# AI Telemetry標準編 CURRENT_STATUS: UNKNOWN OBSERVATION: SPEC_ONLY FRESHNESS: UNKNOWN PAGE_TYPE: reference CANONICAL_URL: /tools/ea-051-ai-telemetry CLAIM_IDS: none EVIDENCE_IDS: EVD-EA-051-URL-6A0029787A22, EVD-EA-051-URL-5E36EEBF9907, EVD-EA-051-URL-E45DC2C99A6D, EVD-EA-051-URL-B8771AA21367, EVD-EA-051-URL-08867ABA5640, EVD-EA-051-URL-7889FF67F45A, EVD-EA-051-URL-9FE096EE4EF7, EVD-EA-051-URL-6ACAC33977CC, EVD-EA-051-URL-B669B429143C, EVD-EA-051-URL-66CB031FFA27, EVD-EA-051-URL-D66257F5E85E, EVD-EA-051-URL-0F5EEBDD1974, EVD-EA-051-URL-C10087515A45, EA-051-R11-RESEARCH, EA-051-R11-WEB-READBACK UNKNOWN_IDS: EA-051-UNKNOWN-01, EA-051-UNKNOWN-CURRENTNESS OPS_IDS: none ## Summary “OpenTelemetry and W3C Trace Context provide a strong interoperability substrate for AI telemetry, but AI-specific semantic conventions remain an evolving layer. As of 2026-09-14, OpenTelemetry’s GenAI conventions have moved to a dedicated repository and several agentic concepts remain under active development. OpenInference offers a complementary OpenTelemetry-based AI schema with broad model/tool/retrieval/agent/evaluation coverage. Enterprise deployments should pin and record schema versions, validate provider/language instrumentation coverage, and treat prompt/output capture as governed sensitive telemetry.” ## Current judgment - Stable common substrate and AI semantic layer must be separated. W3C Trace Context provides a mature cross-service propagation mechanism; OpenTelemetry provides transport/data-model/collector ecosystem. AI-specific semantics are moving faster and should be version-gated independently. - OpenTelemetry GenAI semantic conventions were split from the core semantic-conventions repository in 2026. The dedicated repository exposes a GenAI schema URL but, at the inspected releases page, no formal GitHub release exists. Therefore future-book wording must not imply a settled GA-level AI telemetry standard. - Current OpenTelemetry GenAI material covers not only inference but retrieval, memory, tool execution, agent/workflow/planning operations. This is sufficient to define a future Core trace topology, while individual attribute stability still requires per-version confirmation. - OpenInference is not an alternative transport to OpenTelemetry; it is an AI-specific semantic convention layer designed to ride on OpenTelemetry/OTLP. It already provides a broad span-kind taxonomy and evaluation/annotation concepts useful for production AI operations. - OpenTelemetry GenAI and OpenInference are overlapping but not identical schemas. Treating them as wire-compatible synonyms would be unsafe. An update should maintain an explicit mapping table and record the originating schema/version on telemetry. - Instrumentation maturity differs by provider/language. The cited OpenTelemetry Python GenAI issue demonstrates that even within the same project some integrations may emit different signal sets. “Uses OTel” does not prove equivalent observability coverage. - Agent hierarchy remains an active design area. Issue #94 records a missing generic grouping primitive for iterations/tasks/skills/phases, which limits generic reconstruction of complex agent trajectories. - Sensitive prompt/tool/output capture is a governance control, not a harmless debugging default. OpenInference exposes explicit masking knobs; the update should require capture policy, redaction policy and retention policy before enabling content-rich traces. ## Scope Enterprise AI Core / interoperability / observability / implementation / governance / security-privacy / provider mapping input ## Confirmed - Stable common substrate and AI semantic layer must be separated. W3C Trace Context provides a mature cross-service propagation mechanism; OpenTelemetry provides transport/data-model/collector ecosystem. AI-specific semantics are moving faster and should be version-gated independently. - OpenTelemetry GenAI semantic conventions were split from the core semantic-conventions repository in 2026. The dedicated repository exposes a GenAI schema URL but, at the inspected releases page, no formal GitHub release exists. Therefore future-book wording must not imply a settled GA-level AI telemetry standard. - Current OpenTelemetry GenAI material covers not only inference but retrieval, memory, tool execution, agent/workflow/planning operations. This is sufficient to define a future Core trace topology, while individual attribute stability still requires per-version confirmation. - OpenInference