{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-18T13:45:35.999Z",
  "record_id": "VXI-EXT-PROCUREMENT-BEDROCK-DATASOURCE-EXIT-01-v1",
  "record_kind": "external_reference",
  "title": "Bedrock: Deleting a data source can retain indexed data",
  "system": "Amazon Bedrock Knowledge Bases",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does deleting a Bedrock knowledge-base data source remove its vector data and store?",
  "near_questions": [
    "What remains after deleting a Bedrock data source?",
    "Does RETAIN preserve the indexed vectors during offboarding?",
    "Does Bedrock DELETE also remove the vector store?",
    "What does DELETE_UNSUCCESSFUL mean for AI data exit?",
    "Which failureReasons must be resolved before closure?",
    "How do we verify the data-source deletion policy?",
    "Can deleting the knowledge base leave its store in place?",
    "What evidence covers derived vectors after connector removal?",
    "Which separately managed storage remains in the exit inventory?",
    "Can a deletion request alone prove Bedrock data cleanup?",
    "How should an owner reconcile retained AI retrieval data?",
    "What prevents us from closing this Bedrock offboarding review?"
  ],
  "supported_claims": [
    {
      "claim": "Bedrock documents separate DELETE and RETAIN data-deletion policies. RETAIN leaves the data; DELETE removes the data without deleting the vector store itself and can fail because of vector-store configuration or access. DELETE_UNSUCCESSFUL and failureReasons identify an unsuccessful deletion. Data-source removal alone does not establish complete exit cleanup.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Verified buyer configuration, actual data erasure, effective access or completed business actions",
    "Legal advice, compliance determination, vendor certification or safety assurance",
    "Runtime enforcement, permission to act or expanded licensed-checker coverage"
  ],
  "public_summary": "Bedrock documents separate DELETE and RETAIN data-deletion policies. RETAIN leaves the data; DELETE removes the data without deleting the vector store itself and can fail because of vector-store configuration or access. DELETE_UNSUCCESSFUL and failureReasons identify an unsuccessful deletion. Data-source removal alone does not establish complete exit cleanup.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "Amazon Bedrock: Delete a knowledge-base data source",
    "source_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/kb-ds-delete.html",
    "checked_on": "2026-10-18",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-BEDROCK-DATASOURCE-EXIT-01-v1",
    "candidate_record_sha256": "cfc0208cff271742739a0a025e905075d0c5f607d60d8e5ff103905c3858e622",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "Bedrock documents separate DELETE and RETAIN data-deletion policies. RETAIN leaves the data; DELETE removes the data without deleting the vector store itself and can fail because of vector-store configuration or access. DELETE_UNSUCCESSFUL and failureReasons identify an unsuccessful deletion. Data-source removal alone does not establish complete exit cleanup.",
    "required_buyer_context": "The knowledge base, data source, vector store and effective deletion policy. Deletion status and any failureReasons. Reconciliation of retained vectors, the store and other scoped copies. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "checked_on": "2026-10-18",
    "claim_to_check": "Does deleting a Bedrock knowledge-base data source remove its vector data and store?",
    "documented_statement": {
      "status": "documented",
      "statement": "Bedrock documents separate DELETE and RETAIN data-deletion policies. RETAIN leaves the data; DELETE removes the data without deleting the vector store itself and can fail because of vector-store configuration or access. DELETE_UNSUCCESSFUL and failureReasons identify an unsuccessful deletion. Data-source removal alone does not establish complete exit cleanup.",
      "source_ids": [
        "bedrock-delete"
      ]
    },
    "buyer_evidence_required": [
      "The knowledge base, data source, vector store and effective deletion policy.",
      "Deletion status and any failureReasons.",
      "Reconciliation of retained vectors, the store and other scoped copies."
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Do not mark AI data exit complete while the policy retains data, deletion has failed or the separately managed store remains outside the review."
    },
    "unknowns": "The buyer configuration, contract, effective entitlement and operational evidence have not been inspected. Missing evidence does not establish absence or failure of the feature.",
    "evidence_sources": [
      {
        "source_id": "bedrock-delete",
        "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/kb-ds-delete.html",
        "final_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/kb-ds-delete.html",
        "title": "Amazon Bedrock: Delete a knowledge-base data source",
        "checked_on": "2026-10-18",
        "captured_at_utc": "2026-10-18T13:33:51.897Z",
        "version_context": "Rolling Bedrock guide; DELETE and RETAIN policies",
        "sha256": "d941b79fd7742c4880812238911947c7f78550862955937acaa3a5a48530a4fb",
        "bytes": 16237,
        "hash_basis": "Decoded HTTP response body bytes; identifies captured content, not truth or certification",
        "reviewed_sections": [
          "Does deleting a Bedrock knowledge-base data source remove its vector data and store?"
        ]
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Procurement evidence support only; no supplier clearance, legal conclusion, configuration audit or verification of the buyer's claim is supplied.",
    "paid_value": {
      "decision_context": "A data owner ending an AI retrieval integration needs evidence for derived vectors and the separately managed store, not only the connector record.",
      "free": "Complete review, practical questions, sources and limitations; may be saved locally.",
      "single_request": "Existing server-saved version-bound route snapshot for later authenticated retrieval.",
      "evidence_receipt": "The same snapshot plus the existing unsigned delivery receipt.",
      "excluded": [
        "Fresh vendor research",
        "Continuous monitoring or change alerts",
        "Testing the buyer configuration",
        "Private evidence or vendor certification"
      ],
      "integrity": "Hashes identify content versions; they do not prove truth or provide a signature."
    },
    "revalidation": {
      "trigger": "A saved purchase does not recheck the source or buyer configuration.",
      "specific_watch": "The knowledge base, data source, vector store and effective deletion policy. Deletion status and any failureReasons. Reconciliation of retained vectors, the store and other scoped copies."
    },
    "buyer_relevance": "A data owner ending an AI retrieval integration needs evidence for derived vectors and the separately managed store, not only the connector record.",
    "refusal_conditions": [
      "Do not mark AI data exit complete while the policy retains data, deletion has failed or the separately managed store remains outside the review."
    ]
  },
  "niche": {
    "label": "Enterprise AI Data Custody & Exit Assurance",
    "niche_id": "enterprise-ai-data-custody-exit-assurance",
    "topic_id": "enterprise-ai-custody",
    "buyer_intent": "A data owner ending an AI retrieval integration needs evidence for derived vectors and the separately managed store, not only the connector record."
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#bedrock-data-source-delete-retained-vector-boundary",
  "machine_readable_record": "/varexis-index/records/bedrock-data-source-delete-retained-vector-boundary.json"
}
