Sample · Walkthrough
STYLIZED · DEMO DATA

A single signed record, walked end to end

What your auditor actually reads.One prior-auth decision — patient, model, score, chain, notes.

Below is a stylized walkthrough of the artifact a regulated buyer receives when they hand a single coverage decision to their auditor. Patient identifier, model version, the score at the moment it escalated, the tamper-evident chain of every preceding evaluation run, and the reviewer annotations that closed the audit packet. The data is fictional; the shape is the production shape.

Quick read

Explain this simply

Four parts of the same evidence trail, from decision to sign-off.

  1. Start with one coverage decision.

    The walkthrough opens with a fictional prior-auth request that the model sent for manual review, then shows the case details and decision inputs. Read the case details → See the decision inputs →

  2. Follow the evidence backward.

    Five preceding evaluation runs are linked into one history, so a buyer can walk back through the provenance of the escalation. Read the chain details →

  3. See how review closes the record.

    Timestamped notes show the scoped roles that annotated the path from escalation to sign-off. Read the reviewer notes →

Show me the technical walkthrough →

§01 · The case

A prior-auth hits ESCALATE. 08:14 AM, Tuesday.

The coverage-decision model flagged a request for manual review at 08:14 AM Eastern on Tuesday morning. The card below is the case header — the row of metadata that opens every record on the chain. Patient identifier (fictional), the decision kind, the timestamp, and the scope of roles that can read this row.

CASE · streaming

Loading case header…

§02 · The decision

The model said ESCALATE. Four numbers tell you why.

The decision artifact is the row the buyer reads first. Every value that drove the verdict — model id and version, the three evaluators that ran inline, the score at the moment the decision was committed, the escalate-and-throw thresholds it crossed, and the rationale that drove the manual review.

A throw rate of 0.138 exceeded the configured ceiling of 0.120. The clinical-coverage rubric flagged the request as off-label coverage. The review path is medical-director sign-off — the same path the production record would carry.

§03 · The chain

The provenance walks back. Five runs, every one chained.

Every row in the table below is a preceding evaluation run that fed the system up to the 08:14 AM escalation. Each row's prev_hashpoints back to the row directly below it — the row that produced that hash. The bottommost row is the chain's genesis (no predecessor). A buyer walks the page top to bottom and reads the provenance as one connected history.

LEDGER · streaming

Loading chain…

§04 · The annotations

Who annotated the record — and when.

Three reviewer notes captured the path from escalation to sign-off. Each was authored under a scoped role — medical-director, compliance-audit, care-manager — and each timestamp sits on the same claim as its author's scope. The audit packet these notes contribute to is reproducible from the chain itself.

NOTES · streaming

Loading reviewer notes…

§05 · Next

Walk your own record the same way.

Join the waitlist for single-practitioner early access, or talk to Enterprise for a BAA path and a co-written scope. Both routes take ten minutes; the audit walk-back is shaped on the same surface. Working an outside-counsel or AI-vendor-diligence matter? Walk the counsel diligence Q&A →

Download · Buyer brief
Healthcare · prior auth
See the audit path as one case, not four disconnected tools.
Get the one-page case study for a fictional mid-market healthcare network using Plumbline to capture, evaluate, review, and replay prior-authorization decisions.

Four moments the buyer can replay

  1. 01CaptureThe request lands with its context and scope.
  2. 02Evaluate / escalateScores and thresholds explain the manual-review path.
  3. 03ReviewNotes and sign-off stay attached to the decision.
  4. 04Replay / exportThe chain and signed evidence travel together.

Unlock the PDF

Leave an email for the next-step note, then the download appears here.

Fictional demo data only: Patient-7421 is not a real patient or PHI. The full walkthrough lives at /sample-evidence.