is not an alternative transport to OpenTelemetry; it is an AI-specific semantic convention layer designed to ride on OpenTelemetry/OTLP. It already provides a broad span-kind taxonomy and evaluation/annotation concepts useful for production AI operations. - OpenTelemetry GenAI and OpenInference are overlapping but not identical schemas. Treating them as wire-compatible synonyms would be unsafe. An update should maintain an explicit mapping table and record the originating schema/version on telemetry. - Instrumentation maturity differs by provider/language. The cited OpenTelemetry Python GenAI issue demonstrates that even within the same project some integrations may emit different signal sets. “Uses OTel” does not prove equivalent observability coverage. - Agent hierarchy remains an active design area. Issue #94 records a missing generic grouping primitive for iterations/tasks/skills/phases, which limits generic reconstruction of complex agent trajectories. - Sensitive prompt/tool/output capture is a governance control, not a harmless debugging default. OpenInference exposes explicit masking knobs; the update should require capture policy, redaction policy and retention policy before enabling content-rich traces. ## UNKNOWN - EA-051-UNKNOWN-01: first formal release/versioning policy of semantic-conventions-genai; convergence/divergence trajectory with OpenInference; provider-specific auto-instrumentation parity; stable representation for agent iteration/task grouping. - EA-051-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。 ## Evidence - EVD-EA-051-URL-6A0029787A22 (RESEARCH): author/org: W3C — https://www.w3.org/TR/trace-context/ - EVD-EA-051-URL-5E36EEBF9907 (RESEARCH): author/org: OpenTelemetry — https://opentelemetry.io/docs/specs/semconv/ - EVD-EA-051-URL-E45DC2C99A6D (RESEARCH): author/org: OpenTelemetry — https://github.com/open-telemetry/semantic-conventions-genai - EVD-EA-051-URL-B8771AA21367 (RESEARCH): version/revision: repository main; schema URL shown as — https://opentelemetry.io/schemas/gen-ai/1.42.0 - EVD-EA-051-URL-08867ABA5640 (RESEARCH): author/org: OpenTelemetry — https://github.com/open-telemetry/semantic-conventions-genai/releases - EVD-EA-051-URL-7889FF67F45A (RESEARCH): author/org: OpenTelemetry — https://github.com/open-telemetry/semantic-conventions-genai/blob/main/docs/gen-ai/gen-ai-spans.md - EVD-EA-051-URL-9FE096EE4EF7 (RESEARCH): author/org: OpenTelemetry — https://github.com/open-telemetry/semantic-conventions-genai/blob/main/docs/gen-ai/gen-ai-agent-spans.md - EVD-EA-051-URL-6ACAC33977CC (RESEARCH): author/org: Arize AI / OpenInference — https://arize-ai.github.io/openinference/spec/ - EVD-EA-051-URL-B669B429143C (RESEARCH): author/org: Arize AI / OpenInference — https://arize-ai.github.io/openinference/spec/semantic_conventions.html - EVD-EA-051-URL-66CB031FFA27 (RESEARCH): author/org: Arize AI / OpenInference — https://arize-ai.github.io/openinference/spec/configuration.html - EVD-EA-051-URL-D66257F5E85E (RESEARCH): author/org: OpenTelemetry semantic-conventions-genai contributors — https://github.com/open-telemetry/semantic-conventions-genai/issues/94 - EVD-EA-051-URL-0F5EEBDD1974 (RESEARCH): author/org: OpenTelemetry opentelemetry-python-genai contributors — https://github.com/open-telemetry/opentelemetry-python-genai/issues/98 - EVD-EA-051-URL-C10087515A45 (RESEARCH): author/org: Arize-ai/openinference contributors — https://github.com/Arize-ai/openinference/issues/3097 - EA-051-R11-RESEARCH (RESEARCH): EA-051 監査済みresearch / canonical revision binding - EA-051-R11-WEB-READBACK (IMPL): EA-051 Web body identity / canonical readback ## Failure / limits Repository main pages are moving targets; exact attribute names/status can change without product deployment changes. ## Failure / limits “No GitHub releases” is an as-of observation, not evidence that the project is unusable or unversioned in every distribution channel. ## Failure / limits OpenInference author docs establish its own intended semantics, not universal industry adoption. ## Failure / limits Issue reports establish concrete gaps in cited implementations/revisions, not defects in every language/provider/version. ## Failure / limits Trace completeness can fail at async boundaries, browser/desktop automation boundaries, external SaaS calls or components that do not propagate context. A trace backend cannot reconstruct events never instrumented. ## Failure / limits Capturing full model inputs/outputs can create