{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-30T18:53:33.881Z",
  "record_id": "VXI-EXT-ICE10-AGENTCORE-LONGTERM-RETENTION-PRUNER-01-v1",
  "record_kind": "external_reference",
  "title": "Long-term expiry requires deployed/executed timestamp-based pruner in reviewed design, distinct from DeleteEvent-derived residue",
  "system": "Amazon Web Services",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does a configured memory age prove AgentCore long-term records expire automatically?",
  "near_questions": [
    "Does a long-term AgentCore memory TTL policy execute deletion by itself?",
    "What evidence shows the AgentCore memory pruner actually ran?",
    "Can short-term event expiry establish long-term memory retention compliance?",
    "What separates a memory age rule from its pruning workflow?"
  ],
  "supported_claims": [
    {
      "claim": "The reviewed AWS lifecycle design implements timestamp-filtered pruning in a separate workflow and states that AgentCore memory lacks a built-in auto-delete TTL in that design context.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
    "Buyer implementation, live runtime enforcement, settled payment, verified deletion or certification are not established.",
    "No expanded capabilities or licences for existing INDEX executables."
  ],
  "public_summary": "The reviewed AWS lifecycle design implements timestamp-filtered pruning in a separate workflow and states that AgentCore memory lacks a built-in auto-delete TTL in that design context.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "Amazon Web Services primary documentation: aws memory lifecycle",
    "source_url": "https://aws.amazon.com/blogs/machine-learning/designing-lifecycle-policies-for-agentcore-memory/",
    "checked_on": "2026-10-30",
    "candidate_record_id": "VXI-EXT-ICE10-AGENTCORE-LONGTERM-RETENTION-PRUNER-01-v1",
    "candidate_record_sha256": "46dc28c4d6d88f967ba502870e13e98e7425ca0856588ae92a5f51005399d630",
    "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": "The reviewed AWS lifecycle design implements timestamp-filtered pruning in a separate workflow and states that AgentCore memory lacks a built-in auto-delete TTL in that design context.",
    "required_buyer_context": "memory class; configured policy; scheduler/workflow; record timestamps; deletion/reconciliation results. 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",
    "applicability_status": "Primary rolling documentation captured 2026-10-30; runtime/version applicability must be checked before reliance. No buyer deployment was inspected.",
    "checked_on": "2026-10-30",
    "claim_to_check": "Does a configured memory age prove AgentCore long-term records expire automatically?",
    "documented_statement": {
      "status": "documented",
      "statement": "The reviewed AWS lifecycle design implements timestamp-filtered pruning in a separate workflow and states that AgentCore memory lacks a built-in auto-delete TTL in that design context.",
      "source_ids": [
        "aws-memory-lifecycle"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "Does a configured memory age prove AgentCore long-term records expire automatically? A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence. Long-term expiry requires deployed/executed timestamp-based pruner in reviewed design, distinct from DeleteEvent-derived residue. The decision turns on the documented operation and required evidence, not on a different vendor name. This is an operational review inference, not an observed deployment outcome.",
      "source_ids": [
        "aws-memory-lifecycle"
      ]
    },
    "buyer_evidence_required": [
      "memory class",
      "configured policy",
      "scheduler/workflow",
      "record timestamps",
      "deletion/reconciliation results"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence."
    },
    "unknowns": "The buyer implementation, effective authority, source-data completeness and actual business outcomes were not inspected.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "No buyer deployment or transaction was observed."
