aibvf-mcp

Added value: +{
+  "description": "Optional input-quality factor retained for portfolio scoring. Lower it when supplied pillars rest on weak evidence.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}

Added value: +{
+  "description": "Evidence that workflows, roles, decision rights and measures are ready. Pass only what is known. Explicit gaps and omitted checks block Accelerate until all four checks are evidenced.",
+  "properties": {
+    "decision_rights_defined": {
+      "description": "True only when decision, override and escalation rights have named human owners, false when authority remains unclear.",
+      "type": "boolean"
+    },
+    "measures_updated": {
+      "description": "True only when performance measures and incentives reflect the redesigned work, false when the old measures remain.",
+      "type": "boolean"
+    },
+    "roles_redesigned": {
+      "description": "True only when affected roles, accountabilities and capability expectations have been rewritten, false when roles remain unchanged.",
+      "type": "boolean"
+    },
+    "workflow_redesigned": {
+      "description": "True only when the end-to-end workflow has been redesigned around the AI and retained human judgement, false when the existing workflow remains.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision score is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional 0–1. How grounded the four pillar scores are in real evidence versus estimated from context. Defaults to 1 (treated as measured). If the organisation lacks formal change-readiness or risk metadata, estimate the pillars from what you know AND set this lower to say so — decision confidence is reduced proportionally and a caveat is attached, instead of returning a falsely confident verdict on soft inputs."New value: +"Optional 0 to 1 input-quality factor. The default ranges from 0.5 when all pillars are estimated to 1 when all are supplied. Supplied values still require evidence review. Lower this factor when the supplied pillars rest on weak evidence."

Previous value: -"Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown."New value: +"Evidence that workflows, roles, decision rights and measures are ready. Pass only what is known. Explicit gaps and omitted checks block Accelerate until all four checks are evidenced."

Previous value: -"BVF scoring modules that fired for this input."New value: +"Scoring-rule and sector-context labels. Sector labels do not certify clinical validation or regulatory compliance."

Previous value: -"Confidence in the verdict, 0-100."New value: +"Heuristic decision score, 0 to 100, adjusted for input quality. This score has no probability calibration."

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Meaning and limits of compatibility fields. Present these labels when explaining the result.",
+  "type": "object"
+}

Previous value: -"Modelled net value in EUR after capture rate, low/high."New value: +"Readiness-adjusted benefit hypothesis before project build, run and change costs. Replace planning rates with scoped economics before funding."

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision score is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown."New value: +"Evidence that workflows, roles, decision rights and measures are ready. Pass only what is known. Explicit gaps and omitted checks block Accelerate until all four checks are evidenced."

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Meaning and limits of compatibility fields. Present these labels when explaining the result.",
+  "type": "object"
+}

Previous value: -"Confidence in the verdict if the recommendations land, 0-100."New value: +"Projected heuristic decision score, 0 to 100. The target remains conditional on work architecture and evidence review."

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision score is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional 0–1. How grounded the four pillar scores are in real evidence versus estimated from context. Defaults to 1 (treated as measured). If the organisation lacks formal change-readiness or risk metadata, estimate the pillars from what you know AND set this lower to say so — decision confidence is reduced proportionally and a caveat is attached, instead of returning a falsely confident verdict on soft inputs."New value: +"Optional 0 to 1 input-quality factor. The default ranges from 0.5 when all pillars are estimated to 1 when all are supplied. Supplied values still require evidence review. Lower this factor when the supplied pillars rest on weak evidence."

Previous value: -"Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown."New value: +"Evidence that workflows, roles, decision rights and measures are ready. Pass only what is known. Explicit gaps and omitted checks block Accelerate until all four checks are evidenced."

Previous value: -"BVF scoring modules that fired for this input."New value: +"Scoring-rule and sector-context labels. Sector labels do not certify clinical validation or regulatory compliance."

Previous value: -"Confidence in the verdict, 0-100."New value: +"Heuristic decision score, 0 to 100, adjusted for input quality. This score has no probability calibration."

