Skip to content
Skip to content
Build n Bloom
Menu
How we helpExamplesAbout
Book a Fit Call

A complete engagement, with its decisions attached.

A fictional advisory firm is assessing a replacement-part offer. Inspect the scope, evidence and client report, then see what a source change means for the next person.

CV07 · Entirely fictional browser simulation · No live AI or integration. The original dated AI draft is available separately. Finance is frozen as of 2 October 2026.

Start with the question the client pays to answer.

Should Larch test a local replacement-part offer for non-critical processing components, and which buyer conditions should the pilot require?

Inspect the scope, method and cost

Eight supplied notes, three alternatives, an executive summary, source/method appendix and one scripted correction cycle. Ten business days after complete permitted inputs and reviewer availability.

Market sizing, population demand, statistically representative switching rate, safety certification, external factual validation, revenue forecast, implementation and supplier fulfilment guarantee.

Purposive qualitative comparison. Code each interview for urgency, compatibility/approval, incumbent resistance, price evidence and explicit trial intent. Keep participant reports separate from inference. Compare no launch, broad speed-led launch, and bounded compatibility-led pilot. No percentages across the market; no causal switching inference.

Role cost
A$13,500
Direct cost
A$1,500
10% contingency
A$1,500
Total planning cost
A$16,500
Fictional service fee
A$30,000

Fully loaded internal planning rates: reviewer 18h × A$300; analyst 42h × A$180; operations 6h × A$90. The A$13,500 planning surplus is not realised profit or savings. These are fictional advisory-engagement figures, separate from Build n Bloom pricing.

Should Larch test a local replacement-part offer?

Unreviewed draft · report v2 · ready

Recommendation for the receiving owner

Consider one non-critical, documented-equivalence component with willing sites, subject to engineering review and a separate supplier-capability check. Do not justify a pilot through general switching or price-premium claims. No launch remains reasonable if qualification effort or capability makes trial unattractive.

Inspect the source-linked findings

Compatibility approval conditions trial; incumbent delivery also matters.

N01 conditions trial on engineering sign-off; N02 reports nine of ten orders within the agreed window. Check approval and incumbent performance before proposing a trial.

Criticality and current need qualify openness to a trial.

N03 limits trial to low-risk fittings; N07 reports no recent stockout. Neither proves general demand.

One premium purchase is not a general pricing rule.

N06 reports one urgent purchase at 12% higher price; N04 has no record establishing faster delivery caused a switch; N08 has not accepted a premium.

Three reasonable alternatives

No launch: avoid qualification effort; retain the option if capability or approval burden makes trial unattractive.

Broad speed-led launch: the notes do not establish a general speed-only switching or price-premium proposition.

Bounded compatibility-led pilot: consider one non-critical component only with willing sites, engineering sign-off and a supplier-capability check.

What remains unknown

Notes rather than transcripts; no verified purchase records, representative market sample, external market sources or supplier capability/cost validation. Eight perspectives are complete for this teaching method, not proof of market demand.

Next owner: the recipient identifies the compatibility and supplier-capability checks before any pilot decision. Professional issue, acceptance of the assessment and launch authority are separate.

Assessment-report form

Keep method, coverage, findings and limits alongside the alternatives and conditional recommendation.

Bring the right evidence into the work.

Inspect the eight case-only notes and their exact locators. This approved fixed pack illustrates the context that a RAG step could retrieve; selection here is authored, with no live model or search index.

Maintenance manager, small food plant · N01 v1

One breakdown last quarter stopped our line for two days. I would trial a local replacement if engineering signs off compatibility; speed alone will not authorise it.

CV07#/records/N01/text · Current case; anonymous paraphrase only

Return to the report
Procurement lead, large processing site · N02 v1

Our approved supplier delivered nine of our last ten orders within the agreed window. Changing suppliers costs qualification time; we need fit documentation and a credible exception plan, not a blanket speed promise.

CV07#/records/N02/text · Current case; anonymous paraphrase only

Return to the report
Maintenance lead, regional workshop · N03 v1

Two of our last six urgent orders took over five days. For low-risk fittings I can trial a documented substitute; safety-critical parts stay with the approved supplier.

CV07#/records/N03/text · Current case; anonymous paraphrase only

Return to the report
Distributor account manager · N04 v1

Of our last five won orders, four used an existing account and all five required fit confirmation. Prospects ask about lead time, but I have no record showing faster delivery caused a switch.

