{ "format": "agent-article-v0", "article_id": "EA-145", "canonical_url": "/tools/ea-145-servicenow-ai-agents", "page_type": "reference", "claim_ids": [], "evidence_ids": [ "EVD-EA-145-URL-BD70B8A3DB89", "EA-145-R11-RESEARCH", "EA-145-R11-WEB-READBACK" ], "unknown_ids": [ "EA-145-UNKNOWN-01", "EA-145-UNKNOWN-02", "EA-145-UNKNOWN-CURRENTNESS" ], "operational_object_ids": [], "provider": [], "models": [], "plans": [], "surfaces": [], "regions": [], "current_status": "UNKNOWN", "observation_status": "SPEC_ONLY", "freshness": "UNKNOWN", "last_verified": null, "supersedes": [], "superseded_by": [], "provenance": [ "COMM-044-EA0145", "SRC-EA-145-URL-BD70B8A3DB89", "WEBBODY-EA0145-R8-780517EC" ], "article_sources": [ { "id": "EVD-EA-145-URL-BD70B8A3DB89", "evidence_class": "RESEARCH", "title": "source_class=official product documentation; exact_title=AI Agent Studio overview; author/org=ServiceNow; canonical_url=", "href": "https://www.servicenow.com/docs/r/intelligent-experiences/ai-agent-studio.html", "supports": [], "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。", "origin_class": "SOURCE_PACKET_REFERENCE", "source_or_experiment_ids": [ "SRC-EA-145-URL-BD70B8A3DB89" ], "supporting_locators": [ "EVIDENCE_TABLE", "- source_class=official product documentation; exact_title=AI Agent Studio overview; author/org=ServiceNow; canonical_url=https://www.servicenow.com/docs/r/intelligent-experiences/ai-agent-studio.html" ], "scope": "EVIDENCE_TABLE", "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED" }, { "id": "EA-145-R11-RESEARCH", "evidence_class": "RESEARCH", "title": "EA-145 監査済みresearch / canonical revision binding", "supports": [ "- ESTABLISHED: ServiceNow公式DocsはAI Agent Studioをagent/agentic workflowの作成・管理・テスト・監視アプリとして記載し、version付きexecution logs、manual/automated test・evaluation、AI Guardian設定、analyticsを案内している。全機能にはServiceNow Otto AI Agentsのinstallが必要と記載し、live agent interactionのtestingはVirtual Agentを使う制限も明示している。\n- NOT_ESTABLISHED: Australia releaseのDocs記述は、他release・全tenant・全plan・全regionでの機能有効化、AI Guardianが全prompt injectionを阻止すること、analyticsが因果的ROIや安全率を証明すること、実業務での自律action安全性を確立しない。" ], "limit": "canonical監査・revision bindingの存在を示す。外部ソースcurrentnessが本文またはcontrol-planeで確定していない場合は、currentnessをUNKNOWNのまま保持する。", "origin_class": "AUDITED_CANONICAL_RESEARCH_PACKET", "source_or_experiment_ids": [ "COMM-044-EA0145" ], "supporting_locators": [ "COMM-044-EA0145", "EA-145-R5-LEGACY-MIGRATION-20261008-R1", "content/staging/EA-145.md" ], "scope": "監査済みEA本文・canonical revision・既存Source Graph relationの範囲。欠損currentnessは推測で閉じない。", "provenance_status": "AUDIT_PASS_CANONICAL_BINDING" }, { "id": "EA-145-R11-WEB-READBACK", "evidence_class": "IMPL", "title": "EA-145 Web body identity / canonical readback", "supports": [ "canonical staging bodyのSHA-256一致とR9 canonical ledger readbackをProduction projectionの入力として検証する。" ], "limit": "body identity/readbackは本文claim自体の真偽や外部ソースの最新性を追加保証しない。", "checked_at": null, "origin_class": "IMPLEMENTATION_READBACK", "source_or_experiment_ids": [ "WEBBODY-EA0145-R8-780517EC" ], "supporting_locators": [ "WEBBODY-EA0145-R8-780517EC", "content/staging/EA-145.md", "EA-145-R5-LEGACY-MIGRATION-20261008-R1" ], "scope": "R9/R10 canonical readback後のProduction生成時body identity。", "provenance_status": "CANONICAL_READBACK_BODY_HASH_MATCH" } ], "research_sections": [ { "heading": "WHY_THIS_MATTERS_TO_UPDATE", "text": "ServiceNowのAI Agent Studioを、AI agent/agentic workflowの作成・管理・テスト・監視・AI Guardian・analytics・release/role依存の組織overlayとして更新する。" }, { "heading": "SCOPE_ROUTING", "text": "organization overlay / provider mapping / governance / benchmark / security / audit / operability。