Auditario’s evidence-first 3PL invoice audit methodology
Auditario connects each evaluated charge to its governing source, exact calculation, evidence state, and unresolved blockers. This page explains how a billing candidate is classified, how AI is constrained, and why incomplete proof keeps the claimable result at zero.
Published by Auditario · Methodology version 1 · Updated 14 August 2026
How the method limits a conclusion
A numeric difference is only a candidate. It becomes externally supportable only when the governing documents, billed event, operational inputs, exact arithmetic, source integrity, dispute window, innocent explanations, and certification policy all agree.
The evidence behind the current method is documented separately so this page can remain the decision policy. Inspect the named public sources, full hashes, synthetic layout fixtures, regression lessons, and limits, or read how Auditario researches and corrects public material.
The target three-source evidence model
The target complete audit compares three evidence sources. Current founding audits do not yet include the third:
- What you agreed to pay — your rate card, MSA, amendments, and any written concessions from your provider, in strict order of precedence (a signed amendment beats the original rate card; a document always beats an AI's interpretation).
- What you were billed — supported invoice lines normalized into standard charge categories and traced to their available page, row, or cell citation; unsupported evidence is reported as a coverage gap.
- What actually happened (planned) — Shopify orders, fulfillments, cancellations, and returns. This connector is not built yet, so current founding audits do not claim this coverage.
What “claim-ready” means — and what it doesn't
Auditario keeps evidence, dispatch, and automation as separate states. A detector can be mathematically confident while the merchant-facing result still requires review:
| Class | Meaning |
|---|---|
| Claim-ready | Every required proof is present, independently recomputed, source-bound, inside an established dispute window, and certified for that exact check, provider, and parser layout. Only this state can enter claimable totals. |
| Review required | The engine observed a possible variance, but at least one proof is unresolved. We show the arithmetic and blocker, and claim $0. |
| Optimization | A contractually valid charge you could reduce by changing process, packaging, or terms. Real money, but not an error. |
| In your 3PL's favor | Underbilling. Yes, we report it. An audit that only ever finds errors in one direction isn't an audit. |
| Data quality | The sources conflict or are incomplete, so no reliable conclusion exists. We say so instead of guessing. |
How AI is constrained — and what is not live yet
AI can help read messy documents, but it cannot be the authority for money. The boundary is explicit:
- AI may extract; it cannot decide money. A model may transcribe a printed rate or suggest a category into a strict schema. It cannot calculate a variance, determine that money is owed, or upgrade a publication state.
- Deterministic code does all the math. Expected charges and deltas are computed by exact, repeatable arithmetic from cited structured inputs. Some checks, such as a missing promised credit, have no billed line and therefore require their own explicit evidence.
- Unresolved innocent explanations block publication. The claim-ready policy requires the governing clause, amendments, billing lag, reversals and other plausible explanations to be resolved. Automated model refutation is not connected to a live Phase 1A processing route; it exists only as an injected, recorded-fixture source foundation, so its status is
NOT_RUNand positive candidates remain review-only. - Ambiguity goes to you, not to a guess. If your contract could mean two things and the difference is worth real money, we ask you one specific question — and your answer is versioned and reused forever.
Why “flagged” and “recovered” are different numbers
Auditario keeps the full journey separate: observation → review required → claim-ready → merchant approved → disputed → acknowledged by the provider → credited on an actual invoice. Claim-ready never implies merchant approval or AutoPilot authority. Planned pricing is flat rather than recovery-based, and the recovery ledger counts only credits that verifiably landed.
Dispute windows: the clock your contract started
A governing agreement may impose a provider-specific deadline for disputing an invoice. When the clause and anchor date are established, the engine records whether the window is open or expired. Missing or unsupported terms remain window unknown and can never enter claim-ready money.
What happens when we find nothing
The planned reconciliation statement reports how many lines were evaluated, the rate-card version used, covered spend, and unresolved evidence. It is not a guarantee, attestation, or statement that all billing is correct.
Your data
- This prelaunch site accepts waitlist contact details only; document upload is not open.
- Production intake remains disabled until encryption, tenant access control, retention/deletion, DPA, and security tests pass.
- Shopify access is planned as read-only and minimal; it is not implemented or available today.
- One-click export and deletion workflows are release requirements, not current capabilities.
Put the methodology to work
The methodology is the decision layer behind a practical review. Start with the step-by-step 3PL invoice audit guide, use the printable audit checklist, compare evidence requirements in the billing-error library, or inspect the synthetic sample report.