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Meaning and limits of compatibility fields. Present these labels when explaining the result.",
+  "type": "object"
+}

Previous value: -"Modelled net value in EUR after capture rate, low/high."New value: +"Readiness-adjusted benefit hypothesis before project build, run and change costs. Replace planning rates with scoped economics before funding."

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

Previous value: -"A portfolio document conforming to the AI BVF v1.0 schema: bvf_version, organization (name, industry, optional revenue_eur), and a non-empty initiatives array. Each initiative carries id, name, function, ai_tier, and a scores object whose four pillars are each either a bare number (0–100) or an object { value: 0–100 }; both shapes are accepted everywhere. Every initiative is run through the same rule as score_initiative — governance_risk ≥ 70 OR financial_return ≤ 20 → Stop; all of strategic_alignment/financial_return/change_enablement ≥ 60 with governance_risk ≤ 40 → Accelerate; else Fix — and the verdicts are aggregated into portfolio counts. organization.revenue_eur is required to model EUR value; initiatives that cannot be scored (missing revenue, unknown function/ai_tier) appear in skipped_initiatives rather than scored_initiatives. Validate first with validate_portfolio if the document may be malformed. Schema: https://www.aibvf.com/protocol."New value: +"AI BVF v1.0 portfolio with organization and initiatives. Each initiative carries id, name, function, ai_tier and four scores, supplied as numbers or { value, confidence } objects. Retain each initiative's work_architecture, pillar_basis and optional signal_completeness. pillar_basis marks given or estimated values; estimated pillars are recalculated for the current context and retain an input-quality reduction. Supplied values without provenance are caller-provided, with no claim of evidence verification. Accelerate requires the pillar thresholds and all four work-architecture checks. Missing work-design evidence returns Fix for an otherwise green case. organization.revenue_eur is required for benefit modelling. Validate unfamiliar documents first."

Previous value: -"Sum of net EUR value across scored initiatives, low/high."New value: +"Arithmetic sum of benefit hypotheses. Reconcile overlapping scope, double counting and project costs before using this as a portfolio business case."

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Meaning and limits of compatibility fields. Present these labels when explaining the result.",
+  "type": "object"
+}

Previous value: -"Mean decision confidence across scored initiatives (0–100); 0 when none were scored."New value: +"Mean decision score across scored initiatives (0–100); 0 when none were scored."

Previous value: -"BVF scoring modules that fired for this initiative."New value: +"Scoring-rule and sector-context labels. Sector labels do not certify clinical validation or regulatory compliance."

Added value: +{
+  "description": "Reproducibility record: engine version, the rules that fired, and the resolved inputs. Deterministic, no timestamps. If the verdict is challenged months later, the same inputs on the same engine version reproduce it exactly.",
+  "properties": {
+    "bvf_version": {
+      "type": "string"
+    },
+    "engine": {
+      "type": "string"
+    },
+    "engine_version": {
+      "type": "string"
+    },
+    "inputs_used": {
+      "description": "The resolved inputs the result was computed on, including estimated pillar values.",
+      "type": "object"
+    },
+    "note": {
+      "type": "string"
+    },
+    "rules_fired": {
+      "description": "The rules that actually fired, in order: estimation, gates, classification, value arithmetic.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Present only when signal_completeness was low: warns the verdict rests on soft inputs and confidence was reduced.",
+  "type": "string"
+}

Previous value: -"Confidence in the verdict (0–100)."New value: +"Heuristic decision score, 0 to 100, adjusted for input quality. This score has no probability calibration."

Previous value: -"Modelled net EUR value, low/high."New value: +"Modelled readiness-adjusted EUR benefit, low/high."