Now Platform・Otto AI Agents・Virtual Agentを別availability gateで扱う。" }, { "heading": "CLAIM_OR_RESEARCH_QUESTION", "text": "ServiceNow公式Docsの現行releaseページがAI Agent Studioの作成・実行ログ・手動/自動評価・security control・analytics・前提インストールを何と記載しているか。" }, { "heading": "EVIDENCE_TABLE", "text": "- source_class=official product documentation; exact_title=AI Agent Studio overview; author/org=ServiceNow; canonical_url=https://www.servicenow.com/docs/r/intelligent-experiences/ai-agent-studio.html; publication/update/access_date=Release version Australia / Updated 2026-03-12 / accessed 2026-09-13 JST; version/release/tag/commit/API revision=Australia release; supporting_locator=Overview lines 2043-2072（centralized applicationでAI agents/agentic workflowsをcreate/manage/test/monitor、Otto AI Agentsのinstall、execution logs、version filter、manual single execution/automated multi-execution evaluations、AI Guardianのoffensiveness/prompt injection/long-term memory、analytics）; evidence_label=VERIFIED_SPEC+PRODUCT_VOLATILE; relation=support+limit\n- source_class=official product documentation; exact_title=AI Agent Studio overview; author/org=ServiceNow; canonical_url=https://www.servicenow.com/docs/r/intelligent-experiences/ai-agent-studio.html; publication/update/access_date=Australia release / accessed 2026-09-13 JST; version/release/tag/commit/API revision=Australia release; supporting_locator=Testing agentic AI lines 2099-2105（manual executionとautomated evaluations、security-control access test、live interactionはVirtual Agentを使う必要があるとの制限）; evidence_label=VERIFIED_SPEC+PRODUCT_VOLATILE; relation=support+limit" }, { "heading": "FINDINGS", "text": "- ESTABLISHED: ServiceNow公式DocsはAI Agent Studioをagent/agentic workflowの作成・管理・テスト・監視アプリとして記載し、version付きexecution logs、manual/automated test・evaluation、AI Guardian設定、analyticsを案内している。全機能にはServiceNow Otto AI Agentsのinstallが必要と記載し、live agent interactionのtestingはVirtual Agentを使う制限も明示している。\n- NOT_ESTABLISHED: Australia releaseのDocs記述は、他release・全tenant・全plan・全regionでの機能有効化、AI Guardianが全prompt injectionを阻止すること、analyticsが因果的ROIや安全率を証明すること、実業務での自律action安全性を確立しない。" }, { "heading": "LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE", "text": "release差・plugin/install差・role/ACL・Virtual Agent session制限、評価データの代表性、AI Guardian false positive/negative、agent loop・trigger recursion・tool side effect、analyticsの計測欠損がある。Docsページ自身のAI-generated summaryはas-isで完全性保証なしと注記されているため、本文記載を優先する。" }, { "heading": "AVAILABILITY_GATES", "text": "ServiceNow release、AI Agent Studio/AI agents/AI Guardian/Virtual Agentのinstall・license・subscription、tenant/region、admin role・ACL・scope、Now Assist/LLM provider、workflow/table/data permissions、execution/evaluation quotas、data retention。" }, { "heading": "IMPLEMENTATION_STATE", "text": "ServiceNow official docs + PRODUCT_VOLATILE。Australia releaseの公開仕様確認のみ。tenant activation、role付与、agent作成、live interaction、外部書込み、課金・本番評価は未実施。" }, { "heading": "BENCHMARK_OR_EVAL", "text": "Docsはmanual test、automated multi-execution evaluations、execution logs、analytics metricsを仕様として記載するが、specific dataset・ground truth・threshold・human agreement・業務品質改善値は本Packetで確立していない。UNKNOWN。" }, { "heading": "SECURITY / PRIVACY / AUDIT / COST / OPERABILITY", "text": "Security=AI Guardian、ACL、role、approval、tool scope、Virtual Agent境界をactionごとに確認。Privacy=Now tables、prompt、memory、logs、LLM providerのdata policy。Audit=release、agent/workflow version、execution、test/eval、policy/ACL、approverを相関。Cost=agent execution、model、tool/Assist consumption、evaluation、storageを含む。