Capture the consented encounter, draft the note into your own templates and hand the clinician a draft to edit — with unsupported lines marked, subgroup evaluation, audit trails and nothing filed before signature.
Record the encounter only after consent is captured on the client's terms, on the agreed device and channel.
02
Read the chart the clinician already has open — problem list, medications, allergies, recent results and the last note.
Reason
03
Separate the speakers and keep every statement attached to whoever made it — clinician, patient, carer or interpreter.
04
Draft the note into the client's own template and smart-phrase library, section by section, rather than a house format.
05
Tie each drafted line back to the point in the encounter it came from, so text the encounter does not support is visible.
Decide
06
Detect content in the draft that nobody said and hold it back instead of letting it read like the rest of the note.
07
Mark thin audio, crosstalk, interpreted encounters and weakly supported sections for the clinician to read closely.
Out
08
Present the draft with suggested orders, problem-list changes and coding hints — unplaced, unposted and uncommitted.
09
Retain the consent, the transcript, the draft, every edit made before signature and the signature event itself.
→Product statement
The agent drafts. The clinician edits, attests and signs — nothing reaches the chart unsigned, no order is placed and no billing code is committed by the agent.
Example workflow
One encounter, end to end
AgentHuman
1Consent capturedRecorded on the client's terms before any audio is taken, with a refusal path that does not delay the visit
2Encounter capturedAudio from the agreed device, alongside the chart the clinician already has open
3Speakers separatedEvery statement kept attached to the person who made it — clinician, patient, carer or interpreter
4Draft written to your templateThe client's own sections and smart phrases, with each line tied back to the point it came from
No human action required
Stages 1 to 4 run without a person in the loop — capture, speaker separation and drafting finish before the clinician is asked to read anything. Nothing is filed anywhere in that stretch.
5DecisionSplits on how much of the draft the encounter supports
Fully supported draft
Reaches the clinician as a clean draft.
Unsupported or thin
Reaches the clinician marked line by line.
Clinician review
The draft is held beside the encounter it came from, with unsupported lines marked and the suggested orders and codes still unplaced.
Edit · Attest and sign · Discard the draft
Signed — handed back▼
6Filed on signatureWritten to the chart only when the clinician signs; suggested orders and codes stay unplaced until a clinician acts
7Outcome evaluatedUnsupported content caught, omissions, editing before signature, coding agreement and subgroup results
Edits
Every edit made before signature is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Signing or attesting a note.
Placing an order or a prescription.
Committing a diagnosis or a billing code.
Writing up an examination that was not performed.
Automation boundaryAgent acts unaided
✓Capture the encounter once consent is recorded on the client's terms.
✓Separate speakers and keep every statement attached to the person who made it.
✓Draft the note into the client's own template and smart-phrase library.
✓Mark unsupported lines and hold suggested orders and codes unplaced for the clinician.
Write actions run only inside the approval boundaries agreed during implementation. Signature, orders and codes are not among them.
Adding history the encounter did not contain.
Amending or addending a note already signed.
Recording without consent, or overriding a refusal.
Changing templates, retention or coding rules.
Example output
One drafted note, annotated
Everything the agent drafts is attached to the point in the encounter it came from.
Draft output · single clinic encounterIllustrative example
Encounter
Capture
Speakers
Draft handed to
Line support
Orders and codes
Follow-up visit, in person
Consent recorded first
3 separated
Clinician, unsigned
97%
Suggested, not placed
As receivedThe encounter as it was captured, and the consent recorded before capture began — nothing on this side is drafted, summarised or inferred.
Evidence usedConsent on fileSpeaker-separated transcriptClient note template
Why nothing is filed yetThe agent has no signature authority. Until a clinician attests, the draft sits outside the chart and the suggested orders sit unplaced.
ActionEditAttest and signDiscard the draft
What the score decidesLine support marks which lines to read closely, not whether a note is safe to sign. A clinician signs either way.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every consented encounterIn the room, on the agreed device
03Capture & drafting
Apply the client's own template
Use the approved note templates, smart phrases, specialty sections and the chart already on file.
01Clean draft
Take the typing out of the visit
The clinician leaves the room with a drafted note in their own format instead of an evening of catch-up documentation.
02Clinician review
Put the doubtful lines in front of the clinician
Unsupported and thin sections are marked in the draft rather than buried in text that reads as fluently as the rest.
04Build an evidence trail
Retain the consent, the speaker-separated transcript, the draft, every edit made before signature and the signature event — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
EHR & noteEpic · Oracle Health · MEDITECH athenahealth · note write-back
Orders & resultsOrder sets · e-prescribing Result and referral queues · care plans
Capture & speechIn-room mic · mobile app · telehealth Speech pipeline · interpreter channel
Agent
Clinical documentation & ambient scribe
Captures on consent Drafts the note Holds for signature
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the chart
Each control wraps the one inside it. A draft clears every layer before a clinician reads it, and the signature sits outside all six.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeReturn documentation to the existing workflow if evaluations or production signals degrade.Roll back
L5TraceabilityRecord the consent, transcript, draft, every edit and the signature event.Record
L4Signature gateFiling, orders and codes wait for a clinician to edit, attest and sign.Gate
L3Consent and captureNothing is recorded or kept beyond the consent given for that encounter.Verify
L2Template guardrailsRestrict the draft to the client's approved sections, phrases and defaults.Restrict
L1Support checkingLines the encounter does not support are held back and marked.Hold back
Model coreDraft note proposed — sectioned text, suggested orders, coding hints and line support
L1 – L2Decide whether a drafted line may stand
L3Decides what may be recorded at all
L4 – L5Keep signature with a clinician and the trail intact
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate the draft against the encounter — not only how it reads.
