diff --git a/scripts/kb-eval/data/judge-pass-manifest.json b/scripts/kb-eval/data/judge-pass-manifest.json index fbe84e9..c4432b6 100644 --- a/scripts/kb-eval/data/judge-pass-manifest.json +++ b/scripts/kb-eval/data/judge-pass-manifest.json @@ -4,7 +4,7 @@ "derived_from": "scripts/kb-update/data/full-pass-worklist.json (243 due, all never-verified)", "cadence": "R7–R10 (5 økter × ~49, 8–10 samtidige)", "batch": "R7.1", - "count": 30, + "count": 45, "generated": "2026-07-18" }, "files": [ @@ -973,6 +973,454 @@ } ] }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 10, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#1", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/overview", + "evidence_quote": "Key phrase extraction retires from Azure Language on March 31, 2029.", + "reason": "The 2029-03-31 retirement of sentiment/opinion/custom-text-classification and the Foundry migration path check out, but the claim's load-bearing part that Key Phrase Extraction is unaffected is contradicted - its overview shows it also retires 2029-03-31.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "line": 8, + "claim": "Sentiment Analysis, Opinion Mining og Custom Text Classification avvikles 2029-03-31; PII Detection, Key Phrase Extraction og Language Detection er ikke berørt; migrasjonssti er Microsoft Foundry-modeller", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#4", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support", + "evidence_quote": "Total supported language codes: 94", + "reason": "The 94-language count is confirmed and Norwegian/Finnish/Swedish/Danish appear, but the full enumeration contains no Sami language, so the asserted Sami support is absent from the canonical list (R2).", + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "line": 66, + "claim": "Key Phrase Extraction støtter 94 språk (inkl. norsk, samisk, finsk, svensk, dansk); introduksjonen sier 94+ språk", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#7", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/language-service/custom-named-entity-recognition/how-to/use-containers", + "evidence_quote": "The free account is limited to 5,000 text records per month and only the Free and Standard pricing tiers are valid for containers.", + "reason": "Container docs explicitly allow the free (F0) tier ('the free (F0) or standard (S) pricing tier'), directly contradicting the claim that Standard S is required and F0 is unsupported for containers.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "line": 163, + "claim": "Docker-containere krever Standard S tier; Free F0 tier støttes ikke for containere", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#8", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/language-service/concepts/data-limits", + "evidence_quote": "All other preconfigured features (synchronous) | 5,120 as measured by StringInfo.LengthInTextElements", + "reason": "The synchronous per-document maximum is 5,120 characters and a text record is measured as 1,000 characters - neither matches the claimed '5000 characters per text record' (exact-value mismatch).", + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "line": 181, + "claim": "Maks 5000 tegn per text record; større dokumenter må splittes", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#9", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support", + "evidence_quote": "NorwayEast | Yes | Yes (Prediction supported)", + "reason": "NorwayEast (Oslo) is an enumerated supported region - fully supported for custom question answering and prediction-supported for CLU, Custom NER and Custom text classification, with preconfigured features available in all supported regions - contradicting the claim that Norway does not support Language Services.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md", + "line": 283, + "claim": "Azure Norway-datasentre (Oslo, Stavanger) støtter ikke Language Services per 2026-02; nærmeste regioner er West Europe (Nederland) og North Europe (Irland)", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speaker-recognition.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 8, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-speaker-recognition.md#8", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/speech-sdk", + "evidence_quote": "By downloading any of the Azure Speech in Foundry Tools SDKs, you acknowledge its license. For more information, see: - Microsoft software license terms for the Speech SDK", + "reason": "The Speech SDK is governed by proprietary 'Microsoft software license terms for the Speech SDK', not open source or MIT; the load-bearing open-source/MIT assertion is contradicted (only the separate GitHub code samples are open source).", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speaker-recognition.md", + "line": 403, + "claim": "Speech SDK er gratis, open source med MIT-lisens", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 14, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#3", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits", + "evidence_quote": "Maximum file size for audio input | Not applicable | 1 GB", + "reason": "The best-effort 30-min/24-hr scheduling and lexical+display output hold, but batch transcription has