Operability=release upgrade、session timeout、loop kill switch、rollback、evaluation regression、log completenessを試験。" }, { "heading": "SAFE_WORDING_FOR_FUTURE_BOOK", "text": "「ServiceNow AI Agent Studioの公式Docs（Australia release、2026-03-12更新）は、AI agent/agentic workflowの作成・管理・テスト・監視、execution log、manual/automated evaluation、AI Guardian、analyticsを記載している。Otto AI Agentsのinstall等の前提があり、release・tenant・role・license・session境界と実業務安全性は別途検証が必要である。」" }, { "heading": "UPDATE_WORK_HANDOFF", "text": "ServiceNow organization overlayにrelease・install・role・ACL・Virtual Agent制約を引き継ぐ。次回は各releaseのfeature matrix、license/pricing、AI Guardian仕様、evaluation schema、audit/data retention、公開incident/failure report、loop/trigger/Assist costの再現可能TEST_PROFILEを補う。" }, { "heading": "OPEN_UNKNOWN", "text": "current release beyond Australia、exact licensing/region、AI Guardian detection metrics、evaluation ground truth、agent loop/recursion controls、ACL/data boundary、Assist cost、tenant availability、公開incident。" }, { "heading": "STOP_CONDITION", "text": "Australia Docsの存在をユーザーtenantの有効化・全release・全機能保証へ外挿しない。analytics・manual test・AI Guardianの存在を安全率・ROI・prompt injection完全防御と書かない。\nUNIT_CLOSE_STATUS: INDIVIDUAL_BOUNDED_CLOSE / EVIDENCE_RECORDED / UNKNOWN_PRESERVED\n\n\n===== RUN CLOSE / HANDOFF =====\nINDIVIDUAL_PACKET_COUNT: 9/9（EA-137..EA-145）" }, { "heading": "PRIMARY_SOURCE_RECORD", "text": "11 source records across 9 packets; official project/product documentation, author-maintained repositories, and one primary research paper record exact title, author/org, canonical URL, access/publication date, version/release/tag/API status, supporting locator, evidence label, and relation." }, { "heading": "CLAIM_SEPARATION", "text": "EA-137..145 each has separate question, established/unestablished findings, evidence relation, limits/counterevidence/failure envelope, availability gates, implementation state, benchmark/eval, safe wording, handoff, open unknown, and stop condition." }, { "heading": "EVIDENCE_BOUNDARY", "text": "Framework/API/docs establish documented concepts and current page claims only. Historical paper results, provider marketing, customer quotes, product existence, plan/region/org/role availability, tenant behavior, production safety, and business outcomes remain separately gated or UNKNOWN.\nLIVE_SIDE_EFFECTS: 0. No authenticated tenant operation, external write, billing, contract change, secret input, live agent execution, or dangerous test." }, { "heading": "CURRENTNESS", "text": "ServiceNow official docs still document AI Agent Studio/manual and automated evaluations; 2026-08-14 Zurich AI Guardian docs require admin enablement and describe mitigation, not complete prevention. Australia evaluation docs require agent versions, datasets, permissions and execution logs. Zurich Patch 4 may turn designated AI assets on by default only under stated install/admin conditions." }, { "heading": "PUBLIC_CLAIM", "text": "ServiceNow documents AI Agent Studio for creating/managing/testing agentic assets, execution/evaluation workflows, guardrails and monitoring. Availability and behavior remain release/plugin/license/role/ACL/tenant dependent." }, { "heading": "UNKNOWN", "text": "independent production success/safety rates; Guardian false-positive/false-negative rates; exact tenant entitlement; complete cost/Assist consumption; organization-specific data boundary." } ], "human_url": "/tools/ea-145-servicenow-ai-agents", "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-145-servicenow-ai-agents", "json_url": "/agent/article.json?path=%2Ftools%2Fea-145-servicenow-ai-agents" }