{
  "format": "agent-article-v0",
  "article_id": "EA-058",
  "canonical_url": "/tools/ea-058-prompt-instruction-configuration-management",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EVD-EA-058-URL-118388C854B6",
    "EVD-EA-058-URL-07789C42B49A",
    "EVD-EA-058-URL-B5D112A68AF1",
    "EVD-EA-058-URL-843C089305C7",
    "EVD-EA-058-URL-86C7EB613982",
    "EVD-EA-058-URL-D0A28C3433C2",
    "EA-058-R11-RESEARCH",
    "EA-058-R11-WEB-READBACK"
  ],
  "unknown_ids": [
    "EA-058-UNKNOWN-01",
    "EA-058-UNKNOWN-CURRENTNESS"
  ],
  "operational_object_ids": [],
  "provider": [
    "Google"
  ],
  "models": [],
  "plans": [],
  "surfaces": [],
  "regions": [],
  "current_status": "UNKNOWN",
  "observation_status": "SPEC_ONLY",
  "freshness": "UNKNOWN",
  "last_verified": null,
  "supersedes": [],
  "superseded_by": [],
  "provenance": [
    "COMM-055-EA0058",
    "SRC-EA-058-URL-118388C854B6",
    "SRC-EA-058-URL-07789C42B49A",
    "SRC-EA-058-URL-B5D112A68AF1",
    "SRC-EA-058-URL-843C089305C7",
    "SRC-EA-058-URL-86C7EB613982",
    "SRC-EA-058-URL-D0A28C3433C2",
    "WEBBODY-EA0058-R8-C4473E59"
  ],
  "article_sources": [
    {
      "id": "EVD-EA-058-URL-118388C854B6",
      "evidence_class": "RESEARCH",
      "title": "1) [author-maintained OSS docs] Prompt Registry, MLflow AI Platform. Canonical:",
      "href": "https://mlflow.org/docs/latest/genai/prompt-registry/",
      "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-058-URL-118388C854B6"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "1) [author-maintained OSS docs] Prompt Registry, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-058-URL-07789C42B49A",
      "evidence_class": "RESEARCH",
      "title": "2) [author-maintained OSS docs] Manage Prompt Lifecycles, MLflow AI Platform. Canonical:",
      "href": "https://mlflow.org/docs/latest/genai/prompt-registry/manage-prompt-lifecycles-with-aliases/",
      "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-058-URL-07789C42B49A"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "2) [author-maintained OSS docs] Manage Prompt Lifecycles, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/manage-prompt-lifecycles-with-aliases/"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-058-URL-B5D112A68AF1",
      "evidence_class": "RESEARCH",
      "title": "3) [author-maintained OSS docs] Use Prompts in Apps, MLflow AI Platform. Canonical:",
      "href": "https://mlflow.org/docs/latest/genai/prompt-registry/use-prompts-in-apps/",
      "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-058-URL-B5D112A68AF1"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "3) [author-maintained OSS docs] Use Prompts in Apps, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/use-prompts-in-apps/"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-058-URL-843C089305C7",
      "evidence_class": "RESEARCH",
      "title": "4) [official product docs] List available prompt versions, Generative AI on Vertex AI, Google Cloud. Canonical:",
      "href": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-list-prompt-version",
      "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-058-URL-843C089305C7"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "4) [official product docs] List available prompt versions, Generative AI on Vertex AI, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-list-prompt-version"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-058-URL-86C7EB613982",
      "evidence_class": "RESEARCH",
      "title": "5) [official product docs] Restore a version of a prompt, Generative AI on Vertex AI, Google Cloud. Canonical:",
      "href": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-restore-version",
      "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-058-URL-86C7EB613982"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "5) [official product docs] Restore a version of a prompt, Generative AI on Vertex AI, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-restore-version"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-058-URL-D0A28C3433C2",
      "evidence_class": "RESEARCH",
      "title": "6) [official product docs] Create and use a Vertex AI Prompt to generate text, Google Cloud. Canonical:",
      "href": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-template-create-generate-save",
      "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-058-URL-D0A28C3433C2"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "6) [official product docs] Create and use a Vertex AI Prompt to generate text, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-template-create-generate-save"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EA-058-R11-RESEARCH",
