e999b74eda
feat(ms-ai-architect): decision-b Enhet 1 — dialekt-relabel 51 filer (Kategori→Category + Sist oppdatert→Last updated), 73 byte-eksakte swaps [skip-docs]
...
Ren value-preserving label-relabel av de to norske header-labelene til engelsk på 51 ref-filer (22 bærer begge). Ny testet ren primitiv relabelHeaderDialect() (header-blokk-scoped, kollisjons-/multiforekomst-guard) + manifest-drevet driver relabel-dialect.mjs (frosset 51-fil-manifest, hard per-fil-invariant, idempotent, isMain-guard). **Dato:** bevisst UTE (body-template-felle → Enhet 2). Premiss-korreksjon i roadmap R22: tredje Dato-dialekt (16), 0 bold-duplikater (ikke 4), 1 datoløs (ikke 5), category-none = vindus-artefakt. test-relabel-dialect 11/11; diff +73/-73 0 linjer utover label; suite 782/782 exit 0.
2026-07-06 10:07:52 +02:00
5a0e8d774a
feat(ms-ai-architect): R21 — Status-backfill på 14 advisor-ref-filer (redusert scope etter premiss-korreksjon) [skip-docs]
...
Manifest-drevet applier (scripts/kb-update/backfill-status.mjs) over den testede
insertMetaField-primitiven + ny ren regel statusForFile (filnavn-token → Reference/
Established Practice, operatør-godkjent vokabular). 7 Reference + 7 Established Practice.
Hard per-fil-invariant (én linje, body byte-identisk), idempotent, isMain-guard. 7 tester.
Premiss-korreksjon (auditHeaders, ground-truth 2026-07-06): ekte not-due-restanse er
21 Status + 26 Last-updated (STATE sa 21/22). «0 har norsk dato» var falskt — 21/26
Last-updated-gap bærer allerede Sist oppdatert/Dato → relabel-residual; 5 datoløse gir
«i dag» ved naiv git → utsatt. 4 dual-header ai-act-*-filer med plain-text «Status: GA»
fanget i diff-inspeksjon → revertert (unngår duplikat/motsigelse) → residual (samme
plain-blokk ga R20 duplikat Category). Korrigert residual logget i roadmap §R21.
Verifisering: test-backfill-status 7/7; git diff +14/-0 (kun Status-linjer, body
byte-identisk); not-due Status-missing 21→3; full suite 771/771 exit 0.
2026-07-06 09:41:40 +02:00
a583599ab1
feat(ms-ai-architect): R20 — Category-backfill på 25 kategorisløse ref-filer via insertMetaField [skip-docs]
...
Ny testet primitiv transform.insertMetaField (anker + 500B-back-off som insertHeaderFields, idempotent på eksakt label, body byte-identisk; 6 tester) + backfill-category.mjs (deterministisk folder->category-regel, hard per-fil-invariant, insert-only, aborterer for skriving ved avvik).
Fordeling: 14 Solution Architecture & Advisory (architecture/), 6 Microsoft AI Platforms (platforms/+development/), 4 Responsible AI & Governance, 1 MLOps & GenAIOps. Label = engelsk Category (322 vs 42 Kategori). Eksisterende recommended-mcp-servers/rag-maturity-model urort.
Roadmap: R20 done + R21 (Status/Last-updated not-due) encoded. Verifisering: 0 kategorislose filer (var 25); diff +25/-0; idempotent re-run; suite 764/764 exit 0.
2026-07-06 07:39:54 +02:00
36fd4cfe7b
fix(ms-ai-architect): R5 G5b — 4 innholds-fikser (retired gpt-35-turbo→gpt-4o-mini, vector-quant GA 2024-07-01, 2 overclaims nyansert), hver live-verifisert per MS Learn-kilde [skip-docs]
2026-07-04 17:09:23 +02:00
83fd9b58d3
fix(ms-ai-architect): ✅ Verified → ✅ Documented (tillit-hygiene)
...
