep CentralReach, Rethink, your spreadsheets. Mand does one workflow well: packets in, service authorizations out, which your RBTs then clock in against. Upload treatment-plan PDFs and Mand extracts goals and scores directly.
No import wizard, no migration call. Draft a packet in five minutes; PDFs work on day one.
How it works
From the BCBA's seat. Total time per packet: 5–10 minutes (vs. 60–90 by hand).
Set up your org
Sign up with email + password. Mand enables the three ABA CPT codes by default (97153 / 97155 / 97156). Add clients as you need them. No upfront import required.
Compose a packet
Pick the client → treatment plan → payer → service codes → period → hours/wk. The AI drafts the narrative in 2-3 seconds against the payer-specific template. Already have the treatment plan as a PDF? Upload it and Mand creates a draft plan from it directly. No re-keying.
Review, submit, and track
Edit the draft if it needs it. Submit creates pending service_authorizations. When the payer responds, mark approved. Auths flip active and your RBTs can clock in against them. Mand emails you at 60, 30, and 7 days before each auth expires. When you're ready to re-authorize, open the approved packet and click 'Start renewal.' Same client, same payer, period shifted forward, all fields pre-filled.
What happens if the AI fails on a packet you need today? Mand shows the failure (rate-limited / model down / prompt unsafe) and you write the narrative manually, same as today. The PWA never blocks submission on AI availability.
Start 30-day free trial →Coverage
252 jurisdiction-specific rules. All 50 states + DC.
Every rule cites a primary source — state Medicaid manual, provider bulletin, licensing board rule, or statute. Paralegal-verified. Click any state to read the citations.
Total rules
252
Jurisdictions
50 states + DC + federal
Federal / BACB rules
6
Updated
2026-05-11
Hover to preview. Click to read citations.
Why speed matters
Every day in the approval queue is a day a child waits for care.
The new federal rule gives payers 7 days to respond. Clean, criteria-matched packets get answered faster, so authorizations turn into sessions, not backlog.
Built for what's coming
When payers open the electronic door, Mand's already through it.
The same federal rule behind the 7-day banner (CMS-0057-F) also requires Medicare Advantage, Medicaid, and marketplace plans to expose a free, standardized electronic prior-authorization API (HL7 Da Vinci PAS, built on FHIR) by January 1, 2027. The packet you draft in Mand today is already built to ride that rail: no portal logins, no fax, no re-keying.
We're not waiting for the deadline. Mand's FHIR submission is built and tested now; it switches on for each of your payers as they turn their mandated API on.
Where it stands
- ✓
Da Vinci PAS bundle
Validated against the official FHIR spec (PAS IG v2.2.1).
- ✓
End-to-end electronic submit
Round-tripped against the Da Vinci reference server with SMART Backend Services auth.
Live payer endpoints
Roll out per payer through the Jan 2027 federal deadline.
Questions BCBAs ask first
How is this different from telling ChatGPT to draft a pre-auth packet?
ChatGPT doesn't know your client's VB-MAPP scores, your treatment plan goals, or the payer's medical-necessity criteria. Mand does. It pulls from your records and the payer template before drafting. Generic AI gets denials; payer-aware AI gets approvals.
Do we have to integrate with CentralReach (or Rethink, etc.)?
No. Mand doesn't touch your existing platform. You enter the assessment and treatment plan in Mand (or copy-paste from CentralReach), draft the packet, submit it. CentralReach and Rethink are strong at session data, scheduling, and billing. They don't draft pre-auth narratives against payer-specific criteria. That's the gap Mand fills.
What happens to our data? HIPAA?
We sign BAAs before any real PHI enters Mand. Demo-mode signups are available without a BAA (synthetic data only, enforced at the database layer so a fat-fingered real client name can't slip in). We don't train AI models on your data. The AI calls are stateless; Groq and Anthropic don't retain prompts or responses past the request. Hosted on a single-tenant Postgres in US-East with daily encrypted backups.
What if the AI hallucinates a goal we didn't have?