a documented 1 GB maximum file size, contradicting the claim's unlimited file size (ubegrenset filstoerrelse).", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md", + "line": 39, + "claim": "Batch transcription: asynkron prosessering 30 min - 24 timer (best-effort scheduling); output JSON med lexical + display form; ubegrenset filstørrelse", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#5", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create", + "evidence_quote": "Up to two channels are supported unless diarization is enabled... Diarization is only supported on single-channel (mono) audio.", + "reason": "The claim inverts the condition: the source states 2 channels are supported UNLESS diarization is enabled, and with diarization only mono (1 channel) is supported, so max 2 channels IF diarization enabled is contradicted.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md", + "line": 65, + "claim": "Speaker diarization: maksimalt 2 kanaler hvis diarization er aktivert; støttes ikke på tvers av flere kanaler samtidig", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#6", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create", + "evidence_quote": "The supported audio input locales with current multi-lingual model are: de-DE, en-AU, en-CA, en-GB, en-IN, en-US, es-ES, es-MX, fr-CA, fr-FR, it-IT, ja-JP, ko-KR, pt-BR, and zh-CN.", + "reason": "The 15-locale list matches exactly, but the multilingual model is documented as a generally available feature of the GA fast transcription API (no preview designation anywhere on the page), so the load-bearing preview status is wrong.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md", + "line": 74, + "claim": "Multi-lingual transcription er preview og støtter 15 språk: de-DE, en-AU, en-CA, en-GB, en-IN, en-US, es-ES, es-MX, fr-CA, fr-FR, it-IT, ja-JP, ko-KR, pt-BR, zh-CN", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 14, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#7", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis", + "evidence_quote": "The Batch synthesis API is generally available.", + "reason": "The load-bearing status part is wrong: the claim says the Batch Synthesis REST API is preview, but the page states it is generally available (the >10 min and REST-only parts hold, but R8 condemns the whole claim).", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md", + "line": 134, + "claim": "Batch Synthesis REST API er preview; for lange lydfiler (>10 min); real-time synthesis har <10 min audio-lengde og SDK-støtte, batch er REST API only", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#10", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/previous-year-release-notes", + "evidence_quote": "", + "reason": "No learn.microsoft.com page states that Azure Speech TTS is not native in M365 Copilot or that it integrates via Power Automate custom connectors; this is an unstated architectural assertion, so it cannot be confirmed or refuted.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md", + "line": 248, + "claim": "TTS er ikke native i M365 Copilot per januar 2026; integreres via custom connectors (Power Automate)", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#14", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/speech-services-quotas-and-limits", + "evidence_quote": "Maximum number of transactions per time period for standard voices and custom voices | 20 transactions per 60 seconds", + "reason": "The '0.5M characters/month' and 'S0 for production' parts hold, but the load-bearing figure '5 audio requests/month' is unsupported and contradicted: the F0 free tier is character-based (0.5M chars/month) with a rate limit of 20 transactions per 60 seconds, not a 5-request monthly cap.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md", + "line": 396, + "claim": "Free tier (F0): 5 audio requests/month og 0.5M characters/month; S0 tier for produksjon", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 11, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#7", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/overview", + "evidence_quote": "Custom Translator | Build customized models to translate domain- and industry-specific language | Custom Translator portal (https://portal.customtranslator.azure.ai/) . Tip: Use Microsoft Foundry (https://ai.azure.com/) for text and synchronous document translation operations via a no-code interface.", + "reason": "The no-code Custom Translator workflow (upload/BLEU/deploy) lives in the dedicated Custom Translator portal, not Microsoft Foundry; the docs explicitly scope Microsoft Foundry's no-code interface to text and synchronous document translation only, contradicting the load-bearing location assertion.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md", + "line": 194, + "claim": "Custom Translator er tilgjengelig i Microsoft Foundry (klassisk portal) for no-code workflows med document upload, BLEU-sammenligning og deployment management", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#9", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/foundry/responsible-ai/translator/data-privacy-security", + "evidence_quote": "", + "reason": "Translator's EU Data Boundary support exists via the European endpoint (a Microsoft commitment, not a 'certification'), but the canonical data/privacy page does not state that baseline NMT models are trained on global data or that custom models use only the customer's data, so those distinctive training-provenance assertions cannot be confirmed.