Markøren over-påsto ekstern verifisering; faktisk semantikk (per legend i
m365-copilot-plugins-ecosystem.md) er «hentet fra MS Learn via MCP» = Documented.
Smal scope (operatør-besluttet A): de 101 ✅ Verified-konfidens-cellene i 13 filer
+ 5 kolonne-overskrifter (ptu, agent-memory) + skill-gen-taksonomien
(Verified/Baseline/Assumed → Documented/Baseline/Assumed) + licensing-seksjonstittel.
La de 137 plain «Verified»-cellene i 31 kilde-attribusjons-tabeller stå — de peker
på en faktisk kilde i nabokolonnen (proveniens bevart). Suite 509/509.
2026-06-26 12:31:45 +02:00
2b0d37f370
docs(ms-ai-architect): KB-refresh LOW 50/52 — adr-template: TRYGT (PTU/EUDB/data residency re-verifisert, header-bump)
2026-06-24 13:36:33 +02:00
00af7de1b1
docs(ms-ai-architect): KB-refresh LOW 49/52 — public-sector-checklist: AI Act norsk ikrafttredelse mykgjort (forsinket, 2 steder) + header/footer-bump
2026-06-24 13:36:33 +02:00
e5351c0eb1
docs(ms-ai-architect): KB-refresh LOW 48/52 — licensing-matrix: TRYGT (AI Builder-retirement/Copilot Credits/E7 re-verifisert, header-bump)
2026-06-24 13:36:33 +02:00
7022d622e2
docs(ms-ai-architect): KB-refresh LOW 47/52 — poc-template: TRYGT (header-bump + fjernet 2026-01-XX placeholder)
2026-06-24 13:36:32 +02:00
fc40e4e9e5
docs(ms-ai-architect): KB-refresh LOW 46/52 — migration-patterns: seksjon 6 korrigert (Agent Framework = egen SDK agent-framework, ikke SK-namespace) + Copilot Credits + api_version
2026-06-24 13:36:32 +02:00
a306993f62
docs(ms-ai-architect): KB-refresh LOW 45/52 — regional-availability-verification: TRYGT (Norway East/Sweden Central-tabeller re-verifisert mot live MS Learn, header-bump)
2026-06-24 13:36:32 +02:00
8d52d582b2
docs(ms-ai-architect): KB-refresh LOW 44/52 — ai-utredning-template: AI Act norsk lov-tidslinje mykgjort (forsinket pga EØS) + Foundry URL ai-studio→foundry
2026-06-24 13:36:32 +02:00
104d8c035d
docs(ms-ai-architect): KB-refresh step0 — security.md verifisert mot MS Learn + maskinlesbar header (Hate and Fairness, CMK RBAC-primær; unverified 1→0)
2026-06-24 10:44:34 +02:00
03d596e4ec
docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer)
...
Verifisert mot offisiell MS-doc (juni 2026): «Microsoft Foundry» er det
gjeldende produkt-/portalnavnet; «Foundry (classic)» = gamle «Azure AI Foundry»
(/azure/foundry/ vs /azure/foundry-classic/). Premiss bekreftet før sveip.
Multi-regel, IKKE naiv s/Azure AI Foundry/Microsoft Foundry/ — MS dropper
«Azure AI» (legger IKKE til «Microsoft») for to produktvarianter:
- «Azure AI Foundry Agent[ Service|s]» → «Foundry Agent Service/Agents» (MS-form)
- «Azure AI Foundry Models» → «Foundry Models» (i «Azure OpenAI in Foundry Models»)
- «Azure AI Foundry SDK» → «Microsoft Foundry SDK» (operatør-valg)
- «Azure AI Foundry portal/project» + generisk → «Microsoft Foundry»
- Pre-eksisterende «Microsoft Foundry Models» (4) normalisert → «Foundry Models»
Bevart: «Azure OpenAI», «Azure AI Inference SDK», «Azure AI Search»,
«Azure AI Services», kode-IDer. Historisk ref «(tidligere Azure AI Foundry)»
i model-catalog-2026.md beskyttet via lookbehind. URL /azure/ai-foundry/→
/azure/foundry/ kun i owasp-llm-top10 (KB-ref); docs/-filer deferred.