Added value: +{
+  "description": "Per pillar: \"given\" (caller supplied it) or \"estimated\" (deterministic prior). When any pillar is estimated, tell the user which, and ask for evidence on those to firm up the verdict.",
+  "properties": {
+    "change_enablement": {
+      "enum": [
+        "given",
+        "estimated"
+      ],
+      "type": "string"
+    },
+    "financial_return": {
+      "enum": [
+        "given",
+        "estimated"
+      ],
+      "type": "string"
+    },
+    "governance_risk": {
+      "enum": [
+        "given",
+        "estimated"
+      ],
+      "type": "string"
+    },
+    "strategic_alignment": {
+      "enum": [
+        "given",
+        "estimated"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "The four pillar values the verdict was actually computed on, whether given by the caller or estimated by the engine. Show these to the user when any pillar was estimated.",
+  "properties": {
+    "change_enablement": {
+      "type": "number"
+    },
+    "financial_return": {
+      "type": "number"
+    },
+    "governance_risk": {
+      "type": "number"
+    },
+    "strategic_alignment": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "What moves this verdict, computed deterministically: the value if readiness were one notch worse, the value at revenue minus 20 percent, and the nearest single-pillar movements that flip the classification. Boards trust ranges with visible assumptions over point estimates; show this.",
+  "properties": {
+    "readiness_one_notch_down": {
+      "description": "Null when readiness is already siloed.",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "revenue_minus_20pct": {
+      "type": "object"
+    },
+    "verdict_flips": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Input-quality factor after estimated provenance, pillar quality and any explicit factor are combined conservatively.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}

Added value: +{
+  "description": "The work architecture gate across workflow, roles, human decision rights and performance measures. A stated gap or missing evidence blocks Accelerate.",
+  "properties": {
+    "blocks_accelerate": {
+      "type": "boolean"
+    },
+    "checks": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "gaps": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "gate": {
+      "type": "string"
+    },
+    "next_question": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "unknown",
+        "partial",
+        "gap",
+        "ready"
+      ],
+      "type": "string"
+    },
+    "unknowns": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status",
+    "blocks_accelerate",
+    "checks",
+    "gaps",
+    "unknowns",
+    "gate"
+  ],
+  "type": "object"
+}

Previous value: -"Scored initiative with the highest mid-point net EUR value. Omitted when none were scored."New value: +"Scored initiative with the highest mid-point readiness-adjusted EUR benefit. Omitted when none were scored."

Previous value: -"Net EUR value range for the top initiative."New value: +"Readiness-adjusted EUR benefit range for the top initiative."

Previous value: -"The AI initiative in ordinary business language. Include the organisation, industry, approximate annual revenue, business function, AI ambition and how the organisation works today when known. The resolver extracts what it can and asks one question for the first missing input; it never guesses an unresolved taxonomy value."New value: +"The AI initiative in ordinary business language. Include the organisation, industry, approximate annual revenue, business function, AI ambition and how the organisation works today when known. The resolver extracts what it can and, when several inputs are missing, asks for all of them in one clarification; it never guesses an unresolved taxonomy value."

Previous value: -"The single next question to ask. Present only when status is needs_input."New value: +"One clarification covering every unresolved input. Present only when status is needs_input; ask it once, then call the tool again with the answers in the explicit fields."

Previous value: -"The work architecture gate across workflow, roles, human decision rights and performance measures. Any stated gap blocks Accelerate."New value: +"The work architecture gate across workflow, roles, human decision rights and performance measures. A stated gap or missing evidence blocks Accelerate."

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Previous value: -[
-  "status",
-  "blocks_accelerate",
-  "checks",
-  "gaps",
-  "gate"
-]New value: +[
+  "status",
+  "blocks_accelerate",
+  "checks",
+  "gaps",
+  "unknowns",
+  "gate"
+]

Previous value: -"The work architecture gate across workflow, roles, human decision rights and performance measures. Any stated gap blocks Accelerate."New value: +"The work architecture gate across workflow, roles, human decision rights and performance measures. A stated gap or missing evidence blocks Accelerate."

