Utilization-Management & Medical-Necessity Review AI Agent
Locate the criteria that apply, find where the submitted record speaks to each one, and hand a nurse reviewer or medical director a structured summary — the reviewer decides, and the agent never denies.
Take the request as submitted — member, plan, service, level of care, dates and the requesting provider's own rationale.
02
Pin the criteria set, edition and plan terms that govern that request on that date of service, and stamp what was read.
Reason
03
Find the notes, results, functional scores and prior therapy that speak to each criterion, and cite each one.
04
Mark every criterion evidenced, not evidenced or not applicable, and carry the circumstances it has no field for.
05
Check that the level of care, the dates and the service being compared are the ones the request actually asks for.
Decide
06
Where every criterion is evidenced, the case goes to a reviewer as a complete file, with nothing left to chase.
07
Everything else goes to a qualified clinical reviewer, and to a medical director of the specialty the plan's policy requires.
Out
08
Hand over a structured summary — criteria set and edition, each criterion with its record location, gaps named.
09
Retain the criteria version, the record read, the evidence cited, the decision and the reviewer's own words.
→Product statement
The agent finds the evidence and sets it beside the criteria. The determination is the reviewer's, and an adverse determination is issued only by a qualified clinician — never by this agent, and never on its recommendation.
Example workflow
One review, end to end
AgentHuman
1Request receivedA prior-authorisation, concurrent-review or continued-stay request with the record the provider submitted
2Criteria and plan terms pinnedThe criteria set, edition and plan document in force for that member, service and date of service, with the date read
3Evidence located in the recordEach criterion set beside the note, result, functional score or documented prior therapy that speaks to it
4Summary assembledCriterion by criterion, evidenced or not, with the page it came from and the circumstances no criterion asks about
No human action required
Stages 1 to 4 run without a person in the loop — the criteria lookup, the record search and the summary are finished before a reviewer opens the case. Nothing has been decided.
5DecisionSplits on whether every criterion is evidenced
Every criterion evidenced
Goes to a reviewer as a complete file, undecided.
Anything unevidenced or unclear
Goes to a clinical reviewer, undecided.
Nurse reviewer or medical director
Reads the record itself, decides, and writes the rationale in their own words. An adverse determination is theirs alone.
Approve · Escalate · Send back
Decided — handed back▼
6Determination recordedThe reviewer's decision and their own words, recorded under their name with the criteria version and evidence
7Outcome evaluatedRetrieval recall, criteria-version correctness, reviewer agreement, read-through and overturn on appeal, by payer class and service line
Reviewer changes
Every criterion a reviewer reads differently is counted, in both directions.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Deciding that a service is not medically necessary.
Issuing any adverse determination, in whole or in part.
Recommending a denial, in words or by score.
Ending, shortening or downgrading an authorised stay.
Automation boundaryAgent acts unaided
✓Pin the criteria set, edition and plan terms to the date of service.
✓Retrieve only the record the criteria call for, and cite where each finding sits.
✓Mark each criterion evidenced or not evidenced, and draw no conclusion from it.
✓Assemble the peer-to-peer and appeal packet from the file as it already stands.
Write actions run only inside the approval boundaries agreed during implementation. An adverse determination is not one of them, on any tier, in any configuration.
Choosing which criteria set or edition applies.
Writing the reviewer's clinical rationale for them.
Closing a peer-to-peer, an appeal or a grievance.
Changing criteria sources, thresholds or approval rules.
Example output
One review request, annotated
Everything the agent marks is attached to the criterion and the record line it came from.
Utilisation-review output · single requestIllustrative example
Request
Plan
Criteria edition
Criteria evidenced
Confidence
Determination
Inpatient continued stay
Managed Medicaid
In force, dated
Six of eight
91%
None — reviewer's
As receivedThe request, the plan terms and the criteria edition in force on that date of service, with the date it was read.
Evidence usedProgress note, day 3Functional score on fileDocumented prior therapy
Why two are openTwo criteria have no supporting text in the record. That is a statement about the record, not the patient.
ActionApproveEscalateSend back
What the score decidesHow hard the reviewer should look for evidence the agent may have missed. It does not decide the case.
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 review requestFrom the UM queue and provider intake
03Criteria & plan terms
Apply the criteria that actually govern
The criteria set, edition and plan terms in force for that member, service and date of service — read at review time and stamped with the date.
01Approved path
Take the search off the reviewer
The record is read, the criteria are matched and each finding is cited before a reviewer opens the case, so the reviewer reads rather than hunts.
02Human review
Show the gaps as gaps
A criterion with nothing behind it in the record is named unevidenced and put in front of a clinician — never scored, ranked or handed over as a reason to deny.
