feat(ms-ai-architect): #27-#28 ratifisert — og programmet skrev sitt forste malte tall

To entries anvendt, to nye former ratifisert. Begge valg er samme regel sett
fra hver sin side: SLETT DER SLETTING ER GRATIS, RETT DER SLETTING KOSTER SANN
OG UNIK INFORMASJON. At de ser motsatte ut er et utslag av hva malingen viste,
ikke av to ulike prinsipper.

#27 — REFERENT-ORD SOM FELTNAVNET ALLEREDE BAERER. GOVERNS idx-26t.
  agent-to-agent-a2a-protocol.md:732
  FOR:   **Total sources cited:** 10 unike URLer fra MCP-research + tavily-research
  ETTER: **Total sources cited:** 10 fra MCP-research + tavily-research
  Slettet 12 sammenhengende tegn, null ord forfattet, tellingen urort.
  Alle tre #25-vilkar malt: resten grammatisk, 10 grunnet i de 10 nummererte
  entries, null forfatting. #25s SCOPE naadde likevel ikke — ingenting som
  fjernes her er en delete-klasse-telling.

#28 — KEEP-KLASSE-TELLING DER DEN SANNE HALVDELEN ER BADE SANN OG UNIK.
  GOVERNS idx-26at. Dette er #23s uttrykkelig URATIFISERTE residualtilfelle,
  som #23 sendte tilbake som nytt spoersmaal. Foerste instans, na avgjort.
  rag-document-preprocessing.md:791
  FOR:   ... 8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**
  ETTER: ... 8 Microsoft Learn-artikler + 2 GitHub-repos = **10 kilder**

DETTE ER FOERSTE GANG PROGRAMMET HAR SKREVET ET TALL DET HAR MALT.
Operatoerbeslutning 2026-08-12, stilt som noeyaktig det spoersmaalet. Til na
har hver resolution slettet, paa idx-26v-grunnen at en reparasjon ikke skal
forfatte defektklassen den lukker. Den grunnen star fortsatt der sletting er
GRATIS — derfor sletter idx-26t i samme oekt. Den slutter aa staa der sletting
oedelegger en sann og unik paastand, for da er taushet ikke det billige valget,
men en defekt nummer to.

MALT FOER VALGET BLE LAGT FRAM, ikke etter:
 - 8 distinkte Learn-artikler etter /en-us-normalisering: SANT som skrevet.
 - 2 distinkte github.com-URLer, ikke 4. Altsa 10 navngitte kilder, ikke 12.
 - «8 Microsoft Learn-artikler» forekommer INGEN ANDRE STEDER i fila — det er
   det som gjoer sletting dyr her og gratis alle tidligere ganger.

TO PREMISSER FRA STATE VAR USANNE, begge fanget for handling:
 1. «idx-26t er ordrett samme form som idx-26w» — nei. STATEs gjengivelse
    droppet «+ tavily-research», og det er nettopp det #21 dreier seg om.
    Kvalifikatoren overklaimer IKKE her: den navngir web-benet som dekker de
    fire ikke-Learn-URLene. Bokfort i egen commit (2ba3cee).
 2. «rag-document-preprocessing.md:792» — linja star paa :791. Ankere er
    ordrette strenger, saa ingenting hang paa det; korrigert i entryen.

RESIDU-SVEIP VED EDITSTEDET, som metoden krever — og den fant noe verdt aa
male: rag-fila SLUTTER IKKE ved footeren, en seksjon foelger paa :795-803. En
footer-total kunne dermed vaert malt over feil spenn. MALT: NULL Learn- eller
GitHub-URLer forekommer etter :791; alle 11 forekomster ligger foran. Tallet
dekker det det paastar. a2a-fila har ingen residu — linja er na siste linje.

