Retrieval Architecture for Insurance Claims Intake — Access Rules That Hold Up A developer outlined a staged retrieval architecture for insurance claims intake that defines a retrieval contract—retrieval units, metadata filters, freshness rules, and traceable evidence—before selecting a vector store. The design splits data into explicit collections (policy-clauses, claim-events, repair-guides) and enforces access boundaries through query-level filters rather than UI hints, with a sample TypeScript client showing bounded retries against an Infrai vector query endpoint. Short answer: use staged retrieval with explicit collections, bounded queries, and source context you can trace back to the claim record. Pick the vector store only after writing that retrieval contract. It keeps index cost visible as the corpus grows and stops an intake assistant from treating a plausible paragraph as proof. Start with the answer a claims adjuster must see, not with an embedding model. A coverage question needs policy language, endorsements, and the policy version in force on the loss date. A status question needs claim events and timestamps. Those are different retrieval units, freshness rules, and access rules, so they should not be one undifferentiated collection. I write the contract before choosing an endpoint: | Contract field | Example for claims intake | Why it controls cost | |---|---|---| | Retrieval unit | One clause or one dated claim event | Smaller units increase candidates; oversized chunks waste rerank budget | | Metadata filter | tenant id , policy id , claim id , effective from | Filtering early avoids scanning irrelevant vectors | | Freshness | New claim events available within minutes; policy text changes versioned | Frequent writes raise indexing and storage work | | Evidence | Record ID, page, version, and excerpt | Auditable context prevents unsupported answers | That contract also defines the access boundary. A claimant can retrieve documents for their claim; an adjuster may retrieve the policy and related endorsements; a supervisor can see the audit trail. The filter is part of the query, not a UI hint. That boundary is the design. Infrai fits this early stage when the intake service will also call other backend capabilities and you want breadth behind one plain REST surface. One key and one consistent contract remove a class of SDK and credential glue while you are still testing collections; they do not decide your chunk size or access policy for you. Keep collections explicit: policy-clauses , claim-events , and repair-guides are easier to reason about than a single everything index. The trade-off is operational overhead. Three collections mean three ingestion paths and more monitoring. The catch is that a single mixed index can look cheaper until noisy neighbors force larger top-k values and more downstream filtering. The first useful result should be observable in one terminal session. I use one API client, one bounded query, and preserve the returned source context alongside the generated answer. The payload shape belongs to the collection contract, so the function accepts it rather than inventing fields that the service has not documented here. js type QueryPayload = Record