Patient-Message Reply-Drafting AI Agent (EHR In-Basket)
Read the incoming portal message, retrieve the chart context, classify it and draft a reply into the in-basket — with urgent wording escalated ahead of the queue and a clinician sending every reply.
Take the incoming portal message as the patient wrote it — their own words, their own language, their own urgency.
02
Retrieve only the chart context the reply depends on — last visit, active medications, recent results and orders.
Reason
03
Sort the message into the client's own categories — clinical, refill, results — and route it to the pool that owns it.
04
Draft from what the record and the client's approved answer library support, at the reading level their policy sets.
05
Read a refill request against the last visit and the monitoring the drug requires, and say what the protocol needs.
Decide
06
Match the message against the client's red-flag wording and surface it ahead of the queue, without assigning acuity.
07
Hold back anything that would interpret a result, change a treatment or answer what the record does not cover.
Out
08
Place the draft in the in-basket beside the message and the chart context it used, with gaps marked — unsent.
09
Retain the message, the sources read, the draft, every edit made before sending and who sent it.
→Product statement
The agent drafts into the in-basket. A clinician or the pool that owns the message reads, edits and sends — nothing is sent automatically, ever.
Example workflow
One message, end to end
AgentHuman
1Message receivedFrom the portal in the patient's own words and language, into the in-basket or pool it was addressed to
2Red-flag screenThe client's own red-flag wording is checked before a draft exists; a hit leaves the queue and goes to a person
3Context retrievedLast visit, active medications, recent results, pending orders and the care plan — for that patient and that encounter
4Reply draftedWritten from what the record and the client's approved answers support, with everything they do not cover marked
No human action required
Stages 1 to 4 run without a person in the loop — screening, retrieval and drafting finish before anyone opens the message. Nothing leaves the in-basket in that stretch, and a red-flag hit breaks out of it at once.
5DecisionSplits on what the message asks and what the record supports
Answerable from the record
Reaches the in-basket as a clean draft.
Urgent or unanswerable
Reaches a person marked, ahead of the queue.
Clinician review
The draft is held beside the message and the chart context it used, with the unanswered parts marked and no send action available to the agent.
Edit · Send · Reassign or discard
Sent — handed back▼
6Sent by a personOnly when a person presses send; the agent has no send action, and any disclosure wording goes with the reply
7Outcome evaluatedUrgent messages caught, unsafe drafts, editing before sending, wrong-context retrieval and subgroup results
Sent unchanged
Replies sent with no edit are counted as a risk signal.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Sending any reply to a patient.
Interpreting a result the clinician has not reviewed.
Approving, issuing or renewing a prescription.
Changing a dose, a drug or a treatment plan.
Automation boundaryAgent acts unaided
✓Screen every incoming message against the client's own red-flag wording.
✓Retrieve the chart context the reply depends on, for that patient and encounter.
✓Classify the message and route it to the pool that owns it.
✓Draft a reply the record supports and mark what it does not answer.
Write actions run only inside the approval boundaries agreed during implementation. Send is not one of them.
Deciding that an urgent message can wait its turn.
Closing a message without a person reading it.
Deciding that a message is a billable encounter.
Changing red-flag wording, routing pools or answer libraries.
Example output
One portal message, annotated
Everything the agent drafts is attached to the message and the chart context it came from.
Draft output · single in-basket messageIllustrative example
Message
Written in
Red flags
Draft placed in
Chart support
Refill decision
Refill request, portal
Spanish, out of hours
None found
Refill pool, unsent
88%
Held for the prescriber
As receivedThe message as the patient wrote it, in the language they wrote it in, and the red-flag screen that ran before any draft.
Evidence usedLast visit and doseMonitoring on fileClient refill protocol
Why nothing is sentThe agent has no send action. A refill is a prescribing decision; the draft states what the protocol needs.
ActionEditSendReassign or discard
What the score decidesChart support decides how much of the draft is marked unanswered, not whether a reply is safe to send.
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 incoming messageFrom the portal, into the in-basket
03Retrieval & drafting
Apply the client's own answers
Use the approved phrasing, refill protocols, results-release rules and the chart already on file.
01Clean draft
Take the assembly out of the in-basket
The routine reply arrives written, with the chart context already gathered — the same messages as before, not more of them.
02Human review
Get the urgent message seen sooner
Wording on the client's red-flag list goes to a person ahead of the queue instead of waiting its turn behind routine traffic.
04Build an evidence trail
Retain the message, the chart context read, the draft, every edit made before sending and the person who sent it — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
In-basket & portalEpic In Basket · MyChart · Oracle Health MEDITECH · patient portal
Chart contextProblem list · medications · allergies Last visit and notes · care plan
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the send button
Each control wraps the one inside it. A draft clears every layer before it appears in the in-basket, and the send action sits outside all six.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeReturn the in-basket to the existing workflow if evaluations or production signals degrade.Roll back
L5TraceabilityRecord the message, the context read, the draft, every edit and the sender.Record
L4Send gateEvery reply waits for a person to read, edit and send it.Gate
L3Context bindingNothing is drafted until the patient and the encounter are confirmed to match.Verify
L2Scope limitsRestrict the draft to the client's approved answers and rules.Restrict
L1Red-flag screeningRed-flag wording goes to a person before any draft exists.Escalate
Model coreDraft reply proposed — classification, chart context used, suggested wording and chart support
L1 – L2Decide whether a draft may be written at all
L3Decides which chart the draft may read
L4 – L5Keep send with a person and the trail intact
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate what reaches the patient — not only how the draft reads.
