P PraxisNotes
02 · After · a Tuesday in the new PraxisNotes

The day the paperwork disappeared into the work.

No screen to hunt, no 9pm form, no note stuck in a queue for days. Follow one Tuesday through five people's eyes — a bilingual RBT, her BCBA, the QA lead, the biller, and the AI team working underneath them. The RBT talks between trials; an agent writes; specialist agents check every note; a ready-to-bill packet lands the same evening. Humans commit; agents draft and check.

MR Maria · RBT, 6 sessions today DC Dr. Chen · BCBA, supervises 12 DA Dana · QA lead RO Robert · the biller The AI team →
4:00 PM
Session starts
check-in captures time, place, people
5:47 PM
Note signed
Maria reviews the draft, signs in the car
5:58 PM
Agents reviewed
BCBA-lens + QA-lens pass, minutes later
6:10 PM
Ready to bill
clean packet in Robert's queue

Two hours, ten minutes — from the first trial to a claim that can go out. Compare that to the days of latency a note carries today.

4:02 PM · Maria arrives

The session starts before the notes do

Maria opens the client's card in the car. One authorization badge tells her everything that matters: the payer, the code she's billing, and how many units are left on this authorization. She taps Start session — and the three facts every payer audits are captured right then, at the door.

Time, at check-in — not recalled at 9pm

A server-side clock stamps the real start. Duration and units are computed, never remembered.

Place of service — Home (POS 12)

Florida Medicaid §6.2.4 requires location on every note. It's a tap, not a typed field.

Participants — captured, not reconstructed

Who was present, including whether a caregiver was there — the exact field auditors flag as missing.

EVV-ready by design. Time, location, and participants at check-in are five of the six data elements EVV requires — so if Florida re-expands its EVV mandate, the visit is already verified.

4:02
New session
D.M.
Client · D.M.
Tues 4:00–5:30 PM · in-home
Sunshine Health 97153
Units remaining 12 of 24
Captured on tap
Start 4:02 PM
Place Home · POS 12
Present Maria R. · parent
4:47
recording notes 00:45:12
Español · auto-detected

Mordió dos veces durante la transición al área de mesa. Redirigí con apoyo gestual y ofreció el token

listening · processing · done
This session · 4 voice notes
Mand training · tokens 4:31
Transition · biting 4:47
Or type a quick note…
During · between trials

She talks. In Spanish. In the moment.

Maria holds the mic for a few seconds between trials and describes what just happened — in the language she thinks in. The transcript streams live so she can see it caught the moment. Language is auto-detected across 90+ languages; the note that comes out later is compliant clinical English, with the original kept as evidence.

Push-to-talk

Every voice note is timestamped and attached to the session. Clear states — listening, processing, done — so she's never guessing whether it heard her.

Typing stays first-class

Voice is an accelerant, never the only path. A quick typed note is always right there — noisy room, private detail, or just preference.

Dead-zone homes are handled. Many in-home sessions run where there's no signal. Capture is recorded locally on the device and uploads the moment signal returns — no lost notes, no re-recording from memory.

One data model, four ways in

Voice doesn't replace the session data — it fills it. Every path below lands in the same structured fields, in the database, validated against the client's treatment plan. The note is a rendering of that data — never the other way around.

Captured for her

Date, start/stop, place of service, participants, credentials, authorization — the device, the calendar, and the client record already know. The best capture is no capture.

One tap, mid-session

Behavior counters, duration timers, prompt-level chips, Fair / Good / Poor — big one-hand buttons between trials. Numbers by tapping, not talking — a count beats a sentence.

Spoken between trials

ABC events, client response, environmental changes, observations — any language. The narrative-shaped facts that used to cost the 9pm hour, extracted into fields, not prose.

Asked only if missing

Whatever's still empty against the payer's required elements arrives as one-tap questions. A form that shrinks to just its gaps — and disappears when there are none.

And the form stays — always

The pre-filled form is the fifth path and the editing surface: everything the other four paths captured lands there, reviewable and editable until Maria signs. Professionals who prefer typing use it as capture, first-class, forever — voice is an accelerant, never the only way in.

Validated against the plan

Every behavior recorded must map to a target in the client's assessment and treatment plan; every replacement program must be a plan program. A behavior that isn't in the plan doesn't fail silently — it flags Dr. Chen that the plan may need updating. And every data row remembers its source: tap · voice 4:47pm · answered 5:33pm · edited before signing.

