Start with the thing being measured. Pivot the timeline on the note and both sides go dark — nobody hydrates the context coming in, nobody tracks the inbox going out. The note itself is 12.5% of the arc.
The clinical process runs from booking to closure. Every tool sits in one narrow band of it — and three bands have nothing in them at all.
The encounterclinical process
Schedulingwhy they booked
Prechartingread the whole chart
Historythe interview
Examhands on the patient
CDSthe decision
Documentationthe note
Follow-updid it happen?
booksdays beforeIN THE ROOMafterweeks → months
Answer enginesOE · DoxGPT
the question, answeredyou gather and paste the context by hand
ScribesAbridge · Ambience
hears the room → writes the notenever reads the chart — no precharting
Nobodyno product, no eval
?
?
?
The three empty bands are not mysteries — they are where the questions already go. Classified and counted, the stream is the workflow eval those ? boxes are waiting for.
the ? boxes, answered · praxis — question stream → intent → subintent · de-identified · counts land here as the taxonomy matures
lands before the noteContext questions
“what changed since her last visit?”
“summarize the outside cardiology notes”
“which meds still need reconciling?”
interval history · chart synthesis · med rec
lands at the notePoint-of-care questions
“max metoprolol dose in CKD?”
“differential for this presentation?”
“what does the guideline say here?”
med dosing · differential · guideline lookup
lands after the noteFollow-through questions
“draft a message explaining this result”
“handle this refill request”
“write the prior-auth appeal”
result interpretation · patient messaging · admin drafting
The compute belongs on the dark sides of the note — hydrate the chart coming in, track the inbox and closure going out. Every question above is a vote for where it goes; classified and counted, the stream becomes the workflow eval the ? boxes are waiting for. And learn how clinicians actually use it before trying to teach them. One recommendation, walked end-to-end →
The chart is the whole picture. Every tool hands you a lens instead — so sweep it around and
see how little comes into focus, and how long it takes.
simulated questions
ask a question, or sweep the glass yourself
patient context 0
Empty. Whatever you hand the answer engine, this is
all of it — and right now it is nothing.
0 of 0 items in context
You uncover only what you thought to look at, in whatever shape your
sweep happened to make. No benchmark scores what never came into focus.
Run the same patient twice. Identical engine, identical question — the only difference is
whether anybody swept the chart first.
the same patient, twice · illustrative
T+0
“Cellulitis — what antibiotic?”one patient · one question · one engine
one difference upstream: did anybody sweep the chart?
⏺ without the chart
T+0
Context assembled: 2 itemsage, sex, the complaint
T+0
The chart is not sweptthe 2019 outside ED record is never opened
2019-04 · OUTSIDE ED · amoxicillin → ANAPHYLAXIS
T+2 min
Prescribed: amoxicillin–clavulanatea guideline-standard choice for cellulitis
T+90 min
outcome
Anaphylaxis
epinephrine · ED · admitted overnight. The allergy was in the chart the whole time.
⏺ with the chart
T+0
Context assembled: 38 itemsincluding the scanned outside records
T+0
The chart is sweptthe 2019 outside ED record surfaces
2019-04 · OUTSIDE ED · amoxicillin → ANAPHYLAXIS
T+2 min
Prescribed: doxycyclinethe guideline’s choice when penicillin is out
T+6 d
outcome
Resolved
no reaction, no return visit. Nothing about the model was different.
Both prescriptions are correct answers to the question that was asked. Score either
one against a rubric and it passes — the drug is guideline-appropriate for cellulitis, the reasoning is sound,
the citation is real. The harm is upstream of everything a benchmark can see.
The question that never gets asked
2
The precharting stream, filtered by the doctor, classified by praxis — and the questions that never form.
speaker notes
Every gray dot is a before-visit inquiry — unscheduled, uncounted, unpaid; most of the chart is never reviewed. The doctor is the filter: attention, time, and what they know to ask — only a fraction enters, and color is assigned on the way out. praxis classifies what emerges (intent → subintent): extraction = interval history · med rec · outside records · guideline lookup; reasoning = differential · risk synthesis · dose in context · goals of care. Both lanes end in the answer-engine log, counted as product usage (“1M consultations a day”) — the same cognition, relocated; the tool takes credit. Never formed — the red dots in the pile: “could this be ATTR amyloid?” exists only if you’ve read the 2026 guidance — an unasked question is indistinguishable from no need.