Skip to content
TRESTL

From the claim file to your examiner’s decision, in one place.

Trestl reviews each claim against the member’s plan before payment, shows your examiners the reason for every finding, and exchanges data with the systems you already run.

Prepayment review

Claims are checked against the member’s plan before your payment run, for Hospital Indemnity, Accident and the Critical Illness benefits configured for your plans.

Matches the plan
Pays on schedule, with nothing for your examiners to do.
Doesn’t match
Waits for your examiners, with the reason, before any money goes out.
Both directions
Underpayments are flagged as well as overpayments, so members receive what the plan promises.

Every finding shows its reason.

An examiner sees why a claim was held, what the plan pays, and the evidence, and decides in a few clicks.

An example with made-up figures. Your examiner chooses; Trestl records the decision.
The reason, in plain words
Which term of the member’s plan the claim doesn’t match, not an opaque score.
What the plan pays
Where the amount is in question, the amount the plan pays next to the amount on the claim.
The evidence
The claim history and the plan, and, where relevant, the documents an AI-assisted review compared.
The decision trail
Who reviewed it, what they decided and when, written to the audit ledger.

Your team decides.

Findings land in a queue organized by product and assignment. Analysts decide and move on; managers see the workload across the team.

Role-based access
Analysts, managers and client users each see their own scope. Client users only ever see their organization’s claims.
Assignment and workload
Claims are distributed to analysts by product, with queue and workload views for managers.
AI assists; people decide
AI-assisted reviews of accident reports and clinical documents raise items for review. They never deny a claim.
A complete audit trail
Views of claims data and every decision are recorded in an append-only, hash-chained ledger.

Connect the way you already move claims.

Each client environment gets its own connectors: claims, members and plans in, results out. Two routes, agreed for your environment.

SFTP
Trestl collects files from your SFTP server on the agreed schedule and writes results back to an agreed folder.
Your API
Trestl polls your API with authenticated requests and returns the results to it, as CSV or JSON.

The route, file contract, schedule and acceptance tests are agreed for your environment during implementation, and validated with a representative file before any live data is sent.

A workspace for claims that were already paid

Some questions only surface after payment. Investigators work cases with the same claim history and audit trail, with workload management and recovery tracking.

Case workload
Open investigations organized by status and owner, per client.
Historical diagnostics
A bounded review of paid claims under an agreed scope, reported with the checks completed and any data gaps.
Recovery tracking
Outcomes recorded separately: a finding, an accepted correction, and a confirmed payment outcome.
Same controls
The tenant isolation, access control, and audit trail that protect prepayment review.

For your team.

  • Claims operations

    Findings arrive with their reason, and examiners decide in the queue or in your own system.

    Your team decides
  • Finance

    Findings, accepted corrections and confirmed payment outcomes are reported as separate measures.

    How results are measured
  • Security and compliance

    A BAA, a platform hosted in the US, encryption, tenant isolation and an audit trail.

    Security and trust
  • TPAs

    Trestl works beside your adjudication system: results come back the way claims arrive.

    Exchange

The integration overview, to forward (PDF)

Frequently asked questions

Can Trestl flag underpayments?
Yes. Amount checks compare the paid amount with the amount the plan schedule produces and flag differences in either direction.
Do we have to use the Trestl review workspace?
No. Findings can be reviewed in the Trestl workspace or returned to your adjudication system or TPA through the exchange, depending on how you want your analysts to work.
How are AI-assisted checks governed?
They run on Google Cloud Vertex AI inside our Google Cloud business associate agreement, return structured results, and only ever raise items for human review. If the AI service is unavailable, the check does not fire rather than guessing.
Can you build checks for our specific plans?
Yes. We read your certificates of coverage and set up the checks from their terms. If a certificate has a provision our standard checks don't cover, we build a check for it, even if your plans are the only ones that use it. Each check is tested with your team, on sample or historical claims or in a shadow review, before you rely on its findings for live claims.

Start with a conversation about your book, the claim decisions that need attention, and who owns them. We will show the platform on synthetic data and agree whether a scoped review makes sense.