04Build an evidence trail
Retain the criteria version, the record read, the evidence cited, the reviewer's own rationale and the appeal outcome — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
UM platform & case fileEpic Payer Platform · GuidingCare Jiva · UM case and queue APIs
Criteria & medical policyInterQual · MCG Medicare NCD and LCD · plan medical policy
Clinical record exchangeEpic · Oracle Health · C-CDA and FHIR Provider portal · attachments
Agent
Utilisation & medical-necessity review
Pins criteria Locates evidence Hands to reviewer
Claims, benefits & appealsCore claims · eligibility and benefits Appeals and grievances · member notices
Aggregate retrieval recall and reviewer agreement can look acceptable while a few payer-class and service-line cohorts carry most of the missed evidence — and those are the cohorts least likely to appeal anything. 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
Medicaid and dual-eligible members
5.9%
3.6×
Review
Behavioural-health requests
4.6%
2.8×
Review
Interpreter-required records
3.2%
1.9×
Watch
Repeat in-network requests
1.2%
0.7×
Normal
Bar: missed-evidence lift vs. routine in-network baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
An overturn on appeal is a finding about the summary
When an appeal goes the member's way, the evidence was usually in the record that day. That belongs in the evaluation of the summary handed over.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Retrieval recall, reviewer agreement or overturn rate moves in one slice.
02Diagnose
Traced to the criteria edition, the retrieval, the marking or the wording.
03Improve
The source, retrieval or summary format is changed, re-approved by the medical director and version-linked.
04Verify
Re-run against held-out cases, including every one overturned on appeal.
05Learn
The overturned case becomes a regression case with the missed evidence marked.
Learn → DetectThe return edge. Every cycle also checks what reviewers actually opened — a summary good enough to stop them reading the record is a defect, not a result.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, criteria and plan-term sourcing, retrieval and summarisation, evaluation, reviewer workflow, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02Criteria, edition and plan-term sourcing.
03UM platform and record-exchange APIs.
04Date-of-service criteria and version pinning.
05Minimum-necessary retrieval scoping.
06Evidence location and citation per criterion.
07Summary format sign-off with clinicians.
08Approval-path rules and the no-determination constraint.
09Nurse and medical-director review workflow.
10Recall, agreement and equity-slice evaluation.
11Peer-to-peer and appeal packet assembly.
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 plan, one service lineProductionProduction UM integrationAdvancedMulti-plan / multi-line
Introduced at Pilot
Criteria and plan-term lookup✓✓✓
Evidence location and citation✓✓✓
Structured reviewer summary✓✓✓
Clinician determination gate✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Date-of-service version pinning—✓✓
Concurrent and continued-stay review—✓✓
Reviewer agreement and read-through tracking—✓✓
Observability and audit trail—✓✓
Introduced at Advanced
Peer-to-peer and appeal preparation——✓
Multi-plan and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the plans and service lines in scope, criteria licences and editions, UM platform and record-exchange integrations, review volume, reviewer workflow 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
01The plans, service lines and review types in scope→Workflow discovery and automation-boundary definitionWeek 1
02Your criteria licences and the editions you apply→Criteria, edition and plan-term sourcing, pinned to date of serviceWeek 2
03Access to the UM platform and clinical-record exchange→Epic Payer Platform or GuidingCare, and C-CDA record exchangeWeek 2
04Minimum-necessary and release-of-information rules→Record retrieval scoping and disclosure limitsWeek 3
05Real cases, including the ones overturned on appeal→Evaluation suite, regression cases and failure-mode testingWeek 4
06Named nurse reviewers and a medical director→Reviewer workflow, summary format and agreement trackingWeek 4
07Your written policy on who may issue a denial→Approval-path rules, the clinician gate and the audit trailWeeks 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. The overlap in week 5 is where reviewer agreement is measured on the first live summaries.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Plans and review types in scope; who may issue a denialW2Criteria licences, editions and plan terms pinned to date of serviceW3Record retrieval, evidence citation and the summary formatW4Reviewer workflow, evaluation suite, equity slices and failure-mode testingW5First live summaries, reviewer-agreement measurement and correctionsW6Reviewers decide live cases from agent summaries, then handover
Reading the bandReviewer agreement in week 5 is measured on live cases, not a retrospective sample. Each bar covers its own weeks only.
At the end of W6Reviewers have decided live cases from agent summaries, and every adverse determination in that period was issued by a clinician.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Healthcare AI agent
Build a utilisation-review agent around the reviewers you already have.
Show us the criteria sets you licence, how a request reaches a reviewer, and who may issue an adverse determination. We'll assemble one case as a reviewer would want it, and agree what it may never say.