Structured session data is also what the note alone could never give the clinic: per-behavior graphs and data tables for reauthorization packets, progress analytics, and a capture schema that extends to other CPT codes as data — not code. See the data model →

5:31 PM · session ends · Maria taps Generate

The writer agent asks, instead of inventing

The writer agent reads the structured session data, the voice notes, and the client's treatment plan, and starts composing. When a required fact is missing, it does the one thing today's AI note tools don't: it stops and asks — two one-tap questions on Maria's phone, before the note exists.

Why this matters

A session note is a legal, billable record. If an agent guesses a prompt level or a caregiver's presence, it has fabricated clinical fact — the exact thing an OIG audit recoups on. Asking a targeted question is cheaper than a denial and safer than a guess.

Writer agent reuses the same escalate → push → one-tap answer loop the platform already ships.

"Ask, never invent — every fact in the note is Maria's, not the model's."

5:31
Writer agent 1 of 2
Quick question before I write

Which prompt level did the tacting program need today?

Independent Verbal Gestural Full physical
Next

Was mom present for the transition work?

Yes No Partly

Two taps · the note builds itself from your answers

5:39
Review draft EN ES
Session details form
Behaviors observed voice 4:47
Interventions & response voice 4:47
Replacement programs answered 5:33
Narrative composed
Fidelity Strict Balanced

Only what's in the data. Safest for insurance audits.

Shorten it Make it objective Fix mistakes + Edit by voice
Signature locks version 3 of 3
Maria R., RBT #XX-XXXX · 5:47 PM
5:39 PM · in the car · review and sign

A draft to approve, never a note to write

The note arrives as clean sections — the same structure QA and the payer expect. Each section carries a tiny source chip so Maria can see exactly where every line came from: a form field, a voice note at 4:47, an answer she gave at 5:33. Nothing is unattributed.

Five sections, every source shown

Session details · Behaviors observed · Interventions and response · Replacement programs · Narrative — the CASP-aligned shape that makes a note payer-defensible and QA-checkable.

The fidelity dial, anchored to Strict

"Only what's in the data. Safest for insurance audits." Set as clinic policy, not per-RBT whim — embellishment is a liability the QA agents would only have to catch later.

Edit any way she likes

The ten one-tap actions — shorten, make objective, fix mistakes, and the rest — plus a custom instruction, plus edit-by-voice. A Spanish view for review; the stored note is English.

The signature that means something

Credential-stamped (Maria R., RBT #XX-XXXX, 5:47 PM), always after session end, and it locks the version. The RBT signs every note — the BACB is clear the certificant owns its accuracy.

Draft, never commitment. Voice and AI produce an editable draft. The commit is a separate, deliberate act — Maria's signature — with the specifics read back and the version locked for the audit trail.

5:58 PM · Dr. Chen's queue · BCBA

The BCBA reviews exceptions, not everything

The BCBA-lens agent has already read all fourteen of today's notes for clinical coherence with each client's plan. Dr. Chen opens her phone once: eleven are clean, three need her judgment — each flagged with a specific, citable reason, not a vague "please review."

DC
14 notes · pre-reviewed by agent
Tuesday · 5:58 PM
BCBA-lens
11 clean — plan-aligned, all sections present Expand any one before you approve the batch
D.M. 97153 · Maria R. · behaviors ↔ token & transition goals clean
J.R. 97153 · Andre T. · progress narrative present, quantified clean
+ 9 more clean
3 need your judgment
K.B. · 97153 · Sofia M.

Response to intervention missing for ABC entry 2

T.W. · 97153 · Andre T.

Narrative doesn't reference the fading plan due this month

R.P. · 97153 · Sofia M.

Narrative describes protocol modification — reads like 97155, not 97153

Supervision, filling itself

The BACB requires each RBT get supervision for ≥ 5% of monthly service hours. Review activity counts — so the tracker fills as Dr. Chen works, instead of a spreadsheet she reconstructs at month-end.

Maria R. 5.4% · on track
Andre T. 5.1% · on track
Sofia M. 4.2% · 2 more contacts

A missed cadence isn't a clerical slip — under TRICARE, a missed monthly 97155 recoups 10% of that client's claims for the whole six-month authorization.

Dana's QA cockpit · 100% coverage

Every note checked against the payer's rule pack

Today's QA is a sampling gamble — the industry reviews a sliver, and CentralReach's own data says 80% of notes fail at least one payer requirement. Dana's cockpit inverts it: the QA-lens agent checks 100% of notes against each payer's versioned rule pack in minutes, and hands her a short queue sorted by claim risk.

100%
of today's notes checked

Not 5–10%. Every note, every rule, minutes after signing.

7
exceptions to a human today

The queue Dana actually works — down from reviewing all 218.