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Previous value: -[
-  "status",
-  "blocks_accelerate",
-  "checks",
-  "gaps",
-  "gate"
-]New value: +[
+  "status",
+  "blocks_accelerate",
+  "checks",
+  "gaps",
+  "unknowns",
+  "gate"
+]

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine (from readiness, tier, function and published benchmarks), the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional; when omitted, estimated from the published benchmark upside for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."New value: +"Optional; when omitted, estimated from the disclosed AI BVF planning range for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."

Previous value: -"Citation for the benchmark rates applied."New value: +"Provenance and evidence status for the AI BVF planning rates applied."

Previous value: -"Business function the process belongs to. Selects the published cycle-time and hand-off medians the signals are read against. Call list_taxonomy if unsure."New value: +"Business function the process belongs to. Selects the disclosed AI BVF cycle-time and hand-off reference points used to interpret the signals. Call list_taxonomy if unsure."

Previous value: -"Approximate annual revenue in EUR (must be ≥ 0). Scales the whole output: the benchmark rates are applied as fractions of this figure, so the modelled EUR value range grows with it. A rough order-of-magnitude estimate is fine."New value: +"Approximate annual revenue in EUR (must be ≥ 0). Scales the whole output: the disclosed AI BVF planning rates are applied as fractions of this figure, so the modelled EUR value range grows with it. A rough order-of-magnitude estimate is fine."

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine (from readiness, tier, function and published benchmarks), the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional; when omitted, estimated from the published benchmark upside for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."New value: +"Optional; when omitted, estimated from the disclosed AI BVF planning range for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."

Previous value: -"Approximate annual revenue in EUR (must be ≥ 0). Scales the whole output: the benchmark rates are applied as fractions of this figure, so the modelled EUR value range grows with it. A rough order-of-magnitude estimate is fine."New value: +"Approximate annual revenue in EUR (must be ≥ 0). Scales the whole output: the disclosed AI BVF planning rates are applied as fractions of this figure, so the modelled EUR value range grows with it. A rough order-of-magnitude estimate is fine."

Previous value: -"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine (from readiness, tier, function and published benchmarks), the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."New value: +"OPTIONAL, and each pillar inside it is optional. The four AI BVF pillars, each an honest 0–100 self-assessment, combining deterministically into the verdict: governance_risk ≥ 70 OR financial_return ≤ 20 returns Stop; strategic_alignment, financial_return and change_enablement all ≥ 60 with governance_risk ≤ 40 returns Accelerate; everything else returns Fix. Pass ONLY the pillars the user has real evidence for — do NOT invent numbers for the rest. Missing pillars are estimated deterministically by the engine from disclosed AI BVF planning assumptions, the response reports which via pillar_basis and scores_used, decision confidence is haircut by how much was estimated, and a fully-estimated pass can never return Accelerate (it returns Fix pending confirmation). So call immediately with whatever the user gave you, then ask for evidence on the estimated pillars and re-call to firm the verdict up."

Previous value: -"Optional; when omitted, estimated from the published benchmark upside for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."New value: +"Optional; when omitted, estimated from the disclosed AI BVF planning range for the function (40–52, never enough to clear 60 unmodelled, never low enough to force a Stop). Strength of the modelled return (0–100, higher is better). A value ≤ 20 forces a Stop on its own; ≥ 60 is one of the four conditions required for Accelerate."

Previous value: -"Citation for the benchmark rates applied."New value: +"Provenance and evidence status for the AI BVF planning rates applied."

Added value: +"Build a valid portfolio document from loose organisation and initiative inputs. organization and at least one initiative are required. readiness defaults to traditional; missing pillar scores are estimated and reported, while unresolved taxonomy values return issues instead of guesses."

Added value: +"Optional workforce-impact label retained in the document; it does not change the verdict today."

Added value: +"Optional known compliance regimes retained in the document; governance risk still comes from the supplied or estimated pillar score."

Added value: +"Optional evidenced change-enablement score, 0-100; omitted values are estimated."

Added value: +100

Added value: +0

Added value: +"Optional evidenced financial-return score, 0-100; omitted values are estimated."