      "evidence_class": "RESEARCH",
      "title": "EA-058 監査済みresearch / canonical revision binding",
      "supports": [
        "1. Prompt versioning is an existing implementation practice, not merely a proposal. MLflow provides immutable prompt versions, commit messages, tags, environment aliases, response format and model configuration; aliases can move between versions for promotion/rollback.\n2. Google Vertex AI also exposes saved prompt resources and versions and documents version listing/restoration. Current Python samples use `vertexai.preview.prompts`; therefore API maturity/availability must be rechecked at publication-update time.\n3. Prompt text alone is insufficient for reproducibility. MLflow’s Prompt object itself recognizes model_config, and Vertex examples bind prompt data with model_name/system_instruction and optional generation/safety settings. From these implementations plus EA-055 replay requirements, Core should treat the deployment unit as an execution-configuration bundle rather than only text. This is INFERENCE/PROPOSAL, not a universal standard.\n4. Recommended bundle identity: immutable prompt/instruction revision + model ID/revision/alias resolution + generation parameters + response schema + tool definitions/versions + retrieval/index/policy references + safety/guardrail config + environment + evaluation dataset/version + owner/approval/change reason. Runtime traces should record the resolved immutable revisions actually used.\n5. Environment aliases (`production`, `staging`, etc.) improve operability but are mutable pointers. Audit/replay records must resolve and persist the target version at execution time; retaining only the alias is insufficient forensic provenance.\n6. Rollback should create or select a known configuration revision and preserve history; “edit the current prompt back by hand” destroys provenance. Google’s restore sample creating a restored version and MLflow’s immutable-version/alias model both support this operational pattern."
      ],
      "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-055-EA0058"
      ],
      "supporting_locators": [
        "COMM-055-EA0058",
        "EA-058-R5-LEGACY-MIGRATION-20261008-R1",
        "content/staging/EA-058.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-058-R11-WEB-READBACK",
      "evidence_class": "IMPL",
      "title": "EA-058 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-EA0058-R8-C4473E59"
      ],
      "supporting_locators": [
        "WEBBODY-EA0058-R8-C4473E59",
        "content/staging/EA-058.md",
        "EA-058-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": "Prompt/system instructionはAI挙動を変える実行構成であり、コードを変えなくても安全性、tool選択、出力形式、business rule遵守が変わる。prompt本文だけをGit断片や管理画面に散在させると、incident/replay時に“何が本番で使われたか”を復元できない。EA-054 rollback、EA-055 replay/forensics、EA-056 asset inventoryと接続する構成管理が必要。"
    },
    {
      "heading": "SCOPE_ROUTING",
      "text": "- Enterprise AI Core: versioned configuration / immutable revision / promotion / rollback / provenance\n- PromptOps / implementation: prompt registry、environment alias、CI/eval gate\n- Provider mapping: Google Vertex AI Prompt Management等\n- OSS practice: MLflow Prompt Registry\n- Governance / audit: owner、review、approval、change reason、effective deployment version"
    },
    {
      "heading": "CLAIM_OR_RESEARCH_QUESTION",
      "text": "Promptをversioned artifactとして管理するだけで再現性は得られるか。model、generation settings、tools、retrieval/policy等をどこまで同じconfiguration bundleとして固定する必要があるか。"
    },
    {
      "heading": "EVIDENCE TABLE",
      "text": "1) [author-maintained OSS docs] Prompt Registry, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/ . Accessed 2026-09-14. Locator: Prompt object attributes; sequential Version, Commit Message, Tags, mutable Alias, response_format, model_config; existing prompt versions are immutable. Label: OSS_PRACTICE. Relation: support.\n2) [author-maintained OSS docs] Manage Prompt Lifecycles, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/manage-prompt-lifecycles-with-aliases/ . Accessed 2026-09-14. Locator: staging/production aliases, alias switching, rollback/A-B use. Label: OSS_PRACTICE. Relation: support.\n3) [author-maintained OSS docs] Use Prompts in Apps, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/use-prompts-in-apps/ . Accessed 2026-09-14. Locator: `prompts:/<prompt_name>/<version_or_alias>` and model lineage linkage. Label: OSS_PRACTICE. Relation: support/context.