PII, confidential-data, prompt-secret and retention exposure. Redaction after export may be too late. ## Failure / limits Sampling can distort rare-failure analysis and token/cost aggregation unless sampling semantics are accounted for. ## Failure / limits bounded initial packet complete. Reopen when dedicated OTel GenAI formal release/stability changes, mapping work begins, or a provider mapping requires exact attribute-level verification. --- ## Practice Language SDK support and auto-instrumentation coverage differ by runtime. ## Practice OpenTelemetry GenAI attribute/status/release availability must be rechecked at update publication time. ## Practice Provider SDK versions determine which token/cost/tool attributes are observable. ## Practice Collector/backend must preserve required attributes and W3C trace context across service boundaries. ## Practice Organization policy may prohibit payload-level prompt/output telemetry even where SDK capture is technically available. ## Practice Status: implementable now with maturity caveats. Recommended architecture: W3C Trace Context + OpenTelemetry SDK/OTLP/Collector as substrate; choose one AI semantic profile per instrumentation boundary; persist schema/profile version; map alternate schemas at collector/backend rather than silently mixing attribute names. Instrument at least model, retrieval, tool, agent/workflow and application/backend boundaries. Add evaluation signal separately from raw execution telemetry. ## Practice No benchmark score proves telemetry completeness. Validation should instead use a synthetic trace conformance test: execute a known model→retrieval→tool→model workflow; verify parent/child structure, context propagation, errors, retries, token metadata, evaluation attachment, redaction and sampling behavior. Repeat after instrumentation/provider SDK upgrades. ## Practice Security/privacy: classify prompts, completions, tool arguments/results and retrieved documents before capture; default to metadata-only where sensitivity is unknown. Redact before export when possible. Audit: preserve trace_id, span_id, schema/profile version, instrumentation library version, model/provider identifiers and evaluation provenance. Cost: token/cost attributes are useful but provider instrumentation coverage is uneven; billing records remain the financial source of truth unless independently reconciled. Operability: deploy schema-change detection and dashboards that tolerate missing optional attributes rather than assuming every provider emits identical fields. ## Practice At update time, recheck OpenTelemetry GenAI repository release/tag/schema status and per-section stability. ## Practice Build a mapping appendix: OTel GenAI ↔ OpenInference for model, retrieval, tool, agent/workflow, memory, evaluation and cost/token fields. ## Practice Add a provider/language coverage matrix based on concrete instrumentation releases, not project-level capability claims. ## Practice Define a minimal enterprise trace profile and synthetic conformance TEST_PROFILE. ## Practice Connect this packet directly to EA-052 AgentOps/AI-SRE and later provider mappings. ## Practice W3C Trace Context/OpenTelemetry core substrate must remain separate from evolving AI-specific semantic layers. OpenTelemetry semantic-conventions v1.44.0 moved GenAI content to the dedicated semantic-conventions-genai repository; GenAI conventions remain actively changing/development and require schema/version pinning. OpenTelemetry GenAI and OpenInference are overlapping but not interchangeable schemas. Preserve provider/language instrumentation gaps and all OPEN_UNKNOWN. ## WHY_THIS_MATTERS_TO_UPDATE Enterprise AIの本番運用では、単一providerのログ画面だけではmodel call、retrieval、tool、agent orchestration、application/backendを一つの因果系列として追跡できない。更新版では「OpenTelemetryで全部標準化済み」と単純化せず、W3C Trace Context / OpenTelemetry core / GenAI semantic conventions / OpenInference等の役割と成熟度を分離し、移行期の互換性・privacy・schema driftまで扱う必要がある。 ## SCOPE_ROUTING Enterprise AI Core / interoperability / observability / implementation / governance / security-privacy / provider mapping input ## CLAIM_OR_RESEARCH_QUESTION AI telemetryをprovider横断で構成する際、2026-09-14時点で何が安定した共通基盤で、何が発展途上のAI固有semantic layerか。OpenTelemetry GenAIとOpenInferenceはどこまで共通化でき、どこをschema/version gateとして扱うべきか。 ## EVIDENCE TABLE 1. source class: standard exact title: Trace Context author/org: W3C canonical URL: https://www.w3.org/TR/trace-context/ publication/update/access: W3C Recommendation 2020-02-06; accessed 2026-09-14 version/revision: Recommendation with editorial updates locator: traceparent / tracestate definitions; distributed trace context propagation evidence label: VERIFIED_SPEC relation: support/context 2. source class: official specification exact title: OpenTelemetry semantic conventions 1.44.0 author/org: OpenTelemetry canonical URL: https://opentelemetry.io/docs/specs/semconv/ publication/update/access: accessed 2026-09-14 version/revision: SemConv 1.44.0 page; GenAI section points to dedicated repository locator: “Generative AI: Moved to the OpenTelemetry GenAI semantic conventions repository.” evidence label: VERIFIED_SPEC / PRODUCT_VOLATILE relation: support/context 3. source class: author-maintained repository/spec exact title: OpenTelemetry GenAI Semantic Conventions author/org: OpenTelemetry canonical URL: https://github.com/open-telemetry/semantic-conventions-genai publication/update/access: accessed 2026-09-14 version/revision: repository main; schema URL shown as https://opentelemetry.io/schemas/gen-ai/1.42.0 locator: README; GenAI-specific spans, metrics, events, MCP/provider conventions evidence label: VERIFIED_SPEC / OSS_PRACTICE / PRODUCT_VOLATILE relation: support/context 4. source class: author-maintained repository release state exact title: Releases · open-telemetry/semantic-conventions-genai author/org: OpenTelemetry canonical URL: https://github.com/open-telemetry/semantic-conventions-genai/releases publication/update/access: accessed 2026-09-14 version/revision: no GitHub releases visible as of access date locator: releases page — “There aren’t any releases here” evidence label: OBSERVED / PRODUCT_VOLATILE relation: limit/counter 5. source class: official specification source exact title: Semantic conventions for generative client AI spans author/org: OpenTelemetry canonical URL: https://github.com/open-telemetry/semantic-conventions-genai/blob/main/docs/gen-ai/gen-ai-spans.md publication/update/access: accessed 2026-09-14 version/revision: repository main locator: page status “Development”; inference / embeddings / retrievals / fetch response / memory / execute tool spans evidence label: VERIFIED_SPEC / PRODUCT_VOLATILE relation: support/limit 6. source class: official specification source exact title: Semantic conventions for GenAI agent calls author/org: OpenTelemetry canonical URL: https://github.com/open-telemetry/semantic-conventions-genai/blob/main/docs/gen-ai/gen-ai-agent-spans.md publication/update/access: accessed 2026-09-14 version/revision: repository main locator: create agent / invoke workflow / plan span definitions and requirement language evidence label: VERIFIED_SPEC / PRODUCT_VOLATILE relation: support/context 7. source class: author-maintained specification exact title: OpenInference Specification author/org: Arize AI / OpenInference canonical URL: https://arize-ai.github.io/openinference/spec/ publication/update/access: accessed 2026-09-14 version/revision: current docs locator: OpenInference described as AI observability semantic conventions built on OpenTelemetry; LLM, agent, tool, retrieval, evaluation and privacy requirements evidence label: VERIFIED_SPEC / OSS_PRACTICE relation: support/context 8. source class: author-maintained specification exact title: Semantic Conventions | OpenInference author/org: Arize AI / OpenInference canonical URL: https://arize-ai.github.io/openinference/spec/semantic_conventions.html publication/update/access: accessed 2026-09-14 version/revision: current docs locator: span kinds LLM / EMBEDDING / CHAIN / RETRIEVER / RERANKER / TOOL / AGENT / GUARDRAIL / EVALUATOR / PROMPT; trace/session evaluations evidence label: VERIFIED_SPEC / OSS_PRACTICE relation: support 9. source class: author-maintained specification exact title: OpenInference Configuration author/org: Arize AI / OpenInference canonical URL: https://arize-ai.github.io/openinference/spec/configuration.html publication/update/access: accessed 2026-09-14 version/revision: current docs locator: OPENINFERENCE_HIDE_* controls and __REDACTED__ behavior; defaults documented as False for multiple capture-hiding switches evidence label: VERIFIED_SPEC / OSS_PRACTICE relation: support/limit/security 10. source class: author issue / failure-gap report exact title: Generic Grouping Attributes for Agentic Workflow Spans #94 author/org: OpenTelemetry semantic-conventions-genai contributors canonical URL: https://github.com/open-telemetry/semantic-conventions-genai/issues/94 publication/update/access: opened 2026-04-25; accessed 2026-09-14 version/revision: issue #94, open at indexed source locator: lack of standardized grouping for iterations/tasks/skills/phases in agentic workflows evidence label: SOURCE_REPORT / OSS_PRACTICE / PRODUCT_VOLATILE relation: counter/limit 11. source class: author issue / implementation-gap report exact title: Add metrics support to Anthropic & Groq GenAI instrumentations #98 author/org: OpenTelemetry opentelemetry-python-genai contributors canonical URL: https://github.com/open-telemetry/opentelemetry-python-genai/issues/98 publication/update/access: opened 2026-05-14; accessed 2026-09-14 version/revision: issue #98 locator: OpenAI v2 emits spans+metrics while cited Anthropic/Groq instrumentations emit spans without metrics evidence label: SOURCE_REPORT / OSS_PRACTICE / PRODUCT_VOLATILE relation: counter/limit 12. source class: author issue / schema-operability gap exact title: Publish Semantic Conventions in a Machine-Readable Format #3097 author/org: Arize-ai/openinference contributors canonical URL: https://github.com/Arize-ai/openinference/issues/3097 publication/update/access: opened 2026-05-13; accessed 2026-09-14 version/revision: issue #3097 locator: conventions defined in Markdown and manually re-declared across language packages; request for canonical machine-readable representation evidence label: SOURCE_REPORT / OSS_PRACTICE / PRODUCT_VOLATILE relation: counter/limit ## FINDINGS - Stable common substrate and AI semantic layer must be separated. W3C Trace Context provides a mature cross-service propagation mechanism; OpenTelemetry provides transport/data-model/collector ecosystem. AI-specific semantics are moving faster and should be version-gated independently. - OpenTelemetry GenAI semantic conventions were split from the core semantic-conventions repository in 2026. The dedicated repository exposes a GenAI schema URL but, at the inspected releases page, no formal GitHub release exists. Therefore future-book wording must not imply a settled GA-level AI telemetry standard. - Current OpenTelemetry GenAI material covers not only inference but retrieval, memory, tool execution, agent/workflow/planning operations. This is sufficient to define a future Core trace topology, while individual attribute stability still requires per-version confirmation. - OpenInference is not an alternative transport to OpenTelemetry; it is an AI-specific semantic convention layer designed to ride on OpenTelemetry/OTLP. It already provides a broad span-kind taxonomy and evaluation/annotation concepts useful for production AI operations. - OpenTelemetry GenAI and OpenInference are overlapping but not identical schemas. Treating them as wire-compatible synonyms would be unsafe. An update should maintain an explicit mapping table and record the originating schema/version on telemetry. - Instrumentation maturity differs by provider/language. The cited OpenTelemetry Python GenAI issue demonstrates that even within the same project some integrations may emit different signal sets. “Uses OTel” does not prove equivalent observability coverage. - Agent hierarchy remains an active design area. Issue #94 records a missing generic grouping primitive for iterations/tasks/skills/phases, which limits generic reconstruction of complex agent trajectories. - Sensitive prompt/tool/output capture is a governance control, not a harmless debugging default. OpenInference exposes explicit masking knobs; the update should require capture policy, redaction policy and retention policy before enabling content-rich traces. ## LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE - Repository main pages are moving targets; exact attribute names/status can change without product deployment changes. - “No GitHub releases” is an as-of observation, not evidence that the project is unusable or unversioned in every distribution channel. - OpenInference author docs establish its own intended semantics, not universal industry adoption. - Issue reports establish concrete gaps in cited implementations/revisions, not defects in every language/provider/version. - Trace completeness can fail at async boundaries, browser/desktop automation boundaries, external SaaS calls or components that do not propagate context. A trace backend cannot reconstruct events never instrumented. - Capturing full model inputs/outputs can create PII, confidential-data, prompt-secret and retention exposure. Redaction after export may be too late. - Sampling