Scope: skills (inkl. 3 SKILL.md) + commands + agents + README + CLAUDE.
Ekskludert: docs/ (interne), playground/+tests/ fixtures (testdata),
CHANGELOG.md (historisk logg), STATE.md (gitignored).
3 SKILL.md endret (advisor/engineering/security) → judge-cache teknisk
invalidert for disse, men scorer uendret: advisor 91, eng/gov/infra/sec 96
(alle ≥90). validate 239/0. 0 «Azure AI Foundry» igjen (utenom bevart ref).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:00:27 +02:00
e406ef395e
feat(ms-ai-architect): #8b currency M-items — Defender AI threat protection + OWASP LLM04/06/08/09 + M365 E7/Agent 365 + Foundry Local air-gapped
...
Phase B (M-items) av #8 currency-rest. Nytt innhold, verifisert mot
Microsoft Learn + OWASP GenAI 2026-06-18 (tre research-subagenter).
Begge nye KB-filer wiret i SKILL.md (de-orphan bekreftet: kb-integrity
115/115, orphan-warnings uendret 262).
Nye KB-filer (ms-ai-security/references/ai-security-engineering/):
- owasp-llm-top10-azure-mitigations.md — konsolidert dekning av de fire
OWASP 2025-kategoriene som manglet referanse i SKILL.md-mappingen
(LLM04 Data/Model Poisoning, LLM06 Excessive Agency, LLM08 Vector/
Embedding Weaknesses, LLM09 Misinformation) med verifiserte Azure-tiltak.
OWASP-side 404 for LLM06/08/09 → definisjoner kryssverifisert, merket.
- defender-threat-protection-ai-services.md — Defender for Cloud «AI threat
protection» (gjeldende navn; plan «Defender for AI Services»). GA for
AI applications, Preview for AI agents (fra 2026-02-02). Varselliste m/
Alert ID + MITRE-taktikk, Prompt Shields-integrasjon, prising (75B-token
trial). KRITISK: ikke tilgjengelig i Azure Government (norsk off. sektor).
SKILL.md (ms-ai-security):
- Fylte de 4 «—»-radene LLM04/06/08/09 → owasp-llm-top10-azure-mitigations.md.
- La til Defender-referanse (kjøretids-trusseldeteksjon) + Government-forbehold.
- Fil-telling ai-security-engineering 17→22 (17 var stale; faktisk 20 + 2 nye).
licensing-matrix.md (ms-ai-advisor):
- Ny rad «Microsoft 365 E7» i master-matrisen + dedikert E7/Agent 365-seksjon.
E7 (GA 2026-05-01) bundler E5 + M365 Copilot + Agent 365 + Entra Suite.
Agent 365 = IT-admin kontrollplan (registry/Entra Agent ID/Defender/Purview).
VERIFISERT at begge er reelle SKU-er. Priser (~$99 E7 / ~$15 Agent 365) er
community-/partnerkilder → eksplisitt merket uverifisert.
disconnected-ai-scenarios.md (ms-ai-infrastructure):
- Ny seksjon «Foundry Local — generativt lokalt og air-gapped». To produkter:
on-device (offline etter nedlasting, ingen Azure-sub) + on Azure Local
(Arc/Kubernetes, Preview). Air-gapped/disconnected støttet fra juni 2026
(Preview): edgeartifacts-registry, expansion packs, lokal AD, ingen
telemetri. Del av Microsoft Sovereign Private Cloud — relevant for norsk
suverenitet.