4
payer rule packs live

Sunshine Health, Optum, TRICARE, Cigna — versioned, clinic-editable, no deploy.

Exception queue · sorted by claim risk QA-lens
Note RBT Rule flagged · payer source Risk
K.B. · 97153 Sofia M. Optum · stop-clock timestamp missing after 12-min break High
M.L. · 97153 Andre T. Auth · units billed exceed units remaining High
P.S. · 97153 Maria R. FL Medicaid §6.2.4 · caregiver-absence reason missing Med
A.C. · 97153 Sofia M. TRICARE · narrative thin for a 3-hour session Med
Trends feed coaching, not blame

Error patterns roll up by pod and by RBT — turning the QA rep's manual "track patterns for training" step into a live signal that fights a perpetually-junior workforce (RBT turnover runs 65–103% a year).

Pod A
96%
Pod B
91%
Pod C · new hires
82%
The return loop reaches the phone

When Dana returns a note, it lands as a push on the RBT's phone with the specific fix — a one-tap correction during or right after the next session, not a rejection discovered next morning off the clock.

PraxisNotes · now

One note needs a quick fix: add the stop-clock time after the 4:12 break. Tap to open.

6:10 PM · Robert's ready-to-bill packet

Eleven gates, all green, before the biller touches it

A claim line is only "ready to submit" when every one of eleven checks passes. By the time it reaches Robert, the agents have verified all of them and assembled the packet. His job is the one that has to stay human — pressing submit — not chasing eleven things across three screens.

Session D.M. · 97153 · 6 units · Sunshine Health Ready
Eligibility active

member verified with payer on the date of service

Authorization match

covers 97153, 6 units billed ≤ 12 remaining

Signed, complete note

rendering RBT signature + date, all required fields

Times ↔ units

88 min → 6 units under the 8-minute rule

Code + modifier ↔ credential

97153 rendered by an RBT — consistent

Rendering NPI + taxonomy

enrolled, and matches the claim (Optum 2026)

ICD-10 diagnosis

coded to highest specificity, supports necessity

POS code

12 (home) — matches the note's location

MUE / weekly caps

under the daily MUE and the 40 hr/week plan cap

EVV data captured

six Cures elements on file where applicable

Timely-filing clock

day 0 of 180 — comfortably inside the window, signed same day

The last step — an extension, not an API

Office Puzzle has no public API. We looked — there's no documented REST endpoint or webhook to push into.

So the loop closes with the PraxisNotes browser extension: Robert opens Office Puzzle, selects Maria's client, and the extension fills the session, note, and billing fields straight from the verified packet — field by field or all at once, acting as him, logged in as him. He checks the screen and presses submit. Office Puzzle generates the batch claim to the clearinghouse, exactly as it does today.

The extension ships in the billing-loop phase (months 2–3). Until then the packet works as a guided copy flow — and if Office Puzzle changes its screens, a versioned field map updates the extension without touching the platform.

The owner's evening glance

The whole day, in one strip

The clinic owner doesn't operate a screen — they glance at one. This is Tuesday, closed out: the pipeline numbers the whole product exists to move, instrumented from day one.

214/218
notes signed today
96%
first-pass clean
11min
median time to signed
7
exceptions with humans
trending down
revenue at risk

Every one of those is a lever on the north-star metric — first-pass clean-claim rate — the number that turns a 30–60-day denial loop into a same-day fix. What we commit to measuring →

And for the 1,000+ solo RBTs

This isn't a separate product for clinics. Today's PraxisNotes users — the solo RBTs and BCBAs who already know the app — get the same core loop as an upgrade to the tool they use every night. Clinics unlock a team layer on top. One product, two tiers.

Solo RBT — the core loop
an upgrade to the app they already know
Voice → draft → sign, in any language
The writer agent that asks instead of inventing
A native mobile app — not a responsive web page
Compliant-by-construction notes, kept as their own
Clinic — the team layer on top
everything solo, plus the org-scale pipeline
BCBA-lens + QA-lens review at 100% coverage
Payer rule packs, versioned and clinic-editable
Supervision tracking + role-based caseload views
Ready-to-bill packets, inserted into Office Puzzle by the extension

The solo tier keeps PraxisNotes' existing users on a faster, voice-first version of what they have; the clinic tier is where a 100+ RBT agency stops scaling QA with headcount. Same brain, same tools underneath — the agents that make both run →

By 6:10, Maria is home. The note is already billable.

No 9pm form, no queue, no rework loop. Five people each did the part only a human should — and a team of agents did everything in between. That team is the next page.

Meet the team that makes this run