\n4) [official product docs] List available prompt versions, Generative AI on Vertex AI, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-list-prompt-version . Accessed 2026-09-14. Locator: `prompts.create_version`, `prompts.list_versions`, `prompts.get`. Example uses `vertexai.preview.prompts`. Label: VERIFIED_SPEC / PRODUCT_VOLATILE. Relation: support/availability.\n5) [official product docs] Restore a version of a prompt, Generative AI on Vertex AI, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-restore-version . Accessed 2026-09-14. Locator: `prompts.restore_version`; restored older content becomes a new version. Label: VERIFIED_SPEC / PRODUCT_VOLATILE. Relation: support.\n6) [official product docs] Create and use a Vertex AI Prompt to generate text, Google Cloud. Canonical: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-prompt-template-create-generate-save . Accessed 2026-09-14. Locator: Prompt includes prompt_data, variables, model_name, system_instruction, optional generation/safety configuration and saves a version. Label: VERIFIED_SPEC / PRODUCT_VOLATILE. Relation: support/context."
    },
    {
      "heading": "FINDINGS",
      "text": "1. Prompt versioning is an existing implementation practice, not merely a proposal. MLflow provides immutable prompt versions, commit messages, tags, environment aliases, response format and model configuration; aliases can move between versions for promotion/rollback.\n2. Google Vertex AI also exposes saved prompt resources and versions and documents version listing/restoration. Current Python samples use `vertexai.preview.prompts`; therefore API maturity/availability must be rechecked at publication-update time.\n3. Prompt text alone is insufficient for reproducibility. MLflow’s Prompt object itself recognizes model_config, and Vertex examples bind prompt data with model_name/system_instruction and optional generation/safety settings. From these implementations plus EA-055 replay requirements, Core should treat the deployment unit as an execution-configuration bundle rather than only text. This is INFERENCE/PROPOSAL, not a universal standard.\n4. Recommended bundle identity: immutable prompt/instruction revision + model ID/revision/alias resolution + generation parameters + response schema + tool definitions/versions + retrieval/index/policy references + safety/guardrail config + environment + evaluation dataset/version + owner/approval/change reason. Runtime traces should record the resolved immutable revisions actually used.\n5. Environment aliases (`production`, `staging`, etc.) improve operability but are mutable pointers. Audit/replay records must resolve and persist the target version at execution time; retaining only the alias is insufficient forensic provenance.\n6. Rollback should create or select a known configuration revision and preserve history; “edit the current prompt back by hand” destroys provenance. Google’s restore sample creating a restored version and MLflow’s immutable-version/alias model both support this operational pattern."
    },
    {
      "heading": "LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE",
      "text": "- Versioning a prompt cannot guarantee identical model output; model/provider revisions, nondeterminism, tools, retrieval state and external data may change.\n- A prompt registry does not by itself enforce review, evaluation quality, separation of duties or safe promotion. Those are organization workflow controls.\n- Mutable aliases simplify deployment but introduce time-of-use ambiguity if execution telemetry records only the alias.\n- Provider-native prompt resources differ in schema and lifecycle; do not claim portability of prompt IDs/versions across providers.\n- Google sample APIs shown under `vertexai.preview.prompts` are PRODUCT_VOLATILE and must be revalidated before future publication.\n- Registry deletion/retention settings can conflict with forensic needs; production retention policy must be designed explicitly."
    },
    {
      "heading": "AVAILABILITY_GATES",
      "text": "- MLflow Prompt Registry behavior depends on deployed MLflow version/backend and organization auth configuration; docs establish OSS capability, not any managed-service parity.\n- Vertex AI Prompt APIs require Google Cloud project/auth/location and the current SDK/API surface; preview namespace usage means publication-time status must be rechecked.\n- No claim is made that Anthropic/OpenAI or every provider offers an equivalent first-party registry in every plan/region; provider mapping remains separate."
