7:22pm. Marcus is on his fifth SOAP note. He runs a two-practitioner osteopathy clinic in Kitchener. His last patient left at 5:45. Between then and now he's been doing this: open the EHR, find the appointment, scroll to notes, try to reconstruct the exact sequence of a spinal assessment he performed four hours ago, type it into the template, realize he forgot to document the referral conversation from the 2pm slot, go back, edit that note, return to the current one, check his sticky note that says "L4-L5 R rotation restricted — re-assess 2 wks," translate that into something defensible, save. Next patient.
Two more to go. His associate — three months out of a Canadian College of Osteopathy program — told him last week she didn't realize that "half the job is typing about what you already did." She's already looking at industry positions.
Marcus isn't surprised. He told me he lost his last associate the same way.
The reconstruction problem, specifically
The AMIA 25x5 Task Force published their 2024 TrendBurden survey and the numbers should make every clinic owner uncomfortable: 77% of healthcare professionals reported finishing work later than they wanted to specifically because of documentation. Not patient emergencies. Not complex cases. Paperwork.
And 75% of those same respondents said documentation impedes their ability to provide patient care. Three quarters of clinicians believe the thing they have to do after seeing a patient is making them worse at seeing the patient.
The AMA's 2025 physician data puts finer numbers on it: out of a 57.8-hour average workweek, only 27.2 hours involve direct patient care. Thirteen hours go to indirect care — charting, order entry, inbox management. The rest is admin. That ratio should bother anyone who went into healthcare to help people.
A November 2024 study in Health Affairs found that every additional hour a primary care physician spends on documentation reduces the chance they'll review a patient's outside records by 7.1%. Documentation doesn't just consume time. It crowds out the clinical thinking that requires time.
What makes charting uniquely draining
It isn't the typing. It's the reconstruction.
A physiotherapist assessing a frozen shoulder performs maybe fifteen discrete clinical observations during a thirty-minute session. Range of motion in three planes. Compensatory patterns. Pain response at end range. Tissue quality during manual work. Neural tension findings. Patient-reported pain levels. Functional goals discussed. Home exercise modifications agreed on. Follow-up timing.
All of this happens in the flow of conversation and clinical reasoning. None of it gets documented in real time because the practitioner is treating a person. So the observations live in short-term memory, degrading with every subsequent patient, until the practitioner sits down at 6pm and tries to reconstruct something that felt intuitive three hours ago into structured clinical language.
The problem isn't that documentation is hard. The problem is that documentation requires a completely different cognitive mode than clinical care, and practitioners are asked to switch between them at the end of the day when they have the least capacity for it. It's the equivalent of asking a surgeon to write the operative report mid-procedure — nobody would do that — except the time delay makes it worse, not better.
Why does clinical documentation take so long for practitioners?
Clinical documentation is slow because practitioners must manually reconstruct patient conversations from memory after appointments, translating verbal discussions into structured note formats like SOAP, treatment plans, and assessments. The AMIA TrendBurden 2024 survey found that 77% of healthcare professionals work late specifically because of charting, and most clinicians report the burden hasn't decreased despite new EHR tools.
Memory degradation is the hidden multiplier
By the time a practitioner sits down to chart the fifth or sixth patient of the day, details have started to blur. Was it the 2pm patient who mentioned knee pain radiating from the lateral collateral ligament, or the 3:30? Did the consent conversation happen with the chronic pain patient or the post-surgical follow-up? These micro-confusions compound. Every note takes longer than the last because the memory retrieval costs more. The seventh note at 7:22pm costs more cognitive effort than the first note at 5:50pm. The math is asymmetric in exactly the wrong direction.
When the appointment records itself
Oli Health built something that short-circuits the reconstruction problem entirely. The concept is straightforward but the execution matters: record the appointment conversation — whether it's a telehealth call or an in-person visit using the browser microphone — and let AI generate structured clinical notes from the transcript.
Not one generic note. Up to ten separate note types, each populated from the same conversation, each following a different template. A SOAP note. A treatment plan. A progress note. An initial assessment. Whatever templates the practitioner or practice has configured for that appointment type. The AI doesn't guess which template to use — the practitioner (or practice admin) attaches templates to scheduling configurations in advance, and the system generates a draft for each one the moment the recording finishes processing.
One conversation, multiple structured outputs
A single 20-minute appointment recording can produce a SOAP note, a treatment plan, and a progress summary simultaneously. Each follows its own template structure, populated with the relevant clinical details extracted from the transcript. The practitioner reviews drafts, edits where needed, and signs off. The reconstruction step — the part that consumed Marcus's evening — is gone.
The notes follow the template structure the practitioner designed: if your SOAP template has fields for chief complaint, history of present illness, review of systems, medications, and allergies, the AI populates each one with details from that specific conversation. When the patient mentions recurring lower back pain that started six weeks ago and worsens with prolonged sitting, that goes into the HPI section. When they mention naproxen 500mg twice daily, that goes into medications. It's structured extraction, not summarization.
That screenshot is a real generated note from a recorded appointment. The subjective section alone — chief complaint, HPI, review of systems, past medical history, medications, allergies — would take a practitioner fifteen to twenty minutes to reconstruct from memory. The AI produced it in under a minute from the transcript.
Can AI generate multiple types of clinical notes from one appointment?
Yes. Oli Health's AI Notes feature generates up to 10 different structured clinical notes from a single recorded appointment — SOAP notes, treatment plans, progress notes, initial assessments, and more. Each note follows a different practitioner-configured template and is populated with specific clinical details extracted from the conversation transcript, not generic summaries.
The math on a twenty-five patient day
A solo chiropractor in Red Deer sees twenty-five patients a day in fifteen-minute appointments. He has no time to chart between patients. Every note gets deferred. Twenty-five reconstructions from memory over a cold dinner.
