Illustrative walkthrough using seeded data. Product capabilities are marked Built or Planned.
NOTARY AI
Screen 04[BUILT]

Prior-auth PA-8843 auto-denied despite high-risk note

Healthcare Prior-Auth · CMS medical necessity / utilization management — one entry in Company XYZ's versioned library of : preserved decision conditions paired with an Authorized Expected Behavior, reused on every future candidate version.
Company XYZ decision accountability · LoanCore Underwriting 3.2.0Healthcare Prior-Auth · PA-8843Representative lending boundary case
  1. ACCOUNT13
  2. VERIFY47
  3. DEFEND89
  1. Connect
  2. Landscape
  3. Readiness
  4. 4Scenarios
  5. 5Authorize
  6. 6Verify
  7. 7Release
  8. 8Package
  9. 9Hand-off
VERIFYScreen 04
Question
Which decision conditions must future versions continue to handle correctly?
Answer
Company XYZ has preserved representative, boundary, disputed, and previously failed decisions as reusable Assurance Scenarios.
Output
A versioned library of decision conditions with authorized expected outcomes.
Fault attribution · Rule failure

A rigid deterministic gate denied a case the underlying model would have passed.

Decision chain

[BUILT]captured evidence
INPUT
Auth request
CPT 78452, high_risk_note=true
TOOL
Criteria bundle v2
InterQual mapping (subset)
MODEL
Necessity classifier
Score 0.42 — below threshold
RULE
Failing or uncertain node
Auto-deny gate
score<0.5 → DENY without human review
DECISION
Denial issued
Letter sent to member and provider
Why this case is useful for release assurance
source_decision
PA-8843, cardiac stress imaging
trigger
96 auto-determinations missing human-review evidence
failing_node
Auto-deny gate
evidence_level
E4
replayability
Replay-ready from the sealed cassette
missing_evidence
Appeal outcome not captured; the source system does not emit appeal records yet.
applicable_policy
Utilization Management Policy 7.1 (2026-04)
expected_behavior
Authorized by Clinical Compliance / UM — Dr. Elena Voss
suggested_preservation
Preserve decision-time policy version and human-review evidence on the next occurrence
suggested_scenario
Add to the Healthcare Prior-Auth Release Scenario set as a policy-derived case
Candidate provenance
evaluator
company-xyz-evaluator v0.6.2
frozen_input_set
healthcare-prior-auth-sweep-2026-07
evaluated_at
2026-07-22T04:15:00Z
source_evidence
sha256:6b41…c02e
relationship_confidence
Confirmed — decision and adverse-action record share a source identifier
known_limitations
Does not include appeals data; advisory only.
Captured decision
PA-8843, cardiac stress imaging
Outcome
AUTO-DENIED
reason: criteria_bundle_v2 missed 'high_risk_note=true'
Authorized Expected Behavior
Route to clinician review whenever high_risk_note is set.
Evidence
E4sufficient for verification
cassette · sha256:6b41…c02e
Next action

Advisory only. An must define or approve the expected behavior before a candidate version can be verified against it.

→ Authorize expected behavior
Screen anatomy

What this screen proves

For any single decision case, Notary AI can show which nodes ran, which node is failing or uncertain, what was captured, what evidence is missing, and what the record is at.

Why it matters

This is how a case earns a place in the release-assurance suite. A useful case has preserved evidence, a known applicable policy, and a clear expected behavior worth testing every future candidate version against.

Built or Planned

Planned capability for candidate generation; the decision-chain view and evidence grading are built. Candidates shown here are a seeded illustration.

Important boundary

The candidate is advisory. Notary AI does not determine what the acceptable outcome should be — an supplies the Authorized Expected Behavior on Screen 05, and the re-checks eligibility server-side.

Related requirements

Next

A scenario preserves the conditions, but it cannot decide what outcome is acceptable. An authorized Company XYZ reviewer must establish that.

Authorized Behavior