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md", + "line": 228, + "claim": "Microsoft Translator har EU Data Boundary-sertifisering; baseline NMT-modeller er trent på global data, custom-modeller bruker kun kundens data", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#10", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/custom-translator/concepts/sentence-alignment", + "evidence_quote": "Free (F0) subscription training has a maximum limit of 2,000,000 characters.", + "reason": "The Free (F0) tier does support Custom Translator training (capped at 2,000,000 characters; and the free tier has the same features and functionality as the paid plans), contradicting the load-bearing claim that Custom Translator is not supported on F0.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md", + "line": 280, + "claim": "Custom Translator støttes ikke på Free (F0) tier (kun baseline-modeller); Standard (S1) gir full støtte med ubegrenset antall workspaces, projects og modeller", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 16, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#6", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/document-translation/overview", + "evidence_quote": "**Pricing**: Calculated on a per-image basis. For more information, see [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/translator).", + "reason": "Resource requirement (Foundry, not standalone Translator) and the translateTextWithinImage options parameter are confirmed, but the load-bearing 'additional cost based on Azure Vision pricing' is unsupported - Microsoft prices image translation per-image via the Translator pricing page, not Azure Vision pricing.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md", + "line": 70, + "claim": "Oversettelse av bildetekst i .docx/.pptx (batch) krever Azure AI Services multi-service resource (ikke standalone Translator) + parameter \"translateTextWithinImage\": true i options-feltet; tilleggskostnad basert på Azure Vision-prising", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#8", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/service-limits", + "evidence_quote": "Synchronous operation limits | Document size | <= 10 MB. Asynchronous (batch) operation limits | Document size | <= 40 MB.", + "reason": "Service limits set the synchronous document-size limit at <=10 MB, not <40 MB; 40 MB is the per-document batch limit, so the claimed sync/batch threshold is wrong.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md", + "line": 162, + "claim": "Synchronous single-file translation er egnet for filer < 40 MB (batch anbefalt for filstørrelse > 40 MB)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#13", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/solutions/translator-pro/overview", + "evidence_quote": "The app is currently available for Azure Translator resources created in the following regions ... Norway | Norway East (`norwayeast`)", + "reason": "Contradicted: the Azure Translator resource region list includes Norway East, so a Norway region does exist for Translator, refuting the claim that it does not.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md", + "line": 252, + "claim": "Norway-region finnes ikke for Translator — bruk West Europe eller North Europe for geografisk nærhet", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#16", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/document-translation/how-to-guides/use-rest-api-programmatically", + "evidence_quote": "\"summary\": { \"total\": 1, \"failed\": 0, \"success\": 0, \"inProgress\": 1, \"notYetStarted\": 0, \"cancelled\": 0, \"totalCharacterCharged\": 1355, \"totalImageScansSucceeded\": 2, \"totalImageScansFailed\": 0 }", + "reason": "totalCharacterCharged is returned inside the JSON response body 'summary' object, not in response headers as the claim's load-bearing location asserts.", + "file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md", + "line": 359, + "claim": "totalCharacterCharged returneres i response headers for cost tracking", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 16, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#5", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/data-factory/compute-linked-services", + "evidence_quote": "The Update Resource URL for an ML Studio (classic) Web Service endpoint used to update the predictive Web Service with trained model file", + "reason": "The Update Resource activity is an ML Studio (classic) web-service model-update mechanism (uploads a .ilearner trained model), not a batch/online-endpoint feature; the claim's 'batch endpoints only / online via ARM or SDK' framing mischaracterizes the activity.