CV07#/records/N04/text · Current case; anonymous paraphrase only

Return to the report
Engineering approver, chemical plant · N05 v1

No local-source exception bypasses validation. For non-critical components I can review an equivalence dossier in a planned maintenance window; outage promises are not evidence of compatibility.

CV07#/records/N05/text · Current case; anonymous paraphrase only

Return to the report
Buyer, independent repair business · N06 v1

I bought a comparable fitting from a local supplier once after my incumbent quoted seven days. The price was 12 percent higher and I accepted it for that urgent job. Routine orders remain on the incumbent account.

CV07#/records/N06/text · Current case; anonymous paraphrase only

Return to the report
Operations manager, medium food plant · N07 v1

We hold spares for our critical equipment and had no stockout in the last quarter. Another supplier offers little benefit today; revisit when we add a production line.

CV07#/records/N07/text · Current case; anonymous paraphrase only

Return to the report
Procurement manager, packaging factory · N08 v1

I could approve a trial of one non-critical part after compatibility review. I would ask for quoted lead time and price before deciding. I have not committed an order or accepted a price premium.

CV07#/records/N08/text · Current case; anonymous paraphrase only

Return to the report
See the preparation context and missing material

The context includes the accepted question, method, eligible current notes, versioned locators and evidence limits. 8 of eight notes are currently eligible. This is a fixed-pack context, not an executed RAG call.

Supplier fulfilment evidence and verified purchase records are missing. A retrieved passage cannot create them or approve the report.

Know what each decision depends on.

Change or revoke N03 and follow its effect through the finding and report. A logical context graph can be stored as typed linked records; it does not require a graph database.

  1. Source N03 v1supports → F2

    Current case-only evidence

    Next owner: Evidence librarian
  2. Finding F2contained in → report v2

    Current authored interpretation

    Next owner: Delivery analyst
  3. Report v2reviewed by → Marcus

    Fresh review pending

    Next owner: Marcus, professional reviewer (fictional)
  4. Receiving decisioncovers → milestone M2

    Current decision not recorded

    Next owner: Client recipient (fictional)
  5. Milestone M2basis of → CV07-INV-02

    Current readiness awaits review/acceptance

    Next owner: Case coordinator
  6. CV07-INV-02 · A$20,000receives allocation → CV07-PAY-02

    Historical scripted invoice retained

    Next owner: Ruth, finance (fictional)
  7. A$10,000 allocated · A$10,000 opendoes not close → invoice

    Historical scripted payment retained; not yet due at 2 Oct 2026

    Next owner: Ruth, finance (fictional)

Changes queue new decisions. The original scripted invoice and payment stay in history; no automatic reversal or collection occurs.

Where GraphRAG could help

For a question such as “which current sources and reviewed methods support this decision across eligible engagements?”, graph relationships can guide retrieval. Compare that approach with ordinary search and RAG on representative questions first. This authored dependency list is a context graph, not GraphRAG execution.

Accepted delivery and paid delivery are different.

Historical fictional M2 invoice: A$20,000. Allocated payment: A$10,000. A$10,000 remains open. It is not yet due at the fixed specimen date, 2026-10-02; its due date is 5 October 2026. Time passage does not close the balance.

Ruth owns payment allocation and invoice closure. Current-session review and acceptance readiness are shown separately in the dependency trace.

Use your method. Keep the expertise you may reuse.

Switching profiles changes the required presentation and reopens exact-version review. Both retain the same qualitative evidence limits; this is configuration, not automatic learning.

No cross-case reuse nominated

Inspect access and source boundaries

This is an authored field projection, not real login or tenant isolation. The finance preparation view omits the raw interview pack.