Ko: 54 entries (11 apne, 43 resolved). Suite 1052/1052.
MERK ÆRLIG: suiten beviser ikke disse editene. Resolved entries er unntatt
ankersjekk, saa den ville passert uansett. Beviset er hel-linje-sammenligningen:
for-linja 0x, etter-linja 1x, i begge filer.

scripts/kb-eval/data/g7-review-queue.json

@@ -13,7 +13,9 @@
       "#23": "A LINE THAT MIXES THE DELETE CLASS AND THE KEEP CLASS. Ratified 2026-08-11.\nTHE FORM: do NOT split the line. MEASURE the keep-class half against the file first, then DELETE THE WHOLE LINE.\nWHY THAT LOSES NOTHING - measured in both members rather than argued:\n - idx-26ao, genaiops-llm-specific-practices.md:383. \"18 kilder\" is TRUE (18 numbered sources) and restated TWICE more, at :6 in the header block and at :356 in the heading \"### Microsoft Learn-kilder (18 dokumenter)\". Deletion removes nothing the file does not still say.\n - idx-26z, chain-of-thought-prompting.md:500. \"3 unike Microsoft Learn-kilder\" is FALSE - the file's own \"### Microsoft Learn (Verified via MCP)\" table has 5 rows and 5 distinct Learn URLs. \"4 MCP-kall\" is also wrong against 3 enumerated. BOTH numbers in that line are wrong, so splitting it would have preserved a falsehood.\nTHE POINT: the hazard was that deletion takes a true claim with it. MEASUREMENT DISSOLVES THE HAZARD instead of trading it for authoring. Where the keep half is redundant, deletion is free; where it is false, deletion is a correction.\nNOT RATIFIED, BECAUSE NOT INSTANTIATED: the residual case where a keep half is BOTH true AND unique in its file. Neither member is that case. A future member that is must come back as a new question rather than inherit this form.\nGOVERNS: idx-26z, idx-26ao. idx-26ao ALSO falls under #22 - the heading and the three call bullets above its line go in the SAME edit, or the deletion produces the idx-26aq residue.",
       "#24": "A DELETE-CLASS COUNT RESTATED IN THE DOCUMENT HEADER BLOCK. Ratified 2026-08-11.\nTHE FORM: delete the whole parenthetical \"(8 MCP-oppslag, 16 kilder)\" at mlops-security-access-control.md:5, leaving \"**Confidence:** HIGH - Basert paa offisiell Microsoft Learn dokumentasjon\".\nTHE MEASUREMENT THAT TURNED A RE-AUTHORING INTO A DELETION: the header was treated as mixed - one delete-class half, one keep-class half - which would have forced a rewrite inside the reference contract's structured header. It is NOT mixed. \"16 kilder\" is FALSE: the file enumerates 8 numbered sources and carries 10 distinct URLs, 9 of them on learn.microsoft.com. No reading yields 16. \"8 MCP-oppslag\" is unverifiable on the idx-26j ground. BOTH halves fail, so there is nothing to preserve and no replacement to write. What remains asserts no count and is grounded.\nZERO WORDS AUTHORED - the header keeps its field name and its claim; only the false and the unverifiable are removed.\nGOVERNS: idx-26ap, whose second locator (the footer \"**MCP Calls:** 8\" at :744) is deleted by the idx-26j form in the same edit.",
       "#25": "A DELETE-CLASS COUNT RESTATED INSIDE A LINE. Ratified 2026-08-12. Widens #24 from the single header parenthetical it was written for to any in-line restatement - header field OR running prose.\nTHE FORM: delete the CONTIGUOUS delete-class fragment and leave the rest byte-identical. Three conditions, ALL MEASURED rather than assumed: (1) the remainder is grammatical, (2) the remainder is grounded in what the file itself lists, (3) zero words are authored.\nWHY IT IS NOT A REWRITE - which is what idx-26ab's own booking called it. At inferencing-optimization-caching.md:1029 the fragment is \"12 MCP-kall til \", 16 contiguous characters. Removing them leaves \"**Confidence niva: HIGH** - Denne referansen er basert pa offisiell Microsoft-dokumentasjon og kodeeksempler.\", a grammatical Norwegian sentence whose claim the file's own 8 numbered sources and 20 fenced code blocks carry. Nothing is composed. The booking's premise was falsified by writing the resulting string out and reading it, not by argument - the same move that turned #24 from a re-authoring into a deletion.\nTHE LIMIT, which is what keeps this from swallowing the corpus: where the three conditions do not ALL hold, this form does not apply and the case comes back as a new question. A remainder that needs one word added is authoring, and authoring is the idx-26v hazard.\nGOVERNS: idx-26ab.",