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 232, + "claim": "Azure ML Update Resource activity støtter kun batch endpoints; online endpoints krever ARM templates eller Azure ML SDK via Notebook Activity", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#8", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/power-platform/admin/security/secure-web-ai-gateway-agents", + "evidence_quote": "The following connectors currently support secure web and AI gateway Copilot Studio agents ... Azure Data Factory", + "reason": "An Azure Data Factory connector (first-party, Microsoft) is enumerated among connectors supported for Copilot Studio agents, contradicting the claim that Copilot Studio has no native Data Factory connector.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 297, + "claim": "Copilot Studio har ikke native Data Factory connector (per Feb 2026)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#9", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/data-factory/connector-overview", + "evidence_quote": "", + "reason": "No Learn page states that Data Factory can or cannot directly call AI Builder models; AI Builder is absent from the ADF connector list but a negative-existence claim cannot be grounded from silence.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 341, + "claim": "Data Factory kan ikke direkte kalle AI Builder-modeller (per Feb 2026)", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#10", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/data-factory/quickstart-create-data-factory", + "evidence_quote": "", + "reason": "The metadata-stored-in-region behavior is confirmed, but no fetched Learn page enumerates ADF's specific regional availability in Norway East/West (Norway West is a restricted region), so the region-support assertion is unverified.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 357, + "claim": "Azure Data Factory støtter Norway East/West regions (metadata lagres i region)", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#11", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/fabric/admin/region-availability", + "evidence_quote": "Europe | Norway West | (Power BI: yes) | (All Fabric workloads: no) | Power BI only region", + "reason": "Norway West is a Power BI-only region where all Fabric workloads are unavailable, so Fabric capacity is NOT available there, contradicting the load-bearing Norway West part of the claim.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 358, + "claim": "Fabric capacity er tilgjengelig i Norway West/East per Q1 2026 (OneLake-data residency følger capacity-region)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#14", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/data-factory/frequently-asked-questions", + "evidence_quote": "Azure Data Factory is certified for a range of compliance certifications, including SOC 1, 2, 3, HIPAA BAA, and HITRUST.", + "reason": "Azure Data Factory IS certified for HIPAA BAA, directly contradicting the claim's load-bearing assertion that ADF is not HIPAA BAA-compliant.", + "file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md", + "line": 605, + "claim": "Azure Data Factory er ikke HIPAA BAA-compliant (per Feb 2026); Azure Synapse Pipelines er HIPAA-certified (samme teknologi)", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 18, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#9", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "", + "evidence_quote": "", + "reason": "No learn.microsoft.com page states that Power Platform has (or lacks) built-in continuous LLM production evaluation; the negative gap assertion can be neither confirmed nor refuted.", + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "line": 667, + "claim": "Power Platform har ingen built-in continuous evaluation for LLM i production (gap per feb 2026)", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#10", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "", + "evidence_quote": "", + "reason": "No learn.microsoft.com page states a Q2 2026 Copilot Studio roadmap item for native Microsoft Foundry evaluation integration; the forward-looking roadmap claim is unverifiable and uncontradicted.", + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "line": 687, + "claim": "Copilot Studio: ingen out-of-the-box production evaluation; Microsoft roadmap (Q2 2026) inkluderer native integrasjon med Microsoft Foundry evaluation", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#12", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/ai-red-teaming-agent", + "evidence_quote": "Supported attack strategies: UnicodeConfusable, UnicodeSubstitution, Url, Jailbreak, Indirect Jailbreak, Tense, Multi turn, Crescendo", + "reason": "The capability and jailbreak strategy hold, but the load-bearing strategy names prompt_injection and bias_elicitation are absent from the documented supported attack strategies, so a stated part is wrong.", + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "line": 421, + "claim": "azure.ai.evaluation tilbyr AIRedTeamingAgent for automatiserte adversarial scans (attack strategies: jailbreak, prompt_injection, bias_elicitation)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#13", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme", + "evidence_quote": "Built-in evaluators are out of box evaluators provided by Microsoft: ... GroundednessEvaluator, RelevanceEvaluator, ... ViolenceEvaluator, SexualEvaluator, ... QAEvaluator, ContentSafetyEvaluator", + "reason": "The canonical