can distort rare-failure analysis and token/cost aggregation unless sampling semantics are accounted for. ## AVAILABILITY_GATES - Language SDK support and auto-instrumentation coverage differ by runtime. - OpenTelemetry GenAI attribute/status/release availability must be rechecked at update publication time. - Provider SDK versions determine which token/cost/tool attributes are observable. - Collector/backend must preserve required attributes and W3C trace context across service boundaries. - Organization policy may prohibit payload-level prompt/output telemetry even where SDK capture is technically available. ## IMPLEMENTATION_STATE Status: implementable now with maturity caveats. Recommended architecture: W3C Trace Context + OpenTelemetry SDK/OTLP/Collector as substrate; choose one AI semantic profile per instrumentation boundary; persist schema/profile version; map alternate schemas at collector/backend rather than silently mixing attribute names. Instrument at least model, retrieval, tool, agent/workflow and application/backend boundaries. Add evaluation signal separately from raw execution telemetry. ## BENCHMARK_OR_EVAL No benchmark score proves telemetry completeness. Validation should instead use a synthetic trace conformance test: execute a known model→retrieval→tool→model workflow; verify parent/child structure, context propagation, errors, retries, token metadata, evaluation attachment, redaction and sampling behavior. Repeat after instrumentation/provider SDK upgrades. ## SECURITY / PRIVACY / AUDIT / COST / OPERABILITY Security/privacy: classify prompts, completions, tool arguments/results and retrieved documents before capture; default to metadata-only where sensitivity is unknown. Redact before export when possible. Audit: preserve trace_id, span_id, schema/profile version, instrumentation library version, model/provider identifiers and evaluation provenance. Cost: token/cost attributes are useful but provider instrumentation coverage is uneven; billing records remain the financial source of truth unless independently reconciled. Operability: deploy schema-change detection and dashboards that tolerate missing optional attributes rather than assuming every provider emits identical fields. ## SAFE_WORDING_FOR_FUTURE_BOOK “OpenTelemetry and W3C Trace Context provide a strong interoperability substrate for AI telemetry, but AI-specific semantic conventions remain an evolving layer. As of 2026-09-14, OpenTelemetry’s GenAI conventions have moved to a dedicated repository and several agentic concepts remain under active development. OpenInference offers a complementary OpenTelemetry-based AI schema with broad model/tool/retrieval/agent/evaluation coverage. Enterprise deployments should pin and record schema versions, validate provider/language instrumentation coverage, and treat prompt/output capture as governed sensitive telemetry.” ## UPDATE_WORK_HANDOFF 1. At update time, recheck OpenTelemetry GenAI repository release/tag/schema status and per-section stability. 2. Build a mapping appendix: OTel GenAI ↔ OpenInference for model, retrieval, tool, agent/workflow, memory, evaluation and cost/token fields. 3. Add a provider/language coverage matrix based on concrete instrumentation releases, not project-level capability claims. 4. Define a minimal enterprise trace profile and synthetic conformance TEST_PROFILE. 5. Connect this packet directly to EA-052 AgentOps/AI-SRE and later provider mappings. ## OPEN_UNKNOWN first formal release/versioning policy of semantic-conventions-genai; convergence/divergence trajectory with OpenInference; provider-specific auto-instrumentation parity; stable representation for agent iteration/task grouping. ## STOP_CONDITION bounded initial packet complete. Reopen when dedicated OTel GenAI formal release/stability changes, mapping work begins, or a provider mapping requires exact attribute-level verification. --- ## AUDITED_BOUNDARY W3C Trace Context/OpenTelemetry core substrate must remain separate from evolving AI-specific semantic layers. OpenTelemetry semantic-conventions v1.44.0 moved GenAI content to the dedicated semantic-conventions-genai repository; GenAI conventions remain actively changing/development and require schema/version pinning. OpenTelemetry GenAI and OpenInference are overlapping but not interchangeable schemas. Preserve provider/language instrumentation gaps and all OPEN_UNKNOWN. NEXT: /agent/start.json STOP: This is a knowledge projection, not an execution order.