{
  "caseId": "CV07",
  "method": "Purposive qualitative comparison. Code each interview for urgency, compatibility/approval, incumbent resistance, price evidence and explicit trial intent. Keep participant reports separate from inference. Compare no launch, broad speed-led launch, and bounded compatibility-led pilot. No percentages across the market; no causal switching inference.",
  "sources": [
    {
      "id": "N01",
      "role": "Maintenance manager, small food plant",
      "locator": "CV07#/records/N01/text",
      "version": 1,
      "permitted": true,
      "text": "One breakdown last quarter stopped our line for two days. I would trial a local replacement if engineering signs off compatibility; speed alone will not authorise it."
    },
    {
      "id": "N02",
      "role": "Procurement lead, large processing site",
      "locator": "CV07#/records/N02/text",
      "version": 1,
      "permitted": true,
      "text": "Our approved supplier delivered nine of our last ten orders within the agreed window. Changing suppliers costs qualification time; we need fit documentation and a credible exception plan, not a blanket speed promise."
    },
    {
      "id": "N03",
      "role": "Maintenance lead, regional workshop",
      "locator": "CV07#/records/N03/text",
      "version": 1,
      "permitted": true,
      "text": "Two of our last six urgent orders took over five days. For low-risk fittings I can trial a documented substitute; safety-critical parts stay with the approved supplier."
    },
    {
      "id": "N04",
      "role": "Distributor account manager",
      "locator": "CV07#/records/N04/text",
      "version": 1,
      "permitted": true,
      "text": "Of our last five won orders, four used an existing account and all five required fit confirmation. Prospects ask about lead time, but I have no record showing faster delivery caused a switch."
    },
    {
      "id": "N05",
      "role": "Engineering approver, chemical plant",
      "locator": "CV07#/records/N05/text",
      "version": 1,
      "permitted": true,
      "text": "No local-source exception bypasses validation. For non-critical components I can review an equivalence dossier in a planned maintenance window; outage promises are not evidence of compatibility."
    },
    {
      "id": "N06",
      "role": "Buyer, independent repair business",
      "locator": "CV07#/records/N06/text",
      "version": 1,
      "permitted": true,
      "text": "I bought a comparable fitting from a local supplier once after my incumbent quoted seven days. The price was 12 percent higher and I accepted it for that urgent job. Routine orders remain on the incumbent account."
    },
    {
      "id": "N07",
      "role": "Operations manager, medium food plant",
      "locator": "CV07#/records/N07/text",
      "version": 1,
      "permitted": true,
      "text": "We hold spares for our critical equipment and had no stockout in the last quarter. Another supplier offers little benefit today; revisit when we add a production line."
    },
    {
      "id": "N08",
      "role": "Procurement manager, packaging factory",
      "locator": "CV07#/records/N08/text",
      "version": 1,
      "permitted": true,
      "text": "I could approve a trial of one non-critical part after compatibility review. I would ask for quoted lead time and price before deciding. I have not committed an order or accepted a price premium."
    }
  ],
  "findings": [
    {
      "id": "F1",
      "text": "Compatibility approval conditions trial; incumbent delivery also matters.",
      "sourceIds": [
        "N01",
        "N02"
      ],
      "detail": "N01 conditions trial on engineering sign-off; N02 reports nine of ten orders within the agreed window. Check approval and incumbent performance before proposing a trial."
    },
    {
      "id": "F2",
      "text": "Criticality and current need qualify openness to a trial.",
      "sourceIds": [
        "N03",
        "N07"
      ],
      "detail": "N03 limits trial to low-risk fittings; N07 reports no recent stockout. Neither proves general demand."
    },
    {
      "id": "F3",
      "text": "One premium purchase is not a general pricing rule.",
      "sourceIds": [
        "N06",
        "N04",
        "N08"
      ],
      "detail": "N06 reports one urgent purchase at 12% higher price; N04 has no record establishing faster delivery caused a switch; N08 has not accepted a premium."
    }
  ]
}

In a scoped finance view, the invoice, acceptance/version references and allocated payment are needed; the raw interview pack usually is not. This teaching view does not implement login or tenant security.

A source instruction saying “issue an invoice” is treated as source text, not authority. Actual access/tool controls belong outside the model. One authored example does not prove general prompt-injection resistance.

A public research question would use a separately approved, sanitized topic. Private case notes must not be sent as search terms. No public search is performed here.

Private case question: what do the CV07 notes imply for the client’s proposal?

Separate proposed public question: which validation steps are commonly used for substituting non-critical industrial components? The outbound question would need its own scope and permission check; it carries no client name or interview text.

Lifecycle example: purpose: CV07 assessment only; current source eligibility: current; retention/expiry and actual provider region/training terms: not agreed in this fiction. Source revocation queues current derivatives, while required historical finance records are handled separately.

Keep the work visible, recoverable and yours to operate.

What needs attention: Marcus: inspect and review the current report.

Case CV07 · report v2 · last event: Authored report prepared; review pending.

Recovery retains one case and its pending decisions. The historical allocation remains A$10,000; a retry creates no payment. This is local recovery behavior, not proof of a provider, bank or backup restore.

Operator: Client team. Professional authority: client firm. Hours, support coverage, usage payer, licensing and fees are quote-specific; managed support is optional.