azure.ai.evaluation SDK enumeration lists evaluators and simulators but contains no PIIMaskingPreprocessor; the named class is absent, so the existence claim is not grounded.", + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "line": 744, + "claim": "azure.ai.evaluation tilbyr PIIMaskingPreprocessor med mask_types (email, phone, ssn, name)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#18", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme", + "evidence_quote": "Azure AI Evaluation client library for Python - version 1.18.2", + "reason": "The live SDK reference states version 1.18.2, superseding the claimed v1.17.0.", + "file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md", + "line": 1125, + "claim": "Azure AI Evaluation SDK versjon v1.17.0 (per research-dato 2026-06-19)", + "disposition": "outdated" + } + ] + }, { "file": "skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md", "batch": "R7.1", @@ -983,6 +1431,41 @@ "verified_by": "judge-v3.1", "flags": [] }, + { + "file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 15, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/rag-architecture/azure-ai-search-setup.md#1", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity", + "evidence_quote": "Each index supports up to the following number of documents: 24 billion on Basic, S1, S2, and S3; 2 billion on S3 HD; 288 billion on L1; 576 billion on L2", + "reason": "Per-tier index counts (3/15/50/200/200/10) match the current Index limits table, but the claim per-tier document caps (15M/60M/120M/240M per partition) are legacy values superseded by the current flat 24-billion-per-index document limit - a load-bearing part is contradicted.", + "file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md", + "line": 37, + "claim": "Tier-grenser: Free 10 000 docs / 3 indekser | Basic 15M docs / 15 indekser | S1 60M per partition / 50 indekser | S2 120M per partition / 200 indekser | S3 240M per partition / 200 indekser | L1/L2 120M/240M per partition / 10 indekser", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/azure-ai-search-setup.md#12", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-region-support", + "evidence_quote": "You can create an Azure AI Search service in any of the following Azure public regions. ... [Europe: France Central, Germany West Central, Italy North, Norway East, North Europe, Poland Central, Spain Central, Sweden Central, Switzerland North, Switzerland West, UK South, UK West, West Europe]", + "reason": "Norway East appears in the canonical region enumeration but Norway West is absent - the claim that Azure AI Search supports Norway West is contradicted by its absence, so one load-bearing part of the multi-part region claim fails.", + "file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md", + "line": 300, + "claim": "Azure AI Search støtter Norway East og Norway West regioner (data lagres kun i Norge, ingen geo-replikering utenfor EU/EEA)", + "disposition": "outdated" + } + ] + }, { "file": "skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md", "batch": "R7.1", @@ -1053,6 +1536,239 @@ } ] }, + { + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 14, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#7", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/rest/api/searchservice/create-indexer", + "evidence_quote": "Default is source-specific (1000 for Azure SQL Database and Azure Cosmos DB, 10 for Azure Blob Storage).", + "reason": "The batchSize default is source-specific (1000 for SQL/Cosmos, 10 for Blob), not 1 as the claim asserts.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "line": 570, + "claim": "Indexer batchSize har default 1", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#9", + "judge_verdict": "not_grounded", + "rule": "R4", + "evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity", + "evidence_quote": "Before April 3, 2024 | 2 | 25 | 100 | 200 ... After May 17, 2024 | 15 | 160 | 512", + "reason": "Free 50 MB/3 indexes and index counts match, but Basic 2 GB and S1 25 GB match only the superseded pre-April-3-2024 storage row; current storage is 15 GB (Basic) and 160 GB (S1).", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "line": 612, + "claim": "Azure AI Search lagringsgrenser: Free 50 MB / 3 indexes | Basic 2 GB / 15 indexes | Standard S1 25 GB / 50 indexes", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#10", + "judge_verdict": "source_silent", + "rule": "", + "evidence_url": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", + "evidence_quote": "", + "reason": "The free-tier 500 pages/month allowance and S0 pay-as-you-go billing are pricing-page values; the authoritative service-limits page defers monthly allowances to the JS-rendered pricing page, so no authoritative Learn docs page states them verbatim.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "line": 616, + "claim": "Document Intelligence tiers: Free 500 sider/måned | Standard S0 pay-as-you-go", + "disposition": "unsourced" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#11", + "judge_verdict": "not_grounded", + "rule": "", + "evidence_url": "https://learn.microsoft.com/azure/foundry/responsible-ai/openai/limited-access", + "evidence_quote": "all Azure customers are eligible for access to Models sold by Azure ... so customers are not required to submit a registration form unless they are: (a) accessing a model sold by Azure designated as a Limited Access Service, or (b) requesting approval to modify Guardrails", + "reason": "Standard Azure OpenAI usage no longer requires an access application; the blanket requirement the claim asserts is superseded.