{
  "format": "agent-article-v0",
  "article_id": "EA-146",
  "canonical_url": "/tools/ea-146-salesforce-agentforce",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EVD-EA-146-URL-AEDDB8806140",
    "EA-146-R11-RESEARCH",
    "EA-146-R11-WEB-READBACK"
  ],
  "unknown_ids": [
    "EA-146-UNKNOWN-01",
    "EA-146-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-045-EA0146",
    "SRC-EA-146-URL-AEDDB8806140",
    "WEBBODY-EA0146-R8-831174A4"
  ],
  "article_sources": [
    {
      "id": "EVD-EA-146-URL-AEDDB8806140",
      "evidence_class": "RESEARCH",
      "title": "source_class=official product documentation; exact_title=Agentforce: The AI Agent Platform; author/org=Salesforce; canonical_url=",
      "href": "https://www.salesforce.com/agentforce/",
      "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-146-URL-AEDDB8806140"
      ],
      "supporting_locators": [
        "EVIDENCE_TABLE",
        "- source_class=official product documentation; exact_title=Agentforce: The AI Agent Platform; author/org=Salesforce; canonical_url=https://www.salesforce.com/agentforce/"
      ],
      "scope": "EVIDENCE_TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EA-146-R11-RESEARCH",
      "evidence_class": "RESEARCH",
      "title": "EA-146 監査済みresearch / canonical revision binding",
      "supports": [
        "- ESTABLISHED: Salesforce公式ページはAgentforceを企業向けAI agent platformとして掲げ、Data・Reasoning・Actions、Agent Builder、subagents/actions/instructions、Agent Script、Observability、MCP support、multi-agent orchestrationを機能群として記載している。FAQはFlows、MuleSoft、Apex/JavaScript、Salesforce CRM/Data 360を接続要素として説明し、Agent Builderでagent planを観察しresponseをtestできると記載する。\n- NOT_ESTABLISHED: 同ページは、特定orgでのentitlement、edition、region、権限設定、MCP serverの実利用可否、Atlas/Agent Scriptの版互換、成功率・安全率・ROI、全prompt injection防御、顧客実績を確立しない。ページ上の「18K companies」等のvendor statementは、独立した再現可能証拠ではない。"
      ],
      "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-045-EA0146"
      ],
      "supporting_locators": [
        "COMM-045-EA0146",
        "EA-146-R5-LEGACY-MIGRATION-20261008-R1",
        "content/staging/EA-146.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-146-R11-WEB-READBACK",
      "evidence_class": "IMPL",
      "title": "EA-146 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-EA0146-R8-831174A4"
      ],
      "supporting_locators": [
        "WEBBODY-EA0146-R8-831174A4",
        "content/staging/EA-146.md",
        "EA-146-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": "CRMを基盤にした企業Agentの代表的な実装として、Agent Builder、subagent/action/instruction、観測、MCP、multi-agent orchestrationを、Salesforce固有のデータ・権限・契約境界と分離して後続更新へ渡す。"
    },
    {
      "heading": "SCOPE_ROUTING",
      "text": "provider mapping / organization overlay / interoperability / governance / benchmark / implementation / security / audit / operability。"
    },
    {
      "heading": "CLAIM_OR_RESEARCH_QUESTION",
      "text": "Salesforceの現行公開ページは、Agentforceを何のプラットフォームとして説明し、構築・実行・観測・相互運用のどこまでを仕様として示すか。製品ページの機能記載を、全tenantの有効化、性能、安全性、顧客成果へ外挿できるか。"
    },
    {
      "heading": "EVIDENCE_TABLE",
      "text": "- source_class=official product documentation; exact_title=Agentforce: The AI Agent Platform; author/org=Salesforce; canonical_url=https://www.salesforce.com/agentforce/; publication/update/access_date=update date not stated on page / accessed 2026-09-13 23:54 JST; version/release/tag/commit/API revision=current public Agentforce page; supporting_locator=lines 131-167（Agent Development Lifecycle、Agent BuilderでAgentforce/Subagents/Actions/Instructionsを構成、Agent Script、Observability、MCP Support、Multi-Agent Orchestration）; evidence_label=VERIFIED_SPEC+PRODUCT_VOLATILE; relation=support+limit。\n- source_class=official product documentation; exact_title=Agentforce: The AI Agent Platform; author/org=Salesforce; canonical_url=https://www.salesforce.com/agentforce/; publication/update/access_date=update date not stated on page / accessed 2026-09-13 23:54 JST; version/release/tag/commit/API revision=current public Agentforce page; supporting_locator=lines 257-287（AI agentの定義、CRM/Data 360等のtrusted business data、Agent Builder、standard/custom subagents/actions、Flows、MuleSoft connectors、Apex/JavaScript、plan/testの説明）; evidence_label=VERIFIED_SPEC+PRODUCT_VOLATILE; relation=support+context+limit。"