Tester: validate-plugin 239 PASS / 0 FAIL / 0 WARN · kb-integrity 115/115
(262 pre-eksisterende orphan-warnings, uendret) · run-e2e alle suiter PASS.
#8 nå komplett (S-bannere #8a + M-items #8b). Neste: #9 v1.16.0 release.
FLAGG: `/architect:kb-update` apply forblir UTSATT (krever egen bekreftelse).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 20:32:43 +02:00
dd1036ab8a
fix(ms-ai-architect): Foundry URL-navnerom-migrering (ai-foundry → foundry/foundry-classic, 141 filer)
...
Task #5 del 1/3 (URL-migrering). Verifiseringen motbeviste STATE.md-premisset om ren prefix-swap: rebrand er per-URL, ikke mekanisk. En blind sed ai-foundry→foundry ville lagd 56 nye 404-er (classic-stiene finnes ikke under nytt foundry/-prefiks — bekreftet empirisk).
Metode: resolverte alle 237 unike KB-URLer mot live redirects (curl -L), bygde full-URL→full-URL-mapping fra faktisk url_effective. Bevarer locale-form, query (?view=) og #fragment per lenke.
- 231 navnerom-erstatninger over 141 filer (408 forekomster):
- 161 → azure/foundry/ (98 ren prefix-swap + 10 sti-reorg + reorg-tilfeller)
- 69 → azure/foundry-classic/ (eldre hub-spor: assistants, hub-DR, on-your-data; faktisk redirect-mål per operatorvalg)
- 1 → azure/foundry-local/
- 2 døde lenker (404) fikset til verifiserte mål:
- agent-service → azure/foundry/agents/overview
- concepts/evaluation-evaluators/ → azure/foundry/how-to/evaluate-generative-ai-app
- 5 path-/display-referanser (uten https://, i backticks/lenketekst) rettet manuelt.
- 6 slug-baserte ai-foundry-treff urørt (scope-grense): managed-grafana-dashboard, security-baseline, power-platform prompt-builder, architecture baseline-chat (sistnevnte slug-rebrand i annet navnerom — mulig fremtidig funn).
- Parkert til task #5 del 2/3: Norway East GPT-5-datasuverenitet-fiks + modellkatalog-utvidelse (5.3/5.4/5.5, gpt-oss, sora-2).
Verifisert: 0 gjenværende azure/ai-foundry/-navnerom i skills/. validate-plugin.sh 219 PASS. test-kb-integrity.sh 117/117 passed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 13:37:06 +02:00
84e3cfaa03
fix(ms-ai-architect): re-baseline kostnadslaget (GPT-5 $1.25/$10, én prissannhet, 10 filer)
...
Audit-funn Tema B + action-items 149/150. Verifiseringen avdekket at kostnadslag-råten var bredere enn auditens 3 navngitte filer (10 filer totalt).
- GPT-5 flagship $10-15/$40-60 -> $1.25/$10.00 (verifisert juni 2026, 8-12x for hoy). gpt-5-mini $0.25/$2.00, gpt-5-nano $0.05/$0.40. Fjernet falske "Verified MCP"-stempel pa estimat-band.
- deterministic-cost-calculation-model.md gjort til ENESTE kanoniske prissannhet (§1.1). Strippet duplikat pris-tabell fra cost-models.md (rotarsak til GPT-4o $10/$30-motsetning) -> peker til registeret.
- Reconcile-funn utover audit: deterministic hadde GPT-4.1-serien HALVERT ($1/$4 og $0.20/$0.80) -> verifisert $2.00/$8.00 og $0.40/$1.60. multi-model-strategy-costs.md NOK-tabell var fabrikkert 10-47x for hoy (gpt-4o 250/1000 NOK -> 26/105). model-selection (GPT-5 $3/$12), reasoning-models (GPT-5 $20-30/$80-100), token-counting (gpt-4.1 cached $1->$0.50), small-language-models (GPT-4o output 60->105 NOK) rettet.