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "line": 621, + "claim": "Azure OpenAI krever søknad om tilgang (compliance-vurdering)", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#14", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models", + "evidence_quote": "norwayeast is a supported Azure OpenAI region (row present in the model summary table and region availability)", + "reason": "Azure OpenAI is available in the Norway East region (Norway own data-residency Geo); the claim load-bearing West Europe region for Azure AI Services mechanism for Norway residency is wrong.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md", + "line": 625, + "claim": "Azure OpenAI i Norge: data residency i Norge (West Europe region for Azure AI Services)", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 9, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#1", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/whats-new", + "evidence_quote": "Groundedness detection public preview", + "reason": "Claim asserts detection is GA; What's New and the service-limits query-rate table both label it 'Groundedness detection (preview)' / 'public preview' (api-version and correction=preview parts hold, but the GA part is contradicted).", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md", + "line": 4, + "claim": "Groundedness-deteksjon: GA | groundedness correction/mitigating-feature: Preview, api-version 2024-09-15-preview", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#3", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/quickstart-groundedness", + "evidence_quote": "In your request to the groundedness detection API, set the 'mitigating' body parameter to true", + "reason": "domain/task/groundingSources/reasoning params all correct, but the current api-version's correction body parameter is named 'mitigating', not 'correction'; one load-bearing API field name is wrong.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md", + "line": 50, + "claim": "Groundedness Detection API-parametre: domain=MEDICAL|GENERIC, task=QnA|Summarization, groundingSources (array), reasoning true/false, correction true", + "disposition": "outdated" + }, + { + "id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#6", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/how-to/deployment-types#standard", + "evidence_quote": "SKU name in code: Standard ... SKU name in code: ProvisionedManaged", + "reason": "No Azure OpenAI 'E0' tier exists (deployment SKUs are Standard/GlobalStandard/ProvisionedManaged; Content Safety is F0/S0), and Azure AI Search RAG runs on Basic/Free so 'S1 or higher' is not required; load-bearing SKU parts are fabricated/overstated.", + "file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md", + "line": 316, + "claim": "Nødvendige ressurser: Azure OpenAI E0-tier | Azure AI Content Safety Standard tier (Groundedness Detection inkludert) | Azure AI Search S1 eller høyere for RAG-indexing", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 12, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-governance/monitoring-observability/alerting-strategies-escalation.md#2", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/fundamentals/service-limits", + "evidence_quote": "1,000 email actions in an action group.No more than 100 emails every hour for each email address per region.", + "reason": "1000 email actions per action group holds, but the rate limit is 100 emails/hour per email address per region, not 1000 emails/hour per action group; the load-bearing rate part is contradicted.", + "file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md", + "line": 49, + "claim": "Email-notifications: opptil 1000 mottakere per action group; rate limit 1000 emails per hour per action group", + "disposition": "outdated" + }, + { + "id": "ms-ai-governance/monitoring-observability/alerting-strategies-escalation.md#12", + "judge_verdict": "source_silent", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/best-practices-alerts", + "evidence_quote": "Azure Monitor activity alerts, service health alerts, and resource health alerts are free.", + "reason": "First part (activity/service health/resource health alerts free of charge) is grounded, but the load-bearing 'first 10 metric alert rules free per subscription' figure is stated on no official learn page (pricing is JS-rendered) and is not contradicted either, so the composite cannot be grounded.", + "file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md", + "line": 447, + "claim": "Activity Log alerts, Service Health alerts og Resource Health alerts er gratis (ingen kostnad per rule/evaluering); first 10 metric alert rules free per subscription", + "disposition": "unsourced" + } + ] + }, + { + "file": "skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 10, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-governance/monitoring-observability/security-and-audit-logging-ai.md#4", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/navigate-from-classic", + "evidence_quote": "Resource type | Azure OpenAI + Hub | Foundry Resource | Single AIServices kind with child projects. ... AI services | Azure AI Services | Foundry Tools", + "reason": "Defender AI threat protection/AI-SPM does support Azure OpenAI, but the load-bearing rename is contradicted: Foundry Resource (AIServices kind) was classically 'Azure OpenAI + Hub' and Foundry Tools is a distinct current term (classically 'Azure AI Services') - Foundry resource is not the new name for a previous Foundry Tools.", + "file": "skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md", + "line": 40, + "claim": "Microsoft Defender for Cloud AI threat protection + AI-SPM: støtter Azure OpenAI; konfigureres separat for Foundry-ressurser; «Foundry resource» (kind=AIServices) er nytt navn på tidligere «Foundry Tools»", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "flagged", + "claim_count": 9, + "verified": null, + "verified_by": null, + "flags": [ + { + "id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#5", + "judge_verdict": "not_grounded", + "rule": "R2", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/language-support#supported-languages", + "evidence_quote": "nb-NO Norwegian Bokmaal (Norway) supported", + "reason": "The canonical Speech-to-text locales enumeration lists nb-NO (Bokmaal) but contains no nn-NO (Nynorsk) row anywhere (nor in Custom speech or TTS tables); the claim asserts Azure AI Speech supports nynorsk (nn-NO), so one load-bearing part is absent from the enumeration (R2/R8).", + "file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md", + "line": 235, + "claim": "Azure AI Speech norsk språkstøtte: bokmål (nb-NO), nynorsk (nn-NO), Custom Speech for dialektvarianter; funksjoner: real-time transcription, speaker diarization, profanity filter/content moderation, batch-transkripsjon", + "disposition": "outdated" + }, + { + "id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#6", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/azure/ai-services/content-moderator/content-moderator", + "evidence_quote": "PII detection | Basic PII detection in text | Use Azure AI Language PII detection", + "reason": "Image Analysis captions, OCR, Face, and adult/racy/gory content moderation are all Vision features, but PII detection is an Azure AI Language capability, not an Azure AI Vision one (Vision overview enumerates only Face, Image Analysis, OCR); one stated load-bearing part is misattributed (R8).", + "file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md", + "line": 248, + "claim": "Azure AI Vision-kapabiliteter: Image Analysis API (beskrivende bildetekster), OCR, Face API (attributtgjenkjenning); innebygd content moderation og PII detection", + "disposition": "outdated" + }, + { + "id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#9", + "judge_verdict": "not_grounded", + "rule": "R8", + "evidence_url": "https://learn.microsoft.com/en-us/power-apps/maker/canvas-apps/accessible-apps", + "evidence_quote": "The following screen readers have been verified to work with Power Apps: JAWS... Narrator... NVDA...", + "reason": "Screen readers (Narrator/JAWS/NVDA) and keyboard-only navigation are confirmed, but high-contrast mode is absent from the canonical Power Apps canvas accessibility enumeration (which covers layout/color contrast ratios, keyboard, screen readers, controls, multimedia) and from the accessibility-limitations page; one stated load-bearing part is unsupported by the enumerating page (R8/R2).", + "file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md", + "line": 276, + "claim": "Power Apps støtter skjermlesere (Narrator, JAWS, NVDA), tastaturnavigasjon uten mus og høykontrast-modus", + "disposition": "outdated" + } + ] + }, + { + "file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md", + "batch": "R7.1", + "judged_at": "2026-07-18", + "per_file_verdict": "pass", + "claim_count": 6, + "verified": "2026-07-18", + "verified_by": "judge-v3.1", + "flags": [] + }, { "file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md", "batch": "R7.1", diff --git a/skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md b/skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md index 39cb774..54bedb2 100644 --- a/skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md +++ b/skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md @@ -7,6 +7,8 @@ **Type:** reference **Source:** https://learn.microsoft.com/azure/machine-learning/prompt-flow/migrate-prompt-flow-to-agent-framework **Status:** Established Practice +**Verified:** 2026-07-18 +**Verified by:** judge-v3.1 --- diff --git a/skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md b/skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md index 983a0da..8af587a 100644 --- a/skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md +++ b/skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md @@ -5,6 +5,8 @@ **Category:** Norwegian Public Sector AI Governance **Type:** reference **Source:** https://learn.microsoft.com/azure/cost-management-billing/costs/overview-cost-management +**Verified:** 2026-07-18 +**Verified by:** judge-v3.1 ---