Let's say each note takes eight minutes to reconstruct — conservative for a detailed SOAP. That's three hours and twenty minutes of charting per day. Five days a week. Over sixteen hours a week spent writing about things he already did.
If AI Notes cuts that by 80% — and the chiropractor I spoke with said his per-patient documentation time dropped from twelve minutes to about ninety seconds of review — he's getting thirteen hours of his week back. I keep checking that math because it seems too large. It isn't. The documentation burden is just that big when you add it up instead of experiencing it one note at a time.
For telehealth, the recording is built directly into the video call — one button. For in-person visits, the practitioner starts a recording from the appointment sidesheet, and a floating bar stays visible during the session so nothing gets left running accidentally. Both methods produce the same output: a transcript, and from that transcript, structured notes.
A multidisciplinary clinic in Vancouver with three naturopaths, a counselor, and an acupuncturist has a different version of the scaling problem: five different note formats, five different documentation standards, one shared EHR where consistency is aspirational at best. When each practitioner builds their own templates and the AI generates notes following those templates from recorded sessions, the variability problem solves itself. The counselor's notes follow the counselor's structure. The acupuncturist's TCM assessment follows the acupuncturist's structure. Same technology, different outputs.
Note quality, not just speed
The unexpected shift is in accuracy. When a practitioner reconstructs from memory at end of day, details get dropped. The patient mentioned bilateral symptom onset but the practitioner documented unilateral because the bilateral detail was mentioned in passing during a discussion about something else. The medication dosage was stated once and never repeated, so the note says "naproxen" without the dose. The follow-up interval was agreed as "two weeks" but got written as "follow up as needed" because the practitioner was tired and defaulted to vague.
The transcript captures everything. The structured extraction surfaces details that a fatigued practitioner would have missed or rounded off. The AI follows each template precisely — subjective, objective, assessment, plan get the right details in the right fields. The practitioner's job shifts from writing to reviewing. Scan the note, confirm accuracy, sign off. Most clinicians make minor adjustments. A two-minute review of a draft is categorically different from an eight-minute reconstruction from scratch.
How does AI clinical documentation reduce practitioner burnout?
AI clinical documentation eliminates the end-of-day reconstruction burden that drives most after-hours charting. Instead of spending hours rebuilding patient conversations from memory, practitioners review and edit AI-generated draft notes that already contain the clinical details from the recorded appointment. The AMA reports that physicians currently spend only 27.2 out of 57.8 work hours on direct patient care, with documentation consuming the bulk of the remainder.
What to look for in AI charting software
Not all AI charting tools work the same way. Three categories have emerged, and the differences matter more than comparison pages suggest.
Ambient AI scribes listen during the visit and generate a single note. These work reasonably well for primary care with predictable visit structures. For allied health practitioners whose sessions involve manual therapy, movement assessments, or extended counseling, a single ambient note often misses the clinical specificity they need.
Template-based AI documentation — where Oli Health's AI Notes sits — lets the practitioner define the output structure in advance. You build templates, attach them to appointment types, and the AI populates each template from the recorded conversation. The distinction matters because allied health documentation isn't one-size-fits-all. A chiropractor's SOAP note looks nothing like a psychotherapist's progress note, and both are different from an acupuncturist's TCM assessment.
Dictation-plus-formatting tools are speech-to-text with structural cleanup. They save typing time but don't solve the reconstruction problem because the practitioner still has to narrate the note from memory after the session ends.
When evaluating: Does the tool support multiple note types from a single recording? Can you customize templates for your discipline's documentation standards? Does it work for both telehealth and in-person visits? Is the output editable before it becomes part of the patient record? And — this gets overlooked — does it integrate with the rest of your practice management, or is it a standalone tool that adds another tab?
What should practitioners look for in AI charting software?
Practitioners evaluating AI charting software should prioritize: support for multiple note types from a single recording, customizable templates that match their discipline's documentation standards, compatibility with both telehealth and in-person visits, editable drafts before finalizing, and integration with their existing practice management system to avoid workflow fragmentation.
Getting started without overhauling everything
The practitioners who adopted AI notes most successfully all did the same thing: they started small. One appointment type. One template. Three or four patients over a day or two.
The reason this works is calibration. Your first AI-generated SOAP note tells you immediately whether your template structure gives the AI enough guidance. If your template just says "Subjective" with no sub-fields, the AI produces unstructured text. If you break it into chief complaint, HPI, review of systems, and medications, you get precise extraction into each field. Template quality determines output quality.
A reasonable first week:
- Pick your most common appointment type — the one you chart five or six times a day.
- Build a note template with clearly defined sections. "Assessment" is vague. "Assessment: primary diagnosis, secondary considerations, functional limitations, contraindications" gives the AI what it needs.
- Record three to five sessions. For telehealth, hit the AI Notes button. For in-person, start the recording from the appointment sidesheet.
- Review the generated notes against what you would have written manually. Note where the AI was accurate and where the template needs adjustment.
- Refine the template, then expand to your other appointment types.
Most practitioners stop editing templates after the second or third round. Once the structure is right, the AI consistently extracts the right information into the right fields. The ten minutes you spend refining a template saves ten minutes on every note it generates for the rest of the year.
Marcus's associate is still at the clinic. She hasn't started browsing industry postings yet this month. He told me the evenings are different now — not gone, but shorter. He finishes the last note within ten minutes of the last patient instead of ninety. Whether that's enough to keep her long-term, he doesn't know. Neither do I. But the charting isn't the thing pushing her toward the exit anymore, and for a two-person clinic where losing one practitioner means losing half the practice, that matters more than any feature comparison.
If your evenings disappear into charting, it might be worth trying AI Notes on a few patients this week. You'll know within three appointments whether it changes your day.