-      "#26": "AN UNLABELLED TRAILING FOOTER RUN. Ratified 2026-08-12, SCOPED TO ONE FILE.\nSCOPE FIRST, because the scope is the whole decision: this governs ai-impact-assessment-framework.md:651-653 and nothing else. #22's timestamp clause says INSIDE THE BLOCK, and its precedent (idx-26ac, applied 2026-08-12) deleted a timestamp that sat under the label \"**MCP-research metadata:**\". This run carries no heading and no label above it, so #22 does not reach it and could not be made to without the silent widening #22 itself refused.\nTHE FORM: where a file ends in a run of sibling \"**Label:** value\" lines with no heading and no label above them, and EVERY line in the run fails idx-26j's referent test, the run is deleted whole.\nMEASURED LINE BY LINE, not inherited: \":651 **Sist oppdatert via MCP:** 2026-02-04\" is when the generation ran; \":652 **MCP-kilder brukt:** microsoft-learn (docs.microsoft.com, microsoft.com/ai)\" is which tool was used and carries no number at all; \":653 **Antall dokumenter sokt:** 4 (search queries) + 2 (deep fetch)\" puts a document label over values that count operations - a search query is not a document. All three referents are the generation. Nothing countable against the file is in the run: the file's sources are the numbered lists above, untouched, as is the \"**Confidence markers:**\" block.\nWHY THE RUN AND NOT THE COUNTING LINE ALONE: :653 is the only member inside the 58 counting class, so the narrow edit was available. It would have left two lines with the same referent immediately above the edit - the residue class G7 exists for, caught at the edit site this time rather than by a later sweep.\nWHAT STAYS OPEN: the general class - an unlabelled run, and an enumeration with no count - remains open at idx-26ar. This form is an instance, not the class, and a second instance must come back as a question rather than inherit it.\nGOVERNS: idx-26ah."
+      "#26": "AN UNLABELLED TRAILING FOOTER RUN. Ratified 2026-08-12, SCOPED TO ONE FILE.\nSCOPE FIRST, because the scope is the whole decision: this governs ai-impact-assessment-framework.md:651-653 and nothing else. #22's timestamp clause says INSIDE THE BLOCK, and its precedent (idx-26ac, applied 2026-08-12) deleted a timestamp that sat under the label \"**MCP-research metadata:**\". This run carries no heading and no label above it, so #22 does not reach it and could not be made to without the silent widening #22 itself refused.\nTHE FORM: where a file ends in a run of sibling \"**Label:** value\" lines with no heading and no label above them, and EVERY line in the run fails idx-26j's referent test, the run is deleted whole.\nMEASURED LINE BY LINE, not inherited: \":651 **Sist oppdatert via MCP:** 2026-02-04\" is when the generation ran; \":652 **MCP-kilder brukt:** microsoft-learn (docs.microsoft.com, microsoft.com/ai)\" is which tool was used and carries no number at all; \":653 **Antall dokumenter sokt:** 4 (search queries) + 2 (deep fetch)\" puts a document label over values that count operations - a search query is not a document. All three referents are the generation. Nothing countable against the file is in the run: the file's sources are the numbered lists above, untouched, as is the \"**Confidence markers:**\" block.\nWHY THE RUN AND NOT THE COUNTING LINE ALONE: :653 is the only member inside the 58 counting class, so the narrow edit was available. It would have left two lines with the same referent immediately above the edit - the residue class G7 exists for, caught at the edit site this time rather than by a later sweep.\nWHAT STAYS OPEN: the general class - an unlabelled run, and an enumeration with no count - remains open at idx-26ar. This form is an instance, not the class, and a second instance must come back as a question rather than inherit it.\nGOVERNS: idx-26ah.",
+      "#27": "A REFERENT WORD THE FIELD NAME ALREADY CARRIES. Ratified 2026-08-12.\nTHE FORM: where a count line names a referent in its VALUE that contradicts the count, while the FIELD NAME already states the correct referent, delete the contiguous referent words from the value and leave the rest byte-identical. The count is untouched.\nTHE INSTANCE, agent-to-agent-a2a-protocol.md:732. \"**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research\" -> \"**Total sources cited:** 10 fra MCP-research + tavily-research\". Deleted: \" unike URLer\", 12 contiguous characters. The three #25 conditions all hold and were measured, not assumed: the remainder is grammatical; 10 is grounded in the 10 numbered entries the file lists; zero words are authored.\nWHY IT IS NOT #25, which is the reason this needed its own ratification rather than inheritance: #25 removes a DELETE-CLASS count restated in-line. Nothing removed here is a count at all, and nothing in the line has the generation as its referent. The conditions transfer; the scope does not.