- Recalk alle NOK-scenarioer reproduserbart: gpt-5 ~= gpt-4.1 i kost (ikke 30-55x dyrere som gammel tekst pasto) - billigere input ($1.25 vs $2.00), dyrere output. Reell kostnadsdriver = resonnerings-tokens (fakturert som output).
- Fjernet GPT-3.5 Turbo-anbefaling (utfaset). Alignet kurs 11->10.5 NOK/USD i cost-kommando. Cost-agent eksempel: legacy GPT-4 -> GPT-4o-mini, fjernet falskt Verified-stempel.
- kb-update apply cost-bucket deferret til task #8 (kommando-feature, ikke tall-justering).
Verifisert mot OpenAI API pricing + Azure OpenAI pricing via WebSearch 2026-06-18. validate-plugin.sh 219 PASS.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 12:45:21 +02:00
Kjell Tore Guttormsen
781d98f62f
chore(privacy): scrub real-org references from plugin internals (phase 2)
...
Same bulk replacement applied to plugin-internal KB, examples, fixtures,
tests, and docs. Real organization names, persona names, internal system
identifiers, and domain-specific terms replaced with fictional generic
public-sector entity (DDT) and generic terminology.
Scope:
- okr/ — examples, governance, framework, integrations, sources
- ms-ai-architect/ — KB references (engineering, governance, security,
infrastructure, advisor), tests/fixtures, agents, docs
- linkedin-thought-leadership/ — voice samples, network-builder,
examples (genericized identifying headlines to "[your organization]")
- llm-security/ — research notes, scan report
Manual genericization beyond bulk replace:
- okr SKILL.md "Primary user / Domain" — generic Norwegian public sector
- linkedin-voice SKILL.md headline placeholder
- network-builder.md headline placeholder
- high-engagement-posts.md voice sample employer line + hashtag
Phase 3 (factual-attribution review) remains: a few KB files attribute
publicly known transport-sector docs/datasets (e.g. håndbok V440, NVDB)
to the fictional DDT after bulk replace. Needs manual semantic review
to either remove or restore correct citation without re-introducing
affiliation references.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-03 04:28:15 +02:00
Kjell Tore Guttormsen
565043dbde
docs(architect): weekly KB update — 66 files refreshed (2026-04)
...
Updated 66 stale knowledge base reference files (10 critical, 56 high)
across all 5 skills using Microsoft Learn MCP research.
Key factual updates:
- Groundedness Detection API: `correction` → `mitigating` param,
`correctedText` → `correctionText` (breaking change)
- Copilot Studio: GPT-4.1 mini now default (was GPT-4o mini);
Claude Sonnet 4.5 + Opus 4.5 added (experimental, 200K ctx)
- Agentic Retrieval: still public preview; 50M free tokens/month
- Azure security baselines: "Cognitive Services" → "Foundry Tools"
- Databricks: Delta Live Tables → Lakeflow Spark Declarative Pipelines
- MLflow 3 GenAI: new Feedback/Expectation data model
- Token tracking doc: "Azure OpenAI in Foundry Models through a gateway"
- Agent Registry: Risks column (M365 E7), Graph API (preview)
- Copilot DLP: new Entra AI Admin + Purview Data Security AI Admin roles
- ISO/IEC 42001: scope expanded to M365 Copilot, Foundry, Security Copilot
- Zero Trust: CAE now via Conditional Access, Strict Location Enforcement
- Purview: new Fabric Copilots/agents governance section
- AG-UI HITL: ApprovalRequiredAIFunction (C#), @tool approval_mode (Python)
All files: Last updated → 2026-04, *(Verified MCP 2026-04)* markers added.
Build registry: 1341 URLs from 387 files (+2 new URLs).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-09 22:41:26 +02:00
Kjell Tore Guttormsen
baa2d0220b
feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command
...
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.
New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.
Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.
Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 08:58:35 +02:00