Two guards. (1) The prompt explicitly forbids fabrication: "cite only facts in the input." (2) The BCBA reviews and edits before submit. The AI's draft is never the final document. We track edit-distance metrics so we can see when the AI drifts off.
How does re-authorization work when an auth is about to expire?
Mand emails the BCBA at 60, 30, and 7 days before each authorization expires. No spreadsheet to maintain. When you're ready, open the approved packet and click 'Start renewal.' Mand pre-fills a new packet with the same client, payer, service codes, treatment plan, and a suggested period that picks up exactly where the prior auth ends. You review and submit; nothing gets re-keyed from scratch.
What happens if a packet gets denied?
Open the denied packet, read the denial reason, and click 'Amend.' Mand re-drafts the narrative with the denial reason in context. If Cigna says 'insufficient baseline data,' the new draft leads with baseline scores and tightens the medical-necessity argument around them. The amendment is a new version of the same packet; the original is kept for the audit trail. Most denials are re-submitted the same day.
Pricing
Simple, transparent pricing.
Start with a free 30-day trial. The rules engine and all payer templates are included at every tier.
Founding Clinic pricing. Start before October 2026 (when the CPT 2027 codes publish) and your rate locks for life. List prices rise after.
No demo gate. The price on this page is what you actually pay. Every other ABA platform requires a sales call to find out.
Solo
Unlimited packets, 1 BCBA
Founding rate · rises to $299/mo October 2026
Everything you need to evaluate Mand on real work.
- 1 BCBA seat
- Unlimited RBT logins
- 1 location
- All 50 states + DC + federal rules
- All payer templates (Aetna, Magellan, BCBS, Cigna, Optum, …)
- Auth expiration alerts at 60 / 30 / 7 days
- One-click renewal pre-fill from approved packets
- Treatment plan PDF import
- Real PHI after click-through BAA
- Email support
Pilot
Unlimited packets, 2 BCBAs
Founding rate · rises to $599/mo October 2026
For small practices adding a second BCBA.
- 2 BCBA seats
- Unlimited RBT logins
- 2 locations
- Everything in Solo
- Unlimited packet drafts
- Priority AI extractor queue
Practice
Unlimited packets
Founding rate · rises to $1199/mo October 2026
For 1–5 BCBA practices growing past the solo case.
- Up to 5 BCBA seats
- Unlimited RBT logins
- 3 locations
- Everything in Pilot
- Slack support channel
- Pays for itself at >2 net packets / month
Group
Multi-site practice
Founding rate · rises to $2999/mo October 2026
For 6–20 BCBA group practices and small multi-state networks.
- Up to 20 BCBA seats
- Unlimited RBT logins
- Up to 5 locations
- Everything in Practice
- On-prem option available
- SSO (when shipped, no upcharge)
- Audit log exports
- Dedicated Slack channel
- Quarterly business review
Enterprise
Need something bigger?
Multi-state networks, white-label, custom payer integrations, and volume pricing for 20+ BCBAs.
- Unlimited BCBA seats
- Unlimited RBT logins
- Unlimited locations
- Volume pricing
- Custom payer template development
- White-label option
- On-prem deployment
- SOC2 (when earned)
- Custom SLA + dedicated CSM
All tiers include the rules engine, all 11 payer templates, auth expiration alerts, renewal pre-fill, and treatment plan PDF import. Every tier includes unlimited packets. If you find a cap, file a bug. Prices shown are Founding Clinic rates, locked for life if you start before October 2026; list prices rise when the CPT 2027 codes publish.
Draft your first packet in 3 minutes.
30-day free trial, no card required. Full access from day one: all payer templates, AI extraction, and RBT billing included. $149/month after the trial, or $124/month billed annually. Cancel any time.
We sign BAAs before any real PHI enters Mand. Demo signups available without a BAA (synthetic data only). We don't train AI models on your data. Hosted on a single-tenant Postgres in US-East with daily encrypted backups in Cloudflare R2.