Skip to content

Evidence for AI operations

Enterprise AI Operations Dictionary

No English page yet. Showing the Japanese source.

Back to the entrance

Prompt／Instruction Configuration Management

用語・参照用語・参照公式仕様のみ公式仕様のみ鮮度未確認鮮度を確定できない

記事状態: 公開 · 最終確認: 未確認

要点

「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。」

現在の判断

  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.

どこまで当てはまるか

  • Enterprise AI Core: versioned configuration / immutable revision / promotion / rollback / provenance
  • PromptOps / implementation: prompt registry、environment alias、CI/eval gate
  • Provider mapping: Google Vertex AI Prompt Management等
  • OSS practice: MLflow Prompt Registry
  • Governance / audit: owner、review、approval、change reason、effective deployment version

詳しく理解する

なぜ重要か

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。

対象範囲と前提

  • Enterprise AI Core: versioned configuration / immutable revision / promotion / rollback / provenance
  • PromptOps / implementation: prompt registry、environment alias、CI/eval gate
  • Provider mapping: Google Vertex AI Prompt Management等
  • OSS practice: MLflow Prompt Registry
  • Governance / audit: owner、review、approval、change reason、effective deployment version

検討ポイント

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。

EVIDENCE TABLE

利用できる条件

  • MLflow Prompt Registry behavior depends on deployed MLflow version/backend and organization auth configuration; docs establish OSS capability, not any managed-service parity.
  • 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.
  • No claim is made that Anthropic/OpenAI or every provider offers an equivalent first-party registry in every plan/region; provider mapping remains separate.

実装・運用

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.

確認・評価方法

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.

セキュリティとプライバシー

  • 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.
  • Privacy: test examples and prompt variables can contain sensitive data; registry access and retention need data classification.
  • Audit: record author, reviewer, immutable version/hash or provider version ID, change reason, evaluation artifact, approval, promotion time, alias movement and resolved runtime version.
  • Cost: regression evaluation and dual-running/canarying incur inference cost; risk-tier changes rather than every wording edit can determine gate depth.
  • 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.

CURRENTNESS AUDIT

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.

確認できていること

  • 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.

  • 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.

  • 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.

  • 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.

  • 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.

  • 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.

よくある失敗・反証

  • Versioning a prompt cannot guarantee identical model output; model/provider revisions, nondeterminism, tools, retrieval state and external data may change.

  • A prompt registry does not by itself enforce review, evaluation quality, separation of duties or safe promotion. Those are organization workflow controls.

  • Mutable aliases simplify deployment but introduce time-of-use ambiguity if execution telemetry records only the alias.

  • Provider-native prompt resources differ in schema and lifecycle; do not claim portability of prompt IDs/versions across providers.

  • Google sample APIs shown under vertexai.preview.prompts are PRODUCT_VOLATILE and must be revalidated before future publication.

  • Registry deletion/retention settings can conflict with forensic needs; production retention policy must be designed explicitly.

  • 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。

    ---

実務での使い方

  • MLflow Prompt Registry behavior depends on deployed MLflow version/backend and organization auth configuration; docs establish OSS capability, not any managed-service parity.

  • 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.

  • No claim is made that Anthropic/OpenAI or every provider offers an equivalent first-party registry in every plan/region; provider mapping remains separate.

  • 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.

  • 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.

  • 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.

  • Privacy: test examples and prompt variables can contain sensitive data; registry access and retention need data classification.

  • Audit: record author, reviewer, immutable version/hash or provider version ID, change reason, evaluation artifact, approval, promotion time, alias movement and resolved runtime version.

  • Cost: regression evaluation and dual-running/canarying incur inference cost; risk-tier changes rather than every wording edit can determine gate depth.

  • 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.

  • EA-056 AI Asset Registryへ prompt/instruction asset type、immutable version、owner、environment alias、evaluation/approval linkageを追加候補。

  • EA-051 telemetryへ prompt.asset_id, prompt.version, configuration_bundle_id 相当をprovider-neutral fieldとして検討。

  • 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。

  • 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。

  • 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.

まだ確認できていないこと

  • EA-058-UNKNOWN-01

    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。

    ---

  • EA-058-UNKNOWN-CURRENTNESS

    外部根拠の再確認日がcanonical body/control-planeで確定していないため、currentnessはUNKNOWNとして保持する。日付を推測補完しない。

根拠資料

出典ID・検証情報・機械可読データ

根拠の種類と情報の鮮度は、ラベルとアイコンで確認できます。

記事ID
EA-058
最終確認日
—
提供元・モデル・プラン・利用環境
Google
対象地域
—
元資料の全文と収録照合記録
WHY_THIS_MATTERS_TO_UPDATE

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。

SCOPE_ROUTING
  • Enterprise AI Core: versioned configuration / immutable revision / promotion / rollback / provenance
  • PromptOps / implementation: prompt registry、environment alias、CI/eval gate
  • Provider mapping: Google Vertex AI Prompt Management等
  • OSS practice: MLflow Prompt Registry
  • Governance / audit: owner、review、approval、change reason、effective deployment version
CLAIM_OR_RESEARCH_QUESTION