Added value: +100

Added value: +0

Added value: +"Optional evidenced governance-risk score, 0-100, where higher means more risk; omitted values are estimated."

Added value: +100

Added value: +0

Added value: +"Optional evidenced strategic-alignment score, 0-100; omitted values are estimated."

Added value: +100

Added value: +0

Added value: +"Organisation identity and context shared by every initiative in the assembled portfolio."

Added value: +"Optional employee count retained as portfolio context; it does not alter scoring today."

Added value: +0

Added value: +"Optional operating region retained as portfolio context; it does not alter scoring today."

Added value: +"Inputs for a change plan after a Fix or Stop verdict. industry, revenue_eur, function, ai_tier and readiness must match the scoring call so the plan is built against the same case. scores and work_architecture may be copied from score_initiative; omitted pillars are estimated and make the plan provisional. resistance_type and risk_type are optional diagnostics that select the play, and omission triggers a named inference plus the next question to ask."

Added value: +"Sequence one scored portfolio by passing either portfolio, or organization plus initiatives, never both. readiness is always required because it sets pacing. constraints are optional and default to two concurrent initiatives per function across a 90-day horizon."

Added value: +"AI ambition, gen1, gen2 or gen3. Higher tiers are treated as more complex when wave placement is decided."

Added value: +"Business function absorbing the change. Capacity limits are enforced against this field."

Added value: +"Stable initiative identifier used in waves, conflicts and deferrals."

Added value: +"Initiative name shown in the sequenced plan."

Added value: +"The four flat 0-100 pillar values used to classify and place the initiative. Pass the score_initiative scores_used values, not nested score objects."

Added value: +"Change-enablement score from score_initiative, 0-100."

Added value: +"Financial-return score from score_initiative, 0-100."

Added value: +"Governance-risk score from score_initiative, 0-100, where higher means more risk."

Added value: +"Strategic-alignment score from score_initiative, 0-100."

Added value: +"Organisation context used when initiatives are passed at the top level. Required with top-level initiatives and ignored when portfolio is supplied."

Previous value: -"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The page records the response anonymously only when the user chooses an answer; no assessment data is attached."

Previous value: -"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The page records the response anonymously only when the user chooses an answer; no assessment data is attached."

Previous value: -"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The page records the response anonymously only when the user chooses an answer; no assessment data is attached."

Previous value: -"Optional three-question feedback route, present only when any initiative was Fix or Stop. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only when any initiative was Fix or Stop. The page records the response anonymously only when the user chooses an answer; no assessment data is attached."

Previous value: -"Optional one-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."

Previous value: -"Optional one-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."

Previous value: -"Optional one-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."

Previous value: -"Optional one-question feedback route, present only when any initiative was Fix or Stop. The link opens a prefilled email; no response is recorded unless the user chooses to send it."New value: +"Optional three-question feedback route, present only when any initiative was Fix or Stop. The link opens a prefilled email; no assessment data is added and no response is recorded unless the user chooses to send it."

Added value: +{
+  "description": "Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown.",
+  "properties": {
+    "decision_rights_defined": {
+      "description": "True only when decision, override and escalation rights have named human owners, false when authority remains unclear.",
+      "type": "boolean"
+    },
+    "measures_updated": {
+      "description": "True only when performance measures and incentives reflect the redesigned work, false when the old measures remain.",
+      "type": "boolean"
+    },
+    "roles_redesigned": {
+      "description": "True only when affected roles, accountabilities and capability expectations have been rewritten, false when roles remain unchanged.",
+      "type": "boolean"
+    },
+    "workflow_redesigned": {
+      "description": "True only when the end-to-end workflow has been redesigned around the AI and retained human judgement, false when the existing workflow remains.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "The work architecture gate across workflow, roles, human decision rights and performance measures. Any stated gap blocks Accelerate.",
+  "properties": {
+    "blocks_accelerate": {
+      "type": "boolean"
+    },
+    "checks": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "gaps": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "gate": {
+      "type": "string"
+    },
+    "next_question": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "unknown",
+        "partial",
+        "gap",
+        "ready"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "blocks_accelerate",
+    "checks",
+    "gaps",
+    "gate"
+  ],
+  "type": "object"
+}