\nWHY IT IS NOT #21, and this is where the session that arrived here was wrong on a premise rather than on a judgement. STATE asserted this line was word-for-word idx-26w and therefore already governed. MEASURED FALSE: idx-26w reads \"fra MCP-research\" alone, this line reads \"fra MCP-research + tavily-research\". #21 fires only on an OVERCLAIMING provenance qualifier, and this qualifier does not overclaim - it names the web-research leg covering exactly the four non-Learn URLs (a2a-protocol.org x2, linuxfoundation.org, developers.googleblog.com). idx-26w own summary had already said so in writing. The provenance is sound here; the defect is the referent of the count.\nTHE MEASUREMENT THAT MADE IT A DELETION: 10 numbered source entries, 11 distinct URLs, because entry 8 carries two. So \"10\" is true as sources and false as unique URLs, and the line asserted both. Correcting 10 to 11 was available and was NOT taken - deletion of the wrong referent costs nothing, because the field name \"Total sources cited\" already says which one is meant.\nGOVERNS: idx-26t.",
+      "#28": "A KEEP-CLASS COUNT WHOSE TRUE HALF IS BOTH TRUE AND UNIQUE. Ratified 2026-08-12. This is the residual case #23 explicitly declined to ratify and sent back as a new question; this is its first instance, and it is decided rather than inherited.\nTHE FORM: where a keep-class line carries several counts, some measured FALSE and at least one measured TRUE, and that true part is NOT restated anywhere else in the file, CORRECT the false numbers to their measured values. Do not delete the line.\nTHIS IS THE PROGRAMME FIRST AUTHORED NUMBER, and the operator decided it deliberately on 2026-08-12. Until now every resolution deleted, on the idx-26v ground that a repair must not author the defect class it closes. That ground still holds where deletion is FREE - which is why idx-26t, decided in the same session, deletes. It stops holding where deletion destroys a true and unique claim, because then silence is not the cheap option, it is a second defect.\nTHE INSTANCE, rag-document-preprocessing.md:791 (the entry evidence and STATE both said :792 - off by one; the anchor is verbatim text, so nothing depended on it). \"8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**\" -> \"8 Microsoft Learn-artikler + 2 GitHub-repos = **10 kilder**\".\nMEASURED, and the population was re-checked after the edit rather than assumed: 8 distinct learn.microsoft.com articles after /en-us normalisation (TRUE as written), 2 distinct github.com URLs (NOT 4), therefore 10 named source URLs (NOT 12). The three azure.microsoft.com pricing URLs are excluded because the line states its own referent - Learn articles plus GitHub repos - and never claimed to cover them.\nTHE POPULATION CHECK THAT COULD HAVE INVALIDATED THIS: the file does not end at the footer - a further section runs :795-803 - so the footer might have been a section total measured over the wrong span. Measured: ZERO Learn or GitHub URLs occur after :791. All 11 occurrences precede it. The count covers what it claims.\nTHE LIMIT: this form applies only where the true part is BOTH true AND unique. Where the true part is restated elsewhere, deletion remains free and #23 governs. Where every part is false, #24 governs. A keep-class count that is merely unverifiable, rather than measurably wrong, is not reached by this form at all - that is still the idx-26j class.\nGOVERNS: idx-26at."
     }
   },
   "entries": [
@@ -375,13 +377,14 @@
       "id": "idx-26t",
       "file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md",
       "class": "replacement",
-      "status": "open",
+      "status": "resolved",
       "raised": "2026-08-09",
       "summary": "Booked while closing idx-26n, from the check the ratified form requires on what REMAINS in a footer after the MCP-calls line is deleted - the defect sits next to the edit, now for the twelfth time. '**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research' states both a source count and a URL count in one line, and they differ. MEASURED, not inferred: the Kilder section carries 10 numbered entries but 11 distinct URLs, because entry 8 (A2A Protocol Specification) lists two - https://a2a-protocol.org/latest/specification/ and https://a2a-protocol.org/latest/announcing-1.0/. So the line is TRUE read as 'sources cited' and FALSE read as 'unike URLer', and it says both. This is the undefined-referent defect the whole footer class is about, surviving INSIDE the line the ratified form told us to keep and verify - the form presumed kept counts would pass and does not say what to do when one fails. DIRECTION MATTERS AND WAS CHECKED: stated 10 < actual 11 runs the same way as all eight MCP-calls inconsistencies measured corpus-wide, with zero running the other way. DO NOT REPAIR BY PICKING A NUMBER: 10 and 11 are each correct under one reading, so choosing is a referent decision, not arithmetic - the same decision the operator took for the MCP-calls line, and it has not been taken for this field. Two candidate forms, neither ratified: drop the URL wording so the field counts sources only, or keep URLs and restate as 11. Raised as an open operator question in STATE.