    },
    {
      "heading": "FINDINGS",
      "text": "- ESTABLISHED: Salesforce公式ページはAgentforceを企業向けAI agent platformとして掲げ、Data・Reasoning・Actions、Agent Builder、subagents/actions/instructions、Agent Script、Observability、MCP support、multi-agent orchestrationを機能群として記載している。FAQはFlows、MuleSoft、Apex/JavaScript、Salesforce CRM/Data 360を接続要素として説明し、Agent Builderでagent planを観察しresponseをtestできると記載する。\n- NOT_ESTABLISHED: 同ページは、特定orgでのentitlement、edition、region、権限設定、MCP serverの実利用可否、Atlas/Agent Scriptの版互換、成功率・安全率・ROI、全prompt injection防御、顧客実績を確立しない。ページ上の「18K companies」等のvendor statementは、独立した再現可能証拠ではない。"
    },
    {
      "heading": "LIMITS / COUNTEREVIDENCE / FAILURE_ENVELOPE",
      "text": "現行公開ページは製品訴求を含むため、機能存在と実運用性能を分離する。CRM/Data 360の欠損・誤権限、tool/actionの副作用、LLMの誤推論、MCP serverの信頼性、multi-agent loop、human handoff欠落、観測データ欠損、release差が失敗包絡になる。独立benchmark・公開incident・特定orgの再現試験は本Packetで未採集。"
    },
    {
      "heading": "AVAILABILITY_GATES",
      "text": "Salesforce edition/org契約、Agentforce entitlement・credits/resolutions/per-user条件、Data 360/CRM data model、Agent Builder/Agent Script/Observability/MCP/multi-agent各featureのrelease・region・channel、admin permission・profile/permission set・object/field sharing、MuleSoft/Flow/Apex/JavaScript/API接続、model/provider/data residency、action approval・rate/quota・retention。"
    },
    {
      "heading": "IMPLEMENTATION_STATE",
      "text": "Salesforce公式公開ページの仕様確認のみ。tenant login、agent作成、CRM読み書き、MCP接続、課金変更、live/customer test、外部書込みは未実施。"
    },
    {
      "heading": "BENCHMARK_OR_EVAL",
      "text": "公式ページはplanの観察・responseのtest・observabilityを記載するが、公開されたdataset、ground truth、threshold、human agreement、failure rate、cost per accepted outcomeは本Packetで確認できない。UNKNOWN。"
    },
    {
      "heading": "SECURITY / PRIVACY / AUDIT / COST / OPERABILITY",
      "text": "Security=CRM/object/field権限、action allowlist、MCP server trust、prompt injection、approval、handoffを分離検証。Privacy=CRM/Data 360、prompt、memory/log、外部connectorのデータフローとretention。Audit=agent/instruction/action/model/version、tool call、human handoff、admin change、evaluationを相関。Cost=credits/resolutions/per-user、model/tool call、Data 360/MuleSoft、観測・評価を含める。Operability=release pinning、regression、rollback、loop/time limit、MCP outage、log completeness、side-effect replay。"
    },
    {
      "heading": "SAFE_WORDING_FOR_FUTURE_BOOK",
      "text": "「Salesforceの公開Agentforceページは、CRM等の業務データを使うAgent Builder、subagents/actions/instructions、Agent Script、observability、MCP support、multi-agent orchestrationを機能として説明している。ただし、edition・org・region・権限・契約による可用性、性能、安全性、費用、実業務の自律actionは別途検証が必要である。」"
    },
    {
      "heading": "UPDATE_WORK_HANDOFF",
      "text": "provider mappingではSalesforce固有のCRM/Data 360/Flow/MuleSoft/Apex境界をCore agent概念から分離し、organization overlayにentitlement・permission・data residency・approval・audit・costの確認欄を追加する。次回は公式release/feature matrix、pricing/consumption、MCP verified server仕様、security/incident、評価schema、再現可能TEST_PROFILEを補う。"
    },
    {
      "heading": "OPEN_UNKNOWN",
      "text": "current release/API revision、Agent Script/Atlasの版差、MCP availability、exact pricing/credit consumption、tenant/org gates、data retention、公開failure/incident、独立評価、multi-agent stopping/rollback。"
    },
    {
      "heading": "STOP_CONDITION",
      "text": "Salesforce公式マーケティング記載を全tenantの利用可能性、性能保証、prompt injection完全防御、ROI、顧客実績へ拡張しない。\nUNIT_CLOSE_STATUS: INDIVIDUAL_BOUNDED_CLOSE / EVIDENCE_RECORDED / UNKNOWN_PRESERVED\n\n---"
    },
    {
      "heading": "PUBLIC_CLAIM",
      "text": "Salesforce public Agentforce materials describe an enterprise AI-agent platform with Agent Builder, subagents/actions/instructions, Agent Script, observability, MCP support, multi-agent orchestration, and connections to Salesforce CRM/Data 360, Flows, MuleSoft, Apex and JavaScript. These materials do not establish entitlement or availability for every org/edition/region, production performance or safety, complete prompt-injection prevention, ROI, or independently reproduced customer outcomes."
    }
  ],
  "human_url": "/tools/ea-146-salesforce-agentforce",
  "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-146-salesforce-agentforce",
  "json_url": "/agent/article.json?path=%2Ftools%2Fea-146-salesforce-agentforce"
}