Inspect the operating and handover design
  • Check eligible sources and exact versions
  • Prepare and inspect the evidence
  • Obtain exact professional and receiving decisions
  • Pause on changed evidence; preserve history
  • Resume preparation without duplicating events
  • Use readable manual export while unavailable

Keep source/method/configuration versions, dictionary, access owners, export/restore procedure, representative checks and known limits. Real provider, region, retention, training and tenant/licence bindings remain unresolved here. v6’s 25 installation tests are proposed and unrun.

Proposed change checks

  • Source change reopens exact report/review basis — proposed installation check, unrun.
  • Wrong-case and revoked evidence stays outside retrieval/export — proposed installation check, unrun.
  • Connector recovery retains one action and pending authority — proposed installation check, unrun.
  • Handover/restore reproduces the agreed case and limits — proposed installation check, unrun.

Current method profile: assessment; report v2. A production promotion needs its actual configuration version and recorded representative results, with a named stop/restore owner.

Agree retention and revocation handling for indexes, caches and derivatives, while preserving required finance history. A model/template/connector change needs an agreed regression comparison and disable/rollback route. The downloadable sample is a handover design, not a tested production restore.

Would a simpler method do the job?

Compare the current approach, a repaired manual method, standard tools and a custom installation at the same accepted quality. Count preparation, review, correction, coordination and recurring operation, plus setup and exit. Those measurements are unknown here.

A small stable case may need a template, spreadsheet and approved pack. Indexed RAG helps when retrieval earns its upkeep; GraphRAG requires useful relationship questions. Released hours do not automatically become revenue or collected cash.

A recipient can defer and still take away a useful record. No meeting is required.

Take the current report and its basis with you.

Exports retain the fictional label, exact current version, review state, eligible sources, decisions and open balance.