Coverage runs the whole depth of the workflow, and every layer is cut by slice. The suite is built first around the messages that must never be drafted as routine.
Surface — the draft waiting in the in-basket
Depth of coverage ▼
E1Final-output evaluationWas the reply correct, and did the record support it?
E2Urgent-message recallHow many red-flag messages were drafted as routine?
E3Tool evaluationDid it read the correct patient, encounter and result?
E4Unsafe-draft rateHow often would the draft have caused harm if sent unchanged?
E5Slice evaluationHow does draft quality change across specific message cohorts?
E6Business outcomeHow much was edited before sending, and how much went out unread?
Floor — the reply the patient actually receives
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 · Intake / sorting1 mode
PM-01
Urgent read as routine
A red-flag message is drafted and queued like any other.
Stage sortsThe message, its language and the pool it belongs to
02 · Retrieval2 modes
PM-02
Wrong patient or encounter
Context is taken from another chart or an older visit.
PM-03
Refill without the check
Drafted past the last visit or the monitoring the drug needs.
Stage gathersThe patient, the encounter and the results read
03 · Drafting2 modes
PM-04
Result answered too early
A result no clinician has interpreted is explained to the patient.
PM-05
Advice nobody gave
A warm, confident draft states a plan the clinician has not decided.
Stage writesThe reply text and the wording the draft proposes
04 · Review / send1 mode
PM-06
Sent on a glance
A fluent draft is sent unread, with its errors intact.
Stage returnsThe draft a person reads, edits and sends
05 · Change / Version1 mode
PM-07
Silent routing regression
A rule or model change moves what reaches which pool.
Stage tracksModel, prompt, red-flag list and routing changes
Sev-1 · unsafe content reaches the patientSev-2 · the draft misleads the senderSev-3 · the message waits or lands wrong
Draft quality is lowest where the stakes are highest
Aggregate reply quality can look acceptable while a small number of message cohorts carry most of the wrong context, most of the unsafe drafts and most of the replies that go out with a glance. 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
Non-English and translated messages
5.4%
3.4×
Review
Symptom messages with red flags
4.3%
2.7×
Review
Low health-literacy messages
3.1%
1.9×
Watch
Routine administrative requests
1.0%
0.6×
Normal
Bar: lift vs. all-message baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A rise in replies sent unedited opens a ticket, not a case study
Send-without-edit is read here as a risk signal. When it climbs, the cohort is pulled and the drafts are read back against the messages behind them.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Urgent recall, unsafe drafts or replies sent unedited move in a cohort.
02Diagnose
Traced to the sorting, the retrieval, the answer library or the routing.
03Improve
The red-flag list, prompt or protocol rule is changed, re-approved and version-linked.
04Verify
Re-run against held-out messages from the affected cohort, including the ones that failed.
05Learn
That message becomes a regression case and the changed rule enters the in-basket runbook.
Learn → DetectThe return edge. A red-flag or routing change decides which patient waits — 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, retrieval and drafting, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02In-basket, portal and pool routing assessment.
03Red-flag wording and escalation paths.
04Message taxonomy and answer library.
05Chart-context retrieval and encounter binding.
06Refill-protocol and results-release rules.
07Draft generation in the client's phrasing.
08Disclosure wording and send-time attestation.
09Urgent-recall and unsafe-draft evaluation suite.
10Language and health-literacy testing.
11In-basket integration and send 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 clinic, one message poolProductionProduction in-basket integrationAdvancedMulti-specialty / multi-pool
Introduced at Pilot
Drafted replies into the in-basket✓✓✓
Red-flag screening and escalation✓✓✓
A person edits and sends every reply✓✓✓
Baseline draft-quality evaluation✓✓✓
Introduced at Production
Answer library, phrasing and reading level—✓✓
Chart-context retrieval and binding—✓✓
Message classification and pool routing—✓✓
Drafts held to refill and results rules—✓✓
Observability and subgroup evaluation—✓✓
Introduced at Advanced
Multi-language and translation workflows——✓
Multi-specialty and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on message volume and pools, in-basket and portal integration, the answer library, red-flag and routing rules, translation 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 in-basket pools, routing rules and cover arrangements→In-basket, portal and pool routing assessmentWeek 1
02The wording you already treat as a red flag→Red-flag wording and escalation pathsWeek 1
03Your standard answers, refill protocols and results-release rules→Message taxonomy, answer-library and protocol mappingWeek 2
04Access to in-basket, chart, results and refill APIs→Epic In Basket, MyChart, results and refill integrationWeek 2
05Messages that went wrong, including the ones that got sent→Urgent-recall and unsafe-draft evaluation suiteWeek 4
06The languages and reading levels your patients write in→Language and health-literacy testingWeek 5
07Named clinicians and pool staff who will edit and send→Send 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 language and literacy slices and the first replies a person sends.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1In-basket pools, red-flag wording, and what may never be draftedW2Answer library, message taxonomy and API assessmentW3Chart-context retrieval, refill and results rules, first draftsW4Urgent-recall and unsafe-draft suite, disclosure and attestationW5Language and literacy slices, in-basket integration, first replies sentW6Pool staff and clinicians send live replies, then handover
Reading the bandNothing is drafted before week 3, because the red-flag wording has to be agreed first. The bars show that order, not an even spread of effort.
At the end of W6Replies have been edited and sent by the clinicians and pool staff who own the in-basket, 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 an in-basket agent around the reply your clinicians send.
Show us your in-basket pools, the wording you already treat as a red flag, and how a portal message gets answered today. We'll score a week of drafts against the replies your staff actually sent.
