Give a representative the benefit, claim and cost-share answer with the governing document cited beside it, and capture grievances and appeals to the clock — adverse determinations stay with qualified staff.
Take the member's question as the representative typed or heard it, beside the contact record already open.
02
Resolve the enrolment to one plan year, benefit package, group and rider set before any document is opened.
Reason
03
Retrieve the governing document for that enrolment — evidence of coverage or benefit booklet, riders and carve-outs.
04
Read claim, accumulator and eligibility state so a cost-share figure carries the accrual it was calculated against.
05
Check network status for the named provider on the date, product and location asked about, not the default row.
Decide
06
Detect where an answer would function as a coverage decision and send the request to the determination path instead.
07
Detect a grievance or an appeal in what the member said, and open intake against the deadline it starts.
Out
08
Present the draft to the representative with the document, section and effective date cited beside every figure.
09
Retain the question, the sources read, the draft, what the representative actually said and every correction.
→Product statement
The agent retrieves, drafts and cites. The representative speaks, and any adverse determination is made and communicated by qualified staff on the determination path.
Example workflow
One member question, end to end
AgentHuman
1Contact openedCall, secure message or portal chat, with the member record already on the representative's desktop
2Identity verifiedChecked on the plan's agreed fields before any benefit, claim or accumulator detail is read back
3Enrolment resolvedOne plan year, benefit package, group, rider set and effective date — ambiguity is shown, not guessed
4Answer drafted with sourcesThe governing document and section, the claim and accumulator read, and network status on the date asked
No human action required
Stages 1 to 4 run before the representative says anything — verification, resolution and retrieval finish while the member is still explaining. A request that is really a determination ends that stretch on the spot.
5DecisionSplits on whether the answer is information or a determination
Information, sources agree
Reaches the representative as a cited draft.
Determination, conflict or gap
Leaves for the queue that owns it, with what is missing.
Representative
Reads the draft and the section it cites, then speaks to the member — or hands the request to the staff qualified to decide it.
Speak · Correct · Route to determination
Answered — handed back▼
6Answer given, disposition writtenThe representative speaks; intake, routing and the date of receipt are written where policy allows
7Outcome evaluatedAnswer accuracy against the document, plan-variant correctness, routing fit, intake completeness and call-backs by cohort
Corrections
What the representative changed before speaking is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Telling a member a service is not covered.
Making or communicating an adverse determination.
Deciding an appeal, or who reviews it.
Issuing a binding network-status confirmation.
Automation boundaryAgent acts unaided
✓Retrieve the governing document for the resolved enrolment and cite the section.
✓Read claim status, accumulators and eligibility, and show the accrual behind a figure.
✓Draft the representative's answer, and mark where two sources disagree.
✓Open grievance and appeal intake with the date of receipt and the deadline it starts.
Write actions run only inside the approval boundaries agreed during implementation. Determination and denial notices are not among them.
Quoting benefits for an unresolved enrolment.
Closing a grievance, or deciding it is not one.
Advising a member clinically or on treatment choice.
Changing benefit rules, directory data or approved wording.
Example output
One member question, annotated
Everything the agent drafts is attached to the contact and the document it came from.
Answer draft · single member contactIllustrative example
Member asked
Channel
Identity
Drafted for
Confidence
Coverage decision
What do I owe for an MRI?
Phone, interpreter on line
Verified, 3 fields
Representative — not sent
88%
Not made by the agent
As receivedThe member's question as the representative logged it, and the channel it arrived on — including that an interpreter was on the line.
Evidence usedEvidence of coverage, §5Outpatient imaging riderDeductible accrued to date
Why a figure and not a yesThe cost share is quoted against the deductible already accrued. It estimates what the member would owe.
ActionSpeakCorrectRoute to determination
What the score decidesConfidence decides how much the representative checks before speaking, not whether the member is covered.
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 member contactPhone, secure message or portal chat
03Retrieval & citation
Apply the member's own plan documents
Use the evidence of coverage, riders, carve-outs and medical policy for the enrolment actually in force.