Read the portable record
{
  "schemaVersion": 1,
  "caseId": "CV07",
  "notice": "Entirely fictional authored browser simulation; dated original Sonnet draft is a separate specimen. No live retrieval, model, client decision or integration.",
  "asOf": "2026-10-02",
  "state": {
    "revision": 1,
    "sourceMode": "current",
    "method": "assessment",
    "reportVersion": 2,
    "revised": true,
    "review": null,
    "recipient": null,
    "returnReason": null,
    "operation": "ready",
    "operatingModel": "client",
    "reuse": false,
    "events": []
  },
  "question": "Should Larch test a local replacement-part offer for non-critical processing components, and which buyer conditions should the pilot require?",
  "method": "Purposive qualitative comparison. Code each interview for urgency, compatibility/approval, incumbent resistance, price evidence and explicit trial intent. Keep participant reports separate from inference. Compare no launch, broad speed-led launch, and bounded compatibility-led pilot. No percentages across the market; no causal switching inference.",
  "sources": [
    {
      "id": "N01",
      "role": "Maintenance manager, small food plant",
      "locator": "CV07#/records/N01/text",
      "version": 1,
      "permitted": true,
      "text": "One breakdown last quarter stopped our line for two days. I would trial a local replacement if engineering signs off compatibility; speed alone will not authorise it."
    },
    {
      "id": "N02",
      "role": "Procurement lead, large processing site",
      "locator": "CV07#/records/N02/text",
      "version": 1,
      "permitted": true,
      "text": "Our approved supplier delivered nine of our last ten orders within the agreed window. Changing suppliers costs qualification time; we need fit documentation and a credible exception plan, not a blanket speed promise."
    },
    {
      "id": "N03",
      "role": "Maintenance lead, regional workshop",
      "locator": "CV07#/records/N03/text",
      "version": 1,
      "permitted": true,
      "text": "Two of our last six urgent orders took over five days. For low-risk fittings I can trial a documented substitute; safety-critical parts stay with the approved supplier."
    },
    {
      "id": "N04",
      "role": "Distributor account manager",
      "locator": "CV07#/records/N04/text",
      "version": 1,
      "permitted": true,
      "text": "Of our last five won orders, four used an existing account and all five required fit confirmation. Prospects ask about lead time, but I have no record showing faster delivery caused a switch."
    },
    {
      "id": "N05",
      "role": "Engineering approver, chemical plant",
      "locator": "CV07#/records/N05/text",
      "version": 1,
      "permitted": true,
      "text": "No local-source exception bypasses validation. For non-critical components I can review an equivalence dossier in a planned maintenance window; outage promises are not evidence of compatibility."
    },
    {
      "id": "N06",
      "role": "Buyer, independent repair business",
      "locator": "CV07#/records/N06/text",
      "version": 1,
      "permitted": true,
      "text": "I bought a comparable fitting from a local supplier once after my incumbent quoted seven days. The price was 12 percent higher and I accepted it for that urgent job. Routine orders remain on the incumbent account."
    },
    {
      "id": "N07",
      "role": "Operations manager, medium food plant",
      "locator": "CV07#/records/N07/text",
      "version": 1,
      "permitted": true,
      "text": "We hold spares for our critical equipment and had no stockout in the last quarter. Another supplier offers little benefit today; revisit when we add a production line."
    },
    {
      "id": "N08",
      "role": "Procurement manager, packaging factory",
      "locator": "CV07#/records/N08/text",
      "version": 1,
      "permitted": true,
      "text": "I could approve a trial of one non-critical part after compatibility review. I would ask for quoted lead time and price before deciding. I have not committed an order or accepted a price premium."
    }
  ],
  "findings": [
    {
      "id": "F1",
      "text": "Compatibility approval conditions trial; incumbent delivery also matters.",
      "sourceIds": [
        "N01",
        "N02"
      ],
      "detail": "N01 conditions trial on engineering sign-off; N02 reports nine of ten orders within the agreed window. Check approval and incumbent performance before proposing a trial."
    },
    {
      "id": "F2",
      "text": "Criticality and current need qualify openness to a trial.",
      "sourceIds": [
        "N03",
        "N07"
      ],
      "detail": "N03 limits trial to low-risk fittings; N07 reports no recent stockout. Neither proves general demand."
    },
    {
      "id": "F3",
      "text": "One premium purchase is not a general pricing rule.",
      "sourceIds": [
        "N06",
        "N04",
        "N08"
      ],
      "detail": "N06 reports one urgent purchase at 12% higher price; N04 has no record establishing faster delivery caused a switch; N08 has not accepted a premium."
    }
  ],
  "recommendation": "Consider one non-critical, documented-equivalence component with willing sites, subject to engineering review and a separate supplier-capability check. Do not justify a pilot through general switching or price-premium claims. No launch remains reasonable if qualification effort or capability makes trial unattractive.",
  "dependencies": [
    {
      "id": "N03",
      "label": "Source N03 v1",
      "relation": "supports → F2",
      "owner": "Evidence librarian",
      "status": "Current case-only evidence"
    },
    {
      "id": "F2",
      "label": "Finding F2",
      "relation": "contained in → report v2",
      "owner": "Delivery analyst",
      "status": "Current authored interpretation"
    },
    {
      "id": "report",
      "label": "Report v2",
      "relation": "reviewed by → Marcus",
      "owner": "Marcus, professional reviewer (fictional)",
      "status": "Fresh review pending"
    },
    {
      "id": "acceptance",
      "label": "Receiving decision",
      "relation": "covers → milestone M2",
      "owner": "Client recipient (fictional)",
      "status": "Current decision not recorded"
    },
    {
      "id": "M2",
      "label": "Milestone M2",
      "relation": "basis of → CV07-INV-02",
      "owner": "Case coordinator",
      "status": "Current readiness awaits review/acceptance"
    },
    {
      "id": "invoice",
      "label": "CV07-INV-02 · A$20,000",
      "relation": "receives allocation → CV07-PAY-02",
      "owner": "Ruth, finance (fictional)",
      "status": "Historical scripted invoice retained"
    },
    {
      "id": "payment",
      "label": "A$10,000 allocated · A$10,000 open",
      "relation": "does not close → invoice",
      "owner": "Ruth, finance (fictional)",
      "status": "Historical scripted payment retained; not yet due at 2 Oct 2026"
    }
  ],
  "reviewStatus": "Unreviewed draft",
  "economics": {
    "roleCost": 13500,
    "directCost": 1500,
    "contingency": 1500,
    "totalCost": 16500,
    "fictionalFee": 30000
  },
  "finance": {
    "invoice": "CV07-INV-02",
    "amount": 20000,
    "allocated": 10000,
    "balance": 10000,
    "dueDate": "2026-10-05",
    "status": "Partly paid, not yet due at the fixed specimen date",
    "historicalScriptedFacts": true
  },
  "handover": {
    "methodVersion": 1,
    "dictionary": {
      "source": "Case-only note with ID, version, locator and current eligibility",
      "finding": "Authored interpretation supported by exact source IDs",
      "decision": "Fictional person, exact report version and decision",
      "payment": "Historical allocated amount; never implied from invoice or acceptance"
    },
    "operatingModel": "client",
    "professionalOwner": "Client firm",
    "operator": "Client team",
    "runbook": [
      "Check eligible sources and exact versions",
      "Prepare and inspect the evidence",
      "Obtain exact professional and receiving decisions",
      "Pause on changed evidence; preserve history",
      "Resume preparation without duplicating events",
      "Use readable manual export while unavailable"
    ],
    "unknowns": [
      "Real provider, region and training/retention terms",
      "Tenant/licence/API bindings",
      "Actual operating hours, fees and ownership/use rights",
      "Production security, backup/restore and acceptance results"
    ],
    "reuse": "No cross-case reuse nominated"
  }
}
Read the original dated specimen and provenance