Previous value: -[
-  "bvf_version",
-  "classification",
-  "reason",
-  "net_value_eur",
-  "gross_value_eur",
-  "decision_confidence",
-  "multipliers",
-  "drivers",
-  "benchmark_source",
-  "applied_modules"
-]New value: +[
+  "bvf_version",
+  "classification",
+  "reason",
+  "net_value_eur",
+  "gross_value_eur",
+  "decision_confidence",
+  "multipliers",
+  "drivers",
+  "benchmark_source",
+  "applied_modules",
+  "work_architecture"
+]

Added value: +{
+  "description": "Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown.",
+  "properties": {
+    "decision_rights_defined": {
+      "description": "True only when decision, override and escalation rights have named human owners, false when authority remains unclear.",
+      "type": "boolean"
+    },
+    "measures_updated": {
+      "description": "True only when performance measures and incentives reflect the redesigned work, false when the old measures remain.",
+      "type": "boolean"
+    },
+    "roles_redesigned": {
+      "description": "True only when affected roles, accountabilities and capability expectations have been rewritten, false when roles remain unchanged.",
+      "type": "boolean"
+    },
+    "workflow_redesigned": {
+      "description": "True only when the end-to-end workflow has been redesigned around the AI and retained human judgement, false when the existing workflow remains.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Optional evidence that the work around the AI has been redesigned. Pass only what is known. Any explicit false value blocks Accelerate until the gap is closed; omitted checks remain visible as unknown.",
+  "properties": {
+    "decision_rights_defined": {
+      "description": "True only when decision, override and escalation rights have named human owners, false when authority remains unclear.",
+      "type": "boolean"
+    },
+    "measures_updated": {
+      "description": "True only when performance measures and incentives reflect the redesigned work, false when the old measures remain.",
+      "type": "boolean"
+    },
+    "roles_redesigned": {
+      "description": "True only when affected roles, accountabilities and capability expectations have been rewritten, false when roles remain unchanged.",
+      "type": "boolean"
+    },
+    "workflow_redesigned": {
+      "description": "True only when the end-to-end workflow has been redesigned around the AI and retained human judgement, false when the existing workflow remains.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "The work architecture gate across workflow, roles, human decision rights and performance measures. Any stated gap blocks Accelerate.",
+  "properties": {
+    "blocks_accelerate": {
+      "type": "boolean"
+    },
+    "checks": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "gaps": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "gate": {
+      "type": "string"
+    },
+    "next_question": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "unknown",
+        "partial",
+        "gap",
+        "ready"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "blocks_accelerate",
+    "checks",
+    "gaps",
+    "gate"
+  ],
+  "type": "object"
+}

Previous value: -[
-  "bvf_version",
-  "classification",
-  "reason",
-  "net_value_eur",
-  "gross_value_eur",
-  "decision_confidence",
-  "multipliers",
-  "drivers",
-  "benchmark_source",
-  "applied_modules"
-]New value: +[
+  "bvf_version",
+  "classification",
+  "reason",
+  "net_value_eur",
+  "gross_value_eur",
+  "decision_confidence",
+  "multipliers",
+  "drivers",
+  "benchmark_source",
+  "applied_modules",
+  "work_architecture"
+]

Added value: +{
+  "description": "Optional one-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no response is recorded unless the user chooses to send it.",
+  "properties": {
+    "question": {
+      "type": "string"
+    },
+    "url": {
+      "format": "uri",
+      "type": "string"
+    }
+  },
+  "required": [
+    "question",
+    "url"
+  ],
+  "type": "object"
+}

Added value: +{
+  "description": "Optional one-question feedback route, present only for Fix/Stop verdicts. The link opens a prefilled email; no response is recorded unless the user chooses to send it.",
+  "properties": {
+    "question": {
+      "type": "string"
+    },
+    "url": {
+      "format": "uri",
+      "type": "string"
+    }
+  },
+  "required": [
+    "question",
+    "url"
+  ],
+  "type": "object"
+}