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。

EVIDENCE TABLE
FINDINGS
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE
  • Versioning a prompt cannot guarantee identical model output; model/provider revisions, nondeterminism, tools, retrieval state and external data may change.
  • A prompt registry does not by itself enforce review, evaluation quality, separation of duties or safe promotion. Those are organization workflow controls.
  • Mutable aliases simplify deployment but introduce time-of-use ambiguity if execution telemetry records only the alias.
  • Provider-native prompt resources differ in schema and lifecycle; do not claim portability of prompt IDs/versions across providers.
  • Google sample APIs shown under vertexai.preview.prompts are PRODUCT_VOLATILE and must be revalidated before future publication.
  • Registry deletion/retention settings can conflict with forensic needs; production retention policy must be designed explicitly.
AVAILABILITY_GATES
  • MLflow Prompt Registry behavior depends on deployed MLflow version/backend and organization auth configuration; docs establish OSS capability, not any managed-service parity.
  • 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.
  • No claim is made that Anthropic/OpenAI or every provider offers an equivalent first-party registry in every plan/region; provider mapping remains separate.
IMPLEMENTATION_STATE

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.

BENCHMARK_OR_EVAL

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.

SECURITY / PRIVACY / AUDIT / COST / OPERABILITY
  • 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.
  • Privacy: test examples and prompt variables can contain sensitive data; registry access and retention need data classification.
  • Audit: record author, reviewer, immutable version/hash or provider version ID, change reason, evaluation artifact, approval, promotion time, alias movement and resolved runtime version.
  • Cost: regression evaluation and dual-running/canarying incur inference cost; risk-tier changes rather than every wording edit can determine gate depth.
  • 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.
SAFE_WORDING_FOR_FUTURE_BOOK

「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。」

UPDATE_WORK_HANDOFF
  • EA-056 AI Asset Registryへ prompt/instruction asset type、immutable version、owner、environment alias、evaluation/approval linkageを追加候補。
  • EA-051 telemetryへ prompt.asset_id, prompt.version, configuration_bundle_id 相当をprovider-neutral fieldとして検討。
  • 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。
  • 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。
OPEN_UNKNOWN / STOP_CONDITION

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。

---

CURRENTNESS_AUDIT

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.

  • EVD-EA-058-URL-118388C854B6研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    1) [author-maintained OSS docs] Prompt Registry, MLflow AI Platform. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-118388C854B6
    検証箇所
    EVIDENCE TABLE · 1) [author-maintained OSS docs] Prompt Registry, MLflow AI Platform. Canonical: https://mlflow.org/docs/latest/genai/prompt-registry/
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EVD-EA-058-URL-07789C42B49A研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    2) [author-maintained OSS docs] Manage Prompt Lifecycles, MLflow AI Platform. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-07789C42B49A
    検証箇所
    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/
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EVD-EA-058-URL-B5D112A68AF1研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    3) [author-maintained OSS docs] Use Prompts in Apps, MLflow AI Platform. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-B5D112A68AF1
    検証箇所
    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/
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EVD-EA-058-URL-843C089305C7研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    4) [official product docs] List available prompt versions, Generative AI on Vertex AI, Google Cloud. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-843C089305C7
    検証箇所
    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
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EVD-EA-058-URL-86C7EB613982研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    5) [official product docs] Restore a version of a prompt, Generative AI on Vertex AI, Google Cloud. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-86C7EB613982
    検証箇所
    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
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EVD-EA-058-URL-D0A28C3433C2研究資料研究資料根拠の出所: SOURCE_PACKET_REFERENCE

    6) [official product docs] Create and use a Vertex AI Prompt to generate text, Google Cloud. Canonical:

    裏付ける内容
    —
    確認日
    —
    出典・実験ID
    SRC-EA-058-URL-D0A28C3433C2
    検証箇所
    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
    適用範囲
    EVIDENCE TABLE
    出典・来歴
    SOURCE_PACKET_REFERENCE_PROJECTED
    限界
    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。
  • EA-058-R11-RESEARCH研究資料研究資料根拠の出所: AUDITED_CANONICAL_RESEARCH_PACKET

    EA-058 監査済みresearch / canonical revision binding

    裏付ける内容
    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. 2. 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. 3. 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. 4. 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. 5. 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. 6. 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.
    確認日
    —
    出典・実験ID
    COMM-055-EA0058
    検証箇所
    COMM-055-EA0058 · EA-058-R5-LEGACY-MIGRATION-20261008-R1 · content/staging/EA-058.md
    適用範囲
    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。
    出典・来歴
    AUDIT_PASS_CANONICAL_BINDING
    限界
    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。
  • EA-058-R11-WEB-READBACK実装資料実装資料根拠の出所: IMPLEMENTATION_READBACK

    EA-058 Web body identity / canonical readback

    裏付ける内容
    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。
    確認日
    —
    出典・実験ID
    WEBBODY-EA0058-R8-C4473E59
    検証箇所
    WEBBODY-EA0058-R8-C4473E59 · content/staging/EA-058.md · EA-058-R5-LEGACY-MIGRATION-20261008-R1
    適用範囲
    R9/R10 canonical readback後のProduction生成時body identity。
    出典・来歴
    CANONICAL_READBACK_BODY_HASH_MATCH
    限界
    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。
出典ID
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
追跡中のUNKNOWN ID
EA-058-UNKNOWN-01, EA-058-UNKNOWN-CURRENTNESS
再確認のきっかけ
canonical revision/publication state change · body artifact hash change · source currentness change · new contradiction or implementation readback

機械検査: 通過 — Automated validation does not guarantee accuracy or authorize execution.

    同じ記事IDの機械可読データです。