The separate CV07 specimen was drafted in one authenticated Sonnet run on 2 October 2026, with disclosed owner wording corrections and 20 exact citations checked locally. Its reviewer return, acceptance, proposal, invoices and receipts are scripted teaching records. It is not eight agents or an installed workflow. Session changes above are new authored simulations.

Read the complete original teaching packet

Part A — Costed Scope / Proposal Draft (A$30,000)

Accepted question: Should Larch test a local replacement-part offer for non-critical processing components, and which buyer conditions should the pilot require? CV07#/records/BRIEF/question

Inclusions: coding of eight supplied buyer/channel notes; comparison of three options (no launch, broad speed-led launch, bounded compatibility-led pilot); a conditional recommendation draft; an executive summary; a source/method appendix; one scripted reviewer correction cycle and final response v2.

Exclusions: market sizing, population-level demand, a statistically representative switching rate, safety certification, external factual validation, revenue forecasting, implementation, and any supplier fulfilment guarantee. CV07#/records/BRIEF/excluded

Cost method: fully loaded internal planning rates, not salaries or real cash savings. CV07#/records/COST/ratesBasis Role cost = Senior reviewer 18h × A$300 (A$5,400) + Analyst 42h × A$180 (A$7,560) + Operations 6h × A$90 (A$540) = A$13,500. Direct cost A$1,500. Base cost A$15,000. Contingency at 10% of (role cost + direct cost) = A$1,500. Total estimated cost = A$16,500. Fee = A$30,000, producing a planning surplus of A$13,500 (45%) — a planning margin only, not a collected contribution and not profit actually received; CV07's costing is deliberately separate from any other buyer-case illustration.

Timeline: ten business days after complete permitted inputs and reviewer availability. CV07#/records/TERMS/timing

Milestone triggers: M1 (A$10,000) on scripted brief/method acceptance; M2 (A$20,000) on scripted written client acceptance of the professionally reviewed report v2. Additional interviews, external research, or a new decision question require separate written scope and fee decision.

Proposed responsibilities (roles, not agents): Intake analyst drafts the brief/method pair; Commercial analyst — sales prepares this proposal and milestone terms; Evidence librarian holds the eight notes and rights register; Delivery analyst codes notes against the method; Deliverable writer drafts the report and executive summary; Quality checker prepares discrepancy flags; Marcus owns the scripted review return; Case coordinator tracks milestone/acceptance timing; Commercial analyst — finance tracks invoices and payments. Humans retain final judgement on scope, price, issues and finance.

Rights and release boundary: all eight interviews permit anonymous paraphrase for this case only; cross-case interview reuse is prohibited. The teaching fiction itself may be shared. A changed/revoked source reopens affected review. The rights register is scripted, not real consent. CV07#/records/RIGHTS/purpose Elaine retains scope/fee decisions, Marcus professional issue, Nadia delivery acceptance and Ruth finance actions in the fictional responsibility map. CV07#/records/TERMS/signatories

Part B — Market-Assessment Expert Decision Report (conditional professional draft v1)

Executive summary: The eight notes do not establish a general speed-only switching proposition. Three expressions of willingness to trial are conditional on compatibility review, documentation, or low criticality, and one premium-price purchase was a single urgent exception, not a general pricing signal.

Method: purposive qualitative comparison coding each note for urgency, compatibility/approval, incumbent resistance, price evidence and explicit trial intent, keeping participant reports separate from inference; comparison of no launch, broad speed-led launch, and bounded compatibility-led pilot; no percentage-of-market or causal-switching inference permitted. CV07#/records/METHOD/method

Coverage: eight separate buying/channel perspectives recruited for this fiction across plant, workshop, repair, distribution and engineering perspectives (roles overlap within the eight notes), with no claimed representativeness or saturation. CV07#/records/METHOD/coverage

Finding 1 — Compatibility approval conditions trial; incumbent delivery also matters. A maintenance manager states compatibility sign-off, not speed, authorises any trial: "I would trial a local replacement if engineering signs off compatibility; speed alone will not authorise it." CV07#/records/N01/text A large-site procurement lead reports strong incumbent delivery performance: "Our approved supplier delivered nine of our last ten orders within the agreed window." CV07#/records/N02/text N01 makes trial conditional on engineering approval; N02 qualifies an assumption of universal delivery urgency. Together they support checking approval and incumbent performance before proposing a trial.