Added value: +{
+  "description": "Optional one-question feedback route, present only when any initiative was Fix or Stop. The link opens a prefilled email; no response is recorded unless the user chooses to send it.",
+  "properties": {
+    "question": {
+      "type": "string"
+    },
+    "url": {
+      "format": "uri",
+      "type": "string"
+    }
+  },
+  "required": [
+    "question",
+    "url"
+  ],
+  "type": "object"
+}

Previous value: -"A portfolio document conforming to the AI BVF v1.0 schema: bvf_version, organization (name, industry, optional revenue_eur), and a non-empty initiatives array. Each initiative carries id, name, function, ai_tier, and a scores object whose four pillars each carry a numeric value (0–100). Every initiative is run through the same rule as score_initiative — governance_risk ≥ 70 OR financial_return ≤ 20 → Stop; all of strategic_alignment/financial_return/change_enablement ≥ 60 with governance_risk ≤ 40 → Accelerate; else Fix — and the verdicts are aggregated into portfolio counts. organization.revenue_eur is required to model EUR value; initiatives that cannot be scored (missing revenue, unknown function/ai_tier) appear in skipped_initiatives rather than scored_initiatives. Validate first with validate_portfolio if the document may be malformed. Schema: https://www.aibvf.com/protocol."New value: +"A portfolio document conforming to the AI BVF v1.0 schema: bvf_version, organization (name, industry, optional revenue_eur), and a non-empty initiatives array. Each initiative carries id, name, function, ai_tier, and a scores object whose four pillars are each either a bare number (0–100) or an object { value: 0–100 }; both shapes are accepted everywhere. Every initiative is run through the same rule as score_initiative — governance_risk ≥ 70 OR financial_return ≤ 20 → Stop; all of strategic_alignment/financial_return/change_enablement ≥ 60 with governance_risk ≤ 40 → Accelerate; else Fix — and the verdicts are aggregated into portfolio counts. organization.revenue_eur is required to model EUR value; initiatives that cannot be scored (missing revenue, unknown function/ai_tier) appear in skipped_initiatives rather than scored_initiatives. Validate first with validate_portfolio if the document may be malformed. Schema: https://www.aibvf.com/protocol."

Previous value: -"The portfolio document as a JSON object following the AI BVF v1.0 schema: a top-level object with bvf_version, organization, and a non-empty \"initiatives\" array, each initiative carrying the same fields score_initiative expects (industry, revenue_eur, function, ai_tier, readiness, and a scores object with the four 0–100 pillars). Checked structurally only — required fields present, correct types, enum values valid, pillar numbers in range; the pillar values are NOT scored or judged here (use score_initiative or score_portfolio for that). On failure, errors[] names each failing JSON path and the rule it broke."New value: +"The portfolio document as a JSON object following the AI BVF v1.0 schema: a top-level object with bvf_version, organization, and a non-empty \"initiatives\" array, each initiative carrying the same fields score_initiative expects (industry, revenue_eur, function, ai_tier, readiness, and a scores object with the four 0–100 pillars, each either a bare number or an object { value, confidence? }; both shapes pass). Checked structurally only — required fields present, correct types, enum values valid, pillar numbers in range; the pillar values are NOT scored or judged here (use score_initiative or score_portfolio for that). On failure, errors[] names each failing JSON path and the rule it broke."

Added value: +{
+  "description": "Alternative input: the same AI BVF v1.0 portfolio document score_portfolio accepts (organization + initiatives with nested {value} pillar scores). Pass either this OR the top-level organization + initiatives; nested score values are flattened automatically, and missing pillars are estimated honestly.",
+  "type": "object"
+}

Previous value: -[
-  "organization",
-  "initiatives",
-  "readiness"
-]New value: +[
+  "readiness"
+]

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]