    },
    {
      "heading": "IMPLEMENTATION_STATE",
      "text": "IMPLEMENTABLE NOW. Core pattern: immutable artifact revision -> evaluation -> approval -> environment alias/pointer -> deployment -> runtime logs capture resolved revision -> rollback by alias/promotion to an approved immutable version. Store prompt/instruction assets in EA-056 registry and link runtime revision IDs into EA-051 telemetry and EA-055 forensic records."
    },
    {
      "heading": "BENCHMARK_OR_EVAL",
      "text": "Configuration management quality should be tested by change gates rather than a generic model benchmark: regression eval set, policy/safety checks, tool-call contract tests, output-schema tests, cost/latency comparison and canary/rollback exercise. Evaluation dataset/scorer versions are themselves provenance. Passing evaluation does not guarantee production safety."
    },
    {
      "heading": "SECURITY / PRIVACY / AUDIT / COST / OPERABILITY",
      "text": "- Security: prompts can contain policy logic, hidden instructions, tool constraints and sometimes secrets; secrets should be referenced through secret management rather than embedded in prompt artifacts.\n- Privacy: test examples and prompt variables can contain sensitive data; registry access and retention need data classification.\n- Audit: record author, reviewer, immutable version/hash or provider version ID, change reason, evaluation artifact, approval, promotion time, alias movement and resolved runtime version.\n- Cost: regression evaluation and dual-running/canarying incur inference cost; risk-tier changes rather than every wording edit can determine gate depth.\n- Operability: registry/alias caching can delay pointer changes. MLflow documents different cache behavior for immutable versions vs mutable aliases, so rollback RTO must account for cache/propagation semantics."
    },
    {
      "heading": "SAFE_WORDING_FOR_FUTURE_BOOK",
      "text": "「Promptやsystem instructionは単なる文章ではなく、本番挙動を変える構成資産としてversion管理する。再現・監査に必要なのはprompt本文だけではなく、実行時に解決されたprompt revision、model、generation設定、tool/retrieval/policy等の組合せである。`production`のようなaliasは運用に便利だが、監査ログにはalias名だけでなく実際に参照したimmutable versionを残す。」"
    },
    {
      "heading": "UPDATE_WORK_HANDOFF",
      "text": "- EA-056 AI Asset Registryへ prompt/instruction asset type、immutable version、owner、environment alias、evaluation/approval linkageを追加候補。\n- EA-051 telemetryへ `prompt.asset_id`, `prompt.version`, `configuration_bundle_id` 相当をprovider-neutral fieldとして検討。\n- EA-054 rollbackではprompt alias切替だけでなくmodel/tool/retrieval/policyとの整合を確認するcompound rollback checklistへ接続。\n- EA-055 replayではmutable aliasを再解決せず、当時記録したimmutable revisionを参照する。"
    },
    {
      "heading": "OPEN_UNKNOWN / STOP_CONDITION",
      "text": "OPEN: provider横断configuration bundleの最小共通schema。OPEN: first-party prompt registriesのprovider/plan差とretention/export portability。OPEN: promptだけでなくtool schema/retrieval policy/guardrailを同一atomic releaseとして扱う標準的manifestの有無。STOP CONDITION: versioning・promotion・rollbackの実装precedent、prompt-only再現性の限界、Core候補bundle、publication-time recheck点まで確立したためEA-058初回packetはbounded complete。\n\n---"
    },
    {
      "heading": "CURRENTNESS_AUDIT",
      "text": "MLflow prompt templates/versions are immutable but model_config on a prompt version is mutable after creation. Vertex AI prompt versioning/restoration remains PRODUCT_VOLATILE. A prompt-version ID alone is not an immutable full execution configuration."
    }
  ],
  "human_url": "/tools/ea-058-prompt-instruction-configuration-management",
  "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-058-prompt-instruction-configuration-management",
  "json_url": "/agent/article.json?path=%2Ftools%2Fea-058-prompt-instruction-configuration-management"
}