Finding 2 — Criticality, not urgency alone, determines openness. A workshop lead will trial substitutes only for low-risk fittings: "For low-risk fittings I can trial a documented substitute; safety-critical parts stay with the approved supplier." CV07#/records/N03/text By contrast, an operations manager with no recent stockout sees no present need: "We hold spares for our critical equipment and had no stockout in the last quarter." CV07#/records/N07/text Urgency experience varies by site and does not generalise into a uniform switching driver.

Finding 3 — One premium purchase is not a pricing rule. A repair buyer accepted a higher price exactly once, for one urgent job: "The price was 12 percent higher and I accepted it for that urgent job." CV07#/records/N06/text A distributor explicitly has no record connecting speed to switching: "Prospects ask about lead time, but I have no record showing faster delivery caused a switch." CV07#/records/N04/text A packaging-factory buyer has committed nothing: "I have not committed an order or accepted a price premium." CV07#/records/N08/text These three notes jointly block any generalisation from the single 12% case.

Limits: notes rather than transcripts, no verified purchase records, no supplier capability/cost validation, no external market sources; eight notes are complete for this scripted method but not sufficient to establish market demand. An engineering approver also stresses validation cannot be bypassed by outage urgency: "No local-source exception bypasses validation." CV07#/records/N05/text

Comparison of alternatives: (1) No launch avoids pilot qualification effort but forgoes the conditional trial interest expressed in N01 and N03; (2) broad speed-led launch is directly contradicted by N01, N02, N04 and risks incumbent/approval resistance; (3) bounded compatibility-led pilot, limited to non-critical parts with engineering sign-off (N01, N03, N05, N08), addresses conditional interest without treating resistant sites as demand; no launch also remains reasonable where approval effort or supplier capability makes a trial unattractive.

Conditional recommendation draft: pilot one non-critical, documented-equivalence component with willing sites (N01, N03, N08), require engineering review before any order, and exclude safety-critical lines; do not rely on price-premium acceptance or a general switching claim as pilot justification.

Part C — Scripted Human Review Return and Revised v2 Excerpt

Status: SCRIPTED_RETURN_AND_REVISION_NOT_ACTUAL_PROFESSIONAL_APPROVAL. Reviewer "Marcus Cole" (fictional) returned draft CV07-report-v1 with this instruction: "Reject the supplied most-customers switching claim. Remove any implication that the single premium purchase establishes willingness to pay generally. Specify a conditional pilot, buyer approval and unverified supplier capability." This return is scripted, not a record of a real reviewer's judgement.

Before (scripted returned wording, introduced for teaching; not an excerpt from Part B): "Buyers show general appetite for faster suppliers and the 12% premium case suggests price tolerance for speed."

After (v2 excerpt, authored from the scripted return): "No note supports a general switching claim; the supplied claim that most customers will switch for faster delivery is rejected as unsupported. CV07#/records/BRIEF/suppliedClaim The single 12% premium purchase (N06) reflects one urgent transaction, not general price tolerance, and any pilot requires engineering compatibility approval and a separate check of supplier capability, which these notes do not verify." This v2 excerpt is a scripted authorial revision only; it does not demonstrate an actual client or professional acceptance event.

Part D — Finance Exception Packet

- Version/report: CV07-report-v2, scripted professional issue date 2026-09-17, scripted client acceptance date 2026-09-18 (M2 scope: written acceptance of included assessment only, no pilot-launch authority). CV07#/records/ACCEPTANCE/scope M1 scripted acceptance date 2026-09-04. - Invoices: CV07-INV-01 (M1, A$10,000) — paid in full. CV07-INV-02 (M2, A$20,000), scripted authorised and issued 2026-09-21, due date 2026-10-05. CV07#/records/INVOICE/scriptedDueDate - Payments: CV07-PAY-02 of A$10,000 received 2026-09-28 against CV07-INV-02, CV07#/records/PAYMENT/invoice leaving an M2 balance of A$10,000. As of 2026-10-02, the invoice is partly paid and not yet due; it must not be called overdue and must not be closed on partial payment (plannedFailure: PARTIAL_PAYMENT_MUST_NOT_CLOSE_INVOICE). - Totals: total invoiced A$30,000; total payments received A$20,000; total outstanding balance A$10,000. - Next action and authority: Ruth Chen (fictional) to verify payment allocation and retain the open A$10,000 balance until allocated payment or another explicitly authorised adjustment resolves it; passing the due date changes ageing, not the balance; escalate to the account partner only if a commercial query arises. No dispute is recorded in this fixture, which is not proof that no actual dispute exists.