Coverage runs the whole depth of the workflow, and every layer is cut by slice. The suite is built first to catch content the encounter never contained.
Surface — the draft the clinician opens
Depth of coverage ▼
E1Final-output evaluationIs the note faithful to the encounter it was drafted from?
E2Step-level evaluationWere the speakers separated and the right template sections filled?
E3Tool evaluationDid it read and write the correct patient, encounter and note?
E4Fabrication and omissionHow much unspoken content survives, and how much said content is lost?
E5Slice evaluationHow does faithfulness change across specific encounter cohorts?
E6Business outcomeHow much was edited before signature, and did the coding hints agree with the coder?
Floor — the signed note in the chart
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle.
Agent lifecycleDirection of processing →
01 · Capture1 mode
CD-01
Accented speech degrades
Word error rises with accent, crosstalk or room noise.
Stage recordsThe consented audio, the room and the open chart
02 · Transcription2 modes
CD-02
Negation flipped
A denial in the room becomes a finding in the note.
CD-03
Dose or laterality misheard
A strength, frequency or side is transcribed wrong.
Stage hearsWords, speakers, negation, doses and laterality
03 · Drafting2 modes
CD-04
Content nobody said
Unspoken detail appears in the draft, including exam findings.
CD-05
Said but not drafted
Something the clinician stated is missing from the note.
Stage writesThe note sections, orders and coding hints proposed
04 · Review / signature1 mode
CD-06
Signed without reading
A fluent draft is attested with its errors intact.
Stage returnsThe draft the clinician edits, attests and signs
05 · Change / Version1 mode
CD-07
Silent template regression
A template or model change moves note content unnoticed.
Stage tracksModel, prompt, template and coding-rule changes
Sev-1 · wrong content reaches the signed chartSev-2 · the draft misleads the clinicianSev-3 · the draft degrades, more is rewritten
Faithfulness is not spread evenly across encounters
Aggregate note quality can look acceptable while a small number of encounter cohorts carry most of the unsupported lines, most of the rewriting before signature and most of the risk that something nobody said gets signed. Nestack reports performance by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Interpreted and non-English visits
5.8%
3.6×
Review
Accented and non-native speech
4.2%
2.6×
Review
Noisy rooms and telehealth audio
3.1%
1.9×
Watch
Routine single-problem follow-ups
1.0%
0.6×
Normal
Bar: lift vs. routine follow-up baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A line nobody said becomes a test before it becomes a fix
One piece of unsupported text is not closed when the clinician deletes it. It becomes a held-out encounter the next drafting change has to clear.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Unsupported lines, omissions or editing before signature move in a cohort.
02Diagnose
Traced to the audio, the speaker separation, the transcript or the drafting step.
03Improve
The prompt, template or support rule is changed, re-approved and version-linked.
04Verify
Re-run against held-out encounters from the affected cohort, including the ones that failed.
05Learn
That encounter becomes a regression case and the changed rule enters the documentation runbook.
Learn → DetectThe return edge. A template or coding-rule change is a documentation-integrity change — it is signed off before it ships, not after.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, capture, speech and drafting, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02EHR note, order and coding API assessment.
03Consent capture, recording policy and audio retention.
04Note-template and smart-phrase mapping.
05Capture on the agreed devices and channels.
06Speech pipeline and speaker separation.
07Draft generation against client templates.
08Order and coding suggestion handling.
09Fabrication and omission evaluation suite.
10Accent, language and interpreted-visit testing.
11EHR note write-back and signature workflow.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne specialty, one siteProductionProduction EHR integrationAdvancedMulti-specialty / multi-site
Introduced at Pilot
Drafted notes from consented capture✓✓✓
Consent capture and retention policy✓✓✓
Clinician attestation and signature✓✓✓
Baseline faithfulness evaluation✓✓✓
Introduced at Production
Client templates and smart phrases—✓✓
Speaker separation in multi-speaker rooms—✓✓
Order and coding suggestions, unplaced—✓✓
EHR note write-back—✓✓
Observability and subgroup evaluation—✓✓
Introduced at Advanced
Coding and CDI integration——✓
Multi-specialty and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on specialties and templates, EHR, order and coding integrations, encounter volume, consent and retention requirements, approval controls and deployment.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01Your consent, recording and audio-retention policy→Consent capture, recording policy and retention rulesWeek 1
02Your note templates, smart phrases and specialty sections→Note-template and smart-phrase mappingWeek 2
03Access to EHR note, order and coding APIs→Epic and Oracle Health note, order and coding write-backWeek 2
04Recordings or transcripts you are cleared to use→Speech pipeline, speaker separation and the drafting baselineWeek 3
05Notes that went wrong, including the ones that got signed→Evaluation suite, regression cases and failure-mode testingWeek 4
06The languages, accents and interpreter arrangements in your rooms→Accent, language and interpreted-visit testingWeek 5
07Named clinicians who will edit and sign the drafts→Signature workflow, then supervised drafting and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 carries both the subgroup evaluation and the first drafts a clinician signs.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Consent, recording and audio-retention policy signed offW2Note templates, API assessment and the first capture channelW3Speech pipeline, speaker separation and drafting into your sectionsW4Fabrication and omission evaluation suite and regression encountersW5Accent and interpreted-visit slices, write-back, first signed draftsW6Clinicians sign live drafts in clinic, then Agent Care handover
Reading the bandEach bar covers the weeks its work is named in. The accent and interpreted-visit slices sit in week 5, cut from the first signed drafts.
At the end of W6Drafts have been edited and signed by the clinicians who own the notes, then Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Healthcare AI agent
Build a documentation agent around the note your clinicians sign.
Show us your note templates, your consent and recording policy, and how a note reaches the chart today. We'll draft one encounter into your own template and agree what may never reach the chart unsigned.