\nMEASURED 2026-08-12, AND THE #21 INHERITANCE IS REFUSED ON MEASUREMENT RATHER THAN ON CAUTION. The session arrived here believing this line was word-for-word idx-26w and therefore already settled by #21. IT IS NOT, and the difference is exactly the thing #21 turns on. GROUND TRUTH, :732: \"**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research\". idx-26w reads \"fra MCP-research\" ALONE. #21 fires only where the provenance qualifier OVERCLAIMS; here it does not, because the qualifier names the web-research leg that covers precisely the URLs the microsoft-learn server cannot serve - a2a-protocol.org (x2), linuxfoundation.org, developers.googleblog.com. Independently corroborated BEFORE this session measured it: idx-26w own summary already drew this contrast in writing, naming the neighbouring line as one that \"does cover its non-Learn sources\". Three sources agree, so the non-overclaim is not this session reading.\nURL CENSUS, two populations, run rather than argued. Kilder section (:670-end): 11 URL occurrences, 11 distinct - 7 learn.microsoft.com, 2 a2a-protocol.org, 1 linuxfoundation.org, 1 developers.googleblog.com - across 10 numbered entries, entry 8 carrying two. Whole file: 14 distinct, the three extras being code-sample hosts (agents.nav.no, two example.com) that no reading counts as kilder. SO THE COUNT IS 10 AS SOURCES AND 11 AS UNIQUE URLS, and the line says \"unike URLer\" while giving the source number. The defect is the referent of the count, NOT the provenance of it - a different defect from idx-26w, which is why the same-form reading fails twice over.\nALL SIX RATIFIED FORMS EXCLUDED, each against its own stated condition: #21 needs an overclaiming qualifier (measured false). #22 classifies this line KEEP, not delete - its referent is the artifact - so it governs the line only to preserve it, and #22 assumed keep-class meant adjudicable, which this line falsifies: it is countable twice, to two different numbers. #23 needs a mixed delete/keep line; there is no delete-class half here, no generation referent anywhere in the line. #24 needs a header parenthetical. #25 needs a delete-class count restated in-line; there is no delete-class count to remove. #26 is scoped to one other file by its own text.\nTHE DECISION OWED, unchanged in substance from the original booking but now with the arithmetic settled: 10 and 11 are each correct under one reading, so this is a referent choice and not a calculation. Candidate A, drop the referent word so the field counts what its own name says: deleting the contiguous fragment \" unike URLer\" leaves \"**Total sources cited:** 10 fra MCP-research + tavily-research\" - grammatical, grounded in the 10 numbered entries, ZERO words authored, and the field name already says \"sources cited\". Candidate B, keep URLs as the referent and restate 10 as 11 - which authors a number, the idx-26v hazard. Candidate A satisfies all three of #25 conditions but NOT #25 scope, since nothing being deleted is a delete-class count; it therefore needs its own ratification rather than inheritance.",
       "evidence": "footer of this file (last line after the idx-26n deletion); Kilder section entries 1-10, entry 8 carrying two URLs; idx-26n resolution; idx-26j scope addendum 2026-08-09",
       "anchors": [
         "**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research"
-      ]
+      ],
+      "resolution": "APPLIED 2026-08-12 under _meta.ratified_forms[\"#27\"], a form ratified for this entry rather than inherited from #21. The line now reads \"**Total sources cited:** 10 fra MCP-research + tavily-research\"; \" unike URLer\" is deleted and the count 10 is untouched. Verified by whole-line comparison: the pre-edit line occurs 0x, the post-edit line exactly 1x. Residue sweep run at the edit site as the method requires - the line is now the last line of the file and nothing follows it, so no sibling was left carrying the deleted referent. THE OPEN QUESTION IS CLOSED AS A REFERENT CHOICE, NOT AN ARITHMETIC ONE: 10 stands as the source count the field name asks for, and 11 (the distinct-URL reading created by entry 8 carrying two URLs) is not asserted anywhere."
     },
     {
       "id": "idx-26u",
@@ -947,13 +950,14 @@
       "id": "idx-26at",
