/ source freshness / evidence expiry / supplier review
Building an Evidence Expiry Table
How to track which supplier evidence expires by date, event, order value, or business change.
Supplier evidence does not age at one speed. Certificates expire by date. Bank confirmation can expire when the account changes. Contact verification can expire when staff changes. Production evidence can expire when the buyer changes product scope or the supplier moves site. A single last reviewed date is too blunt for serious review work. Teams need an evidence expiry table.
The table should list field, source, last checked date, expiry rule, owner, and next trigger. Legal identity may refresh on a schedule or when a new entity appears. Payment route should refresh on every new beneficiary, domain change, or higher-value order. Product certificates should refresh by expiry date and by model change. Screening may refresh when names, owners, destinations, or product risks change.
AI can populate the first draft by reading case files and extracting dates, document types, and field names. The reviewer should set the expiry rule. A model can see that a certificate expires in December, but it may not know that a new battery configuration invalidates the old product evidence. Business context decides the rule.
Expiry tables help repeat orders. The buyer can see which fields remain current and which require a fresh check. This prevents two bad habits: starting from zero every time and trusting old evidence too long. The table turns memory into an operating record. It also gives reviewers a reason when they ask suppliers for updates.
The final case note should mention expiry when it shapes the decision. Bank beneficiary refreshed because order value exceeded threshold. Certificate still current by date but product model changed; scope review reopened. Public source not refreshed for low-value reorder; refresh required before bulk deposit. These notes keep freshness from becoming an invisible assumption.
The reviewer should start with the document or record behind the claim. Show the extracted field, source date, source channel, and the reason the field matters to the supplier decision. That first view keeps source freshness close to the file instead of letting a model summary set the tone too early.
The practical test is whether the file supports the claim: How to track which supplier evidence expires by date, event, order value, or business change. If the file cannot support it, say so. A missing source, unclear scan, stale record, or unsupported relationship changes whether a buyer can rely on the output before payment, onboarding, shipment release, or a repeat order.
A solid case file captures the exact value under review, the document where it appeared, the page or image location, the capture date, and the reviewer status. If the case involves names, keep the original legal name beside any translation. If it involves payment, place the beneficiary and invoice issuer side by side. If it involves certificates or product claims, separate holder, scope, date, and product model.
The reason for this structure is practical. AI can shorten reading time, but it can also hide weak evidence when the output is too polished. A field table makes the weak spots visible: unreadable text, missing source labels, conflicting names, expired documents, vague product scope, unsupported payment routes, or source data that has not been refreshed for the current order.
AI should prepare the review by extracting fields, grouping related evidence, and pointing to conflicts. It should not close a case by itself when the outcome affects money, supplier approval, regulated product claims, or legal identity. The system should make a short request list for the supplier or analyst, then leave final clearance to a named reviewer when the file contains a hard trigger.
A good output uses action language. It can say request a cleaner license image, confirm the bank beneficiary through a second channel, ask which entity owns the certificate, refresh the public source, or hold the case until the production address is explained. These instructions are more useful than a raw confidence number because they tell the buyer what to do next.
Human review should be required when the case touches critical identity, payment, or product evidence. Triggers include a different legal entity, an unreadable registration field, a third-party bank account, a certificate holder that differs from the seller, a source older than the team's freshness rule, or a supplier explanation that exists only in chat. These cases may still be acceptable, but the acceptance needs a record.
The reviewer note should not be long. It should name the conflict, the evidence received, the explanation accepted or rejected, and the next action. For example: beneficiary differs from invoice issuer; authorization letter received and confirmed by known contact; payment cleared for this invoice only. That kind of note makes the AI workflow defensible later.
A case can mislead the team when the output is reduced to a clean score or short summary. A model can sound certain while the file remains thin. It can read text from a document that is not current, not complete, or not connected to the transaction. It can also treat a supplier-provided statement as verified source evidence unless the workflow keeps source categories visible.