01Approved path
Take the document search off the call
The representative starts from a cited draft instead of searching three systems while the member waits.
02Human review
Send determinations down the right path
A request that needs a coverage decision reaches the staff qualified to make it, instead of being settled at the desk.
04Build an evidence trail
Retain the question, the enrolment resolved, the document and section cited, the draft, what was said and the correction — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Aggregate answer accuracy can look acceptable while a few kinds of contact carry most of the corrections, most of the call-backs and most of the misrouted determinations. 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
Interpreter-assisted calls
5.1%
3.2×
Review
Similarly named plan variants
4.2%
2.6×
Review
Riders and group carve-outs
3.0%
1.9×
Watch
Routine benefit look-ups
1.0%
0.6×
Normal
Bar: lift vs. routine look-up baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
Most fixes land in the source, not the prompt
When an answer is wrong the cause is usually upstream — a rider that never reached the document store, or two systems naming one plan differently.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Answer accuracy, citation checks or call-backs move in one contact cohort.
02Diagnose
Traced to enrolment resolution, the document store, the accumulator feed, the directory or the routing rule.
03Improve
The source is corrected, or the rule re-approved by benefits and compliance, then version-linked.
04Verify
Re-run against held-out contacts from the affected cohort, including the ones that failed.
05Learn
The contact becomes a regression case and the correction enters the member-services runbook.
Learn → DetectThe return edge. A document or directory correction belongs to the team that owns it — the agent only stops repeating the error.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, resolution and retrieval, routing, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02Core-system, CRM and telephony assessment.
03Plan-variant and effective-date rules.
04Identity verification and disclosure scope.
05Governing-document store and citation model.
06Claim, accumulator and eligibility read.
07Provider-directory and network-status read.
08Determination, grievance and appeal routing.
09Answer-accuracy and citation evaluation suite.
10Language access and accessibility testing.
11Contact-centre desktop integration.
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 line of businessProductionProduction desktop integrationAdvancedMulti-product / multi-market
Introduced at Pilot
Cited answer drafting✓✓✓
Plan-variant and effective-date resolution✓✓✓
Identity verification and audit logging✓✓✓
Determination routing to qualified staff✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Claim, accumulator and eligibility read—✓✓
Provider-directory network answers—✓✓
Grievance and appeal intake to deadline—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Language access and accessibility coverage——✓
Multi-product and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on lines of business, plan-variant count, core-system and directory integrations, contact volume, approval controls and deployment requirements.
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
01How an enrolment is identified across core, CRM and directory→Plan-variant and effective-date resolution rulesWeek 1
02Your plan documents by year, variant, group and rider→Governing-document store and citation modelWeek 2
03Access to core claims, CRM, telephony and directory APIs→HealthEdge, Facets or QNXT, Salesforce and Genesys integrationWeek 2
04Identity-verification, disclosure and minimum-necessary rules→Identity gate, disclosure scope and audit loggingWeek 2
05Your determination, grievance and appeal routing rules and their clocks→Routing to the queue that owns each, against its deadlineWeek 4
06Real calls that went wrong, including the ones that were nearly denials→Evaluation suite, regression cases and failure-mode testingWeek 4
07Named representatives, and the languages and formats your members use→Language and accessibility testing, then pilot calls and 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 accessibility slices and the first supervised calls.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Enrolment routing, the identity gate and the determination lineW2Enrolment resolution, identity gate and the document storeW3Claim, accumulator and directory reads behind the cited draftW4Evaluation suite, citation checks and determination-routing testsW5Desktop integration, supervised calls and the language slicesW6Representatives speak from the copilot on the floor, then handover
Reading the bandA bar stops at the last week its work is named in. The language slices sit in week 5 because they come from supervised calls, not a sample.
At the end of W6The copilot has run beside live calls and been read by the representatives who speak from it, 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 member-services copilot around your plan documents.
Show us your plan documents, how an enrolment is identified across your systems, and where a question becomes a determination. We'll answer one real call from those documents and agree where the copilot stops.