       "file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
       "class": "replacement",
-      "status": "open",
+      "status": "resolved",
       "raised": "2026-08-12",
       "summary": "Raised 2026-08-12 while applying idx-26ae, out of the duty to measure a keep-class neighbour BEFORE relying on it (the #21 and #23 discipline). :792 \"**Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**\" is keep class - every part of it is countable against the file - and TWO OF ITS THREE PARTS ARE FALSE.\nMEASURED over two populations that agree, the \"Kilder og verifisering\" section (:748-793) and the whole file: 8 distinct learn.microsoft.com articles, TRUE (the section's two tables carry 6 + 2; the body's one extra occurrence is the same search-indexer-overview article without /en-us/, so it is not a ninth). 2 distinct github.com URLs, NOT 4 - Azure/azure-sdk-for-python and microsoft/Form-Recognizer-Toolkit. Therefore 10 named source URLs, not 12; or 13 if the three azure.microsoft.com pricing URLs at :783-785 count as kilder, a reading the line does not state. NO READING YIELDS 12, and the arithmetic is internally consistent only because the GitHub half is wrong.\nWHY IT IS NOT REPAIRED HERE: correcting 4 to 2 and 12 to 10 authors numbers into the corpus - the idx-26v hazard - and no ratified form covers a keep-class count that is simply wrong. #24 deleted such a count only because BOTH halves failed and there was nothing left to preserve; here \"8 Microsoft Learn-artikler\" is true, so #24's ground does not transfer, and #23 does not reach it because this is not a mixed delete/keep line. The line survived the idx-26ae edit intact and anchored, exactly as that entry required.\nTHE DECISION OWED: delete the whole line, correct the two false parts, or delete only the false parts and keep the true count. Each is a different answer to whether this programme may write a number it has measured, which has not been settled and should not be settled silently by whichever session gets here first.\nSEPARATELY, still not booked and named so it is not mistaken for unseen: :793 \"**Konfidensniva totalt:** 95% Verified (fra MCP), 5% Baseline (norske forhold og priser)\" is the idx-26j locator-4 / idx-26v class - a percentage with no stated denominator - already named in idx-26ae and deliberately left where it was.",
       "evidence": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md:792 (kept when :791 was deleted under idx-26ae, 2026-08-12); URL census of the file: 8 distinct learn.microsoft.com, 2 distinct github.com, 3 azure.microsoft.com pricing URLs; source tables at :750-777; idx-26ae (the application that surfaced it); #21 and #23 (measure-the-keep-half discipline); #24 (why deletion does not transfer); idx-26v (the authoring hazard)",
       "anchors": [
         "**Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**"
-      ]
+      ],
+      "resolution": "APPLIED 2026-08-12 under _meta.ratified_forms[\"#28\"]. The line now reads \"**Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 2 GitHub-repos = **10 kilder**\". Verified by whole-line comparison: pre-edit 0x, post-edit exactly 1x. THIS IS THE FIRST TIME THIS PROGRAMME HAS WRITTEN A NUMBER IT MEASURED, and it was put to the operator as exactly that question rather than settled by whichever session arrived first. The ground for departing from deletion was measured before the choice was offered: \"8 Microsoft Learn-artikler\" is TRUE and occurs NOWHERE ELSE in the file, making this #23 expressly unratified residual case, so deletion would have destroyed a true and unique claim instead of removing a redundant one. Correct line number is :791, not the :792 carried in this entry evidence and in STATE. The neighbouring \"**Konfidensniva totalt:** 95% Verified...\" at :792 is untouched and remains open as the idx-26j locator-4 / idx-26v class, as this entry already recorded."
     }
   ]
 }

skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md

@@ -729,4 +729,4 @@ app.MapA2A(agent, "/a2a/my-agent", agentCard: new()
 | GDPR/AI Act-mapping | Baseline | LLM kunnskap + norsk compliance-praksis |
 | Norsk offentlig sektor-scenarioer | Baseline | LLM kunnskap + norsk kontekst |
 
-**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research
+**Total sources cited:** 10 fra MCP-research + tavily-research

skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md

@@ -788,7 +788,7 @@ Images (JPEG/PNG)?
 
 ---
 
-**Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**
+**Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 2 GitHub-repos = **10 kilder**
 **Konfidensnivå totalt:** 95% Verified (fra MCP), 5% Baseline (norske forhold og priser)