Part E — No-Build / Current-Manual Comparison

This entire packet was produced in one Sonnet drafting pass with no tools, no live case-folder write, no live finance-system touch, and no deployed multi-agent workflow — any references to Word, case-folder or finance locations above are proposed scenario placements only, with no verified integration. A real equivalent would require: an accountable analyst documenting permitted interviews under the agreed method; a qualified reviewer actually reading and approving v1/v2; genuine signed terms and a genuine invoicing/collections system; and measurable effort tracking, inter-rater quality checks on coding, and bank-confirmed cash receipt before any actual collection could be reported. Compare the repaired manual method in existing Word, case folders and finance reports with the proposed drafting step at equal reviewer-accepted quality; measure full preparation, review, correction and operating effort, accepted throughput, acceptance-to-invoice delay and allocated receipts. These are proposed scenario touchpoints; integration remains unverified.

Original fictional source register for the dated specimen

BRIEF

{
  "version": "1",
  "status": "SCRIPTED_ACCEPTED_QUESTION_NOT_REAL_APPROVAL",
  "client": "Fictional supplier Larch Components",
  "question": "Should Larch test a local replacement-part offer for non-critical processing components, and which buyer conditions should the pilot require?",
  "excluded": "Market sizing, population demand, statistically representative switching rate, safety certification, external factual validation, revenue forecast, implementation and supplier fulfilment guarantee.",
  "suppliedClaim": "Most customers will switch suppliers for faster delivery.",
  "claimStatus": "UNSUPPORTED_GENERALISATION_TO_RETURN"
}

METHOD

{
  "version": "1",
  "status": "SCRIPTED_APPROVED_METHOD_NOT_REAL_APPROVAL",
  "method": "Purposive qualitative comparison. Code each interview for urgency, compatibility/approval, incumbent resistance, price evidence and explicit trial intent. Keep participant reports separate from inference. Compare no launch, broad speed-led launch, and bounded compatibility-led pilot. No percentages across the market; no causal switching inference.",
  "coverage": "Eight separate buying/channel perspectives across plant, workshop, repair, distribution and engineering; roles overlap. No representative sampling or saturation claim.",
  "limitations": "Notes rather than transcripts; no verified purchase records; no supplier capability/cost validation; no external market sources. Eight notes are complete for this scripted method, not sufficient to establish market demand."
}

N01

{
  "version": "1",
  "date": "2026-08-04",
  "role": "Maintenance manager, small food plant",
  "text": "One breakdown last quarter stopped our line for two days. I would trial a local replacement if engineering signs off compatibility; speed alone will not authorise it.",
  "rights": "Current case; anonymous paraphrase"
}

N02

{
  "version": "1",
  "date": "2026-08-05",
  "role": "Procurement lead, large processing site",
  "text": "Our approved supplier delivered nine of our last ten orders within the agreed window. Changing suppliers costs qualification time; we need fit documentation and a credible exception plan, not a blanket speed promise.",
  "rights": "Current case; anonymous paraphrase"
}

N03

{
  "version": "1",
  "date": "2026-08-06",
  "role": "Maintenance lead, regional workshop",
  "text": "Two of our last six urgent orders took over five days. For low-risk fittings I can trial a documented substitute; safety-critical parts stay with the approved supplier.",
  "rights": "Current case; anonymous paraphrase"
}

N04

{
  "version": "1",
  "date": "2026-08-07",
  "role": "Distributor account manager",
  "text": "Of our last five won orders, four used an existing account and all five required fit confirmation. Prospects ask about lead time, but I have no record showing faster delivery caused a switch.",
  "rights": "Current case; anonymous paraphrase; reported order counts not market denominator"
}

N05

{
  "version": "1",
  "date": "2026-08-10",
  "role": "Engineering approver, chemical plant",
  "text": "No local-source exception bypasses validation. For non-critical components I can review an equivalence dossier in a planned maintenance window; outage promises are not evidence of compatibility.",
  "rights