    },
    "evidence_sources": [
      {
        "source_id": "aws-memory-lifecycle",
        "url": "https://aws.amazon.com/blogs/machine-learning/designing-lifecycle-policies-for-agentcore-memory/",
        "final_url": "https://aws.amazon.com/blogs/machine-learning/designing-lifecycle-policies-for-agentcore-memory/",
        "captured_at_utc": "2026-10-30T18:22:06.360586+00:00",
        "status": 200,
        "content_type": "text/html;charset=UTF-8",
        "bytes": 1465702,
        "sha256": "317cb423a95b0f0ecf16ac2d86e70fbe7abfabff8afe092ac9f9e4cf1224cc86",
        "title": "Amazon Web Services primary documentation: aws memory lifecycle",
        "publisher": "Amazon Web Services",
        "checked_on": "2026-10-30",
        "capture_status": 200,
        "claim_review_completed": true,
        "hash_basis": "SHA-256 of captured HTTP response-body bytes; not a signature or factual guarantee.",
        "version_context": "Rolling primary documentation captured 2026-10-30. The capture pins source bytes, not a provider runtime release; verify the installed version and configuration.",
        "rights_disposition": "Original bounded paraphrase with source attribution. Captured source body remains private; no source-body redistribution. Vendor documentation rights, code licences and marks are not transferred.",
        "reviewed_sections": [
          "doesn’t provide a built-in auto-delete TTL"
        ]
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Documentation supports only the stated boundary. Existing licensed checkers analyse supported supplied declarations locally; they do not inspect provider accounts, verify live behaviour, enforce decisions or certify compliance.",
    "paid_value": {
      "decision_context": "Does a configured memory age prove AgentCore long-term records expire automatically? A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
      "free": "Complete source review, questions, provenance and limitations; free to read and save locally.",
      "single_request": "Unavailable for this publication-only record; historical saved retrieval is unchanged.",
      "evidence_receipt": "Unavailable for this publication-only record; no paid retrieval entitlement is added.",
      "excluded": [
        "Fresh source research",
        "Native provider integration or schema support",
        "Live inspection or runtime enforcement",
        "Payment settlement or verified deletion",
        "Certification or expanded licences"
      ],
      "integrity": "Hashes identify content versions; they do not prove factual truth or provide a signature."
    },
    "revalidation": {
      "trigger": "Recheck current primary documentation and the applicable API, service, account and configuration before reliance. No ongoing monitoring is included.",
      "specific_watch": "doesn’t provide a built-in auto-delete TTL"
    },
    "buyer_relevance": "Does a configured memory age prove AgentCore long-term records expire automatically? A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
    "refusal_conditions": [
      "A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
      "Do not infer deployment conformance, authority or successful outcomes from source documentation."
    ],
    "decision_context": {
      "operator": "Memory custody reviewer",
      "scenario": "Does a configured memory age prove AgentCore long-term records expire automatically?",
      "consequence": "A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
      "confidence": "Primary documentation supports the narrow stated distinction; deployment conformance and purchase demand remain unestablished."
    },
    "novelty_review": {
      "candidate_id": "ICE10-B04",
      "disposition": "distinct_operational_decision",
      "nearest_record_id": "VXI-EXT-PROCUREMENT-AGENTCORE-EVENT-DELETE-DERIVED-MEMORY-RESIDUE-01-v1",
      "nearest_record_url": "/varexis-index/records/agentcore-event-delete-derived-memory-residue.json",
      "nearest_record_sha256": "240ae602db6e63a80b00e3ac83e9f384479e7a89b7dc19679e92a20ea1f579b4",
      "material_distinction": "Long-term expiry requires deployed/executed timestamp-based pruner in reviewed design, distinct from DeleteEvent-derived residue. The decision turns on the documented operation and required evidence, not on a different vendor name.",
      "review_status": "PASS: source qualification plus independent reviewer challenge and resolved corrections"
    },
    "optional_selection": {
      "guide_id": null,
      "guide_url": null,
      "guide_manifest": "/varexis-index/decision-guides.json",
      "checker": {
        "product_id": "agent-data-exit",
        "price_gbp_excluding_vat": 79,
        "purchase_url": "/index-access?route=agentic_pack_data_exit_v1",
        "licence_scope": "Existing separate internal-use licence; subscriptions do not include the executable.",
        "benefit": "Optional local analysis of supported supplied declarations only; no native provider integration or verification is added."
      },
      "boundary": "The existing checker does not connect to this platform or execute these review worksheets. Use it only for its already-supported supplied declaration schema and separate licence."
    },
    "exact_access": {
      "endpoint": "/mcp/catalogue",
      "tool": "get_publication_record",
      "arguments": {
        "record_id": "VXI-EXT-ICE10-AGENTCORE-LONGTERM-RETENTION-PRUNER-01-v1"
      },
      "record_url": "/varexis-index/records/agentcore-longterm-retention-pruner.json",
      "original_mcp_search": false,
      "paid_saved_retrieval": false
    }
  },
  "niche": {
    "niche_id": "ice10-custody",
    "label": "AI Data Custody, Retention & Exit Assurance",
    "classification_id": "custody",
    "classification_label": "AI Data Custody, Retention & Exit Assurance",
    "topic_id": "custody",
    "buyer_intent": "Does a configured memory age prove AgentCore long-term records expire automatically? A proposed TTL or event expiry is not proof that the long-term pruner ran; require its scope, execution and deletion evidence.",
    "comparison_role": "supplementary_discovery"
  },
  "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#agentcore-longterm-retention-pruner",
  "machine_readable_record": "/varexis-index/records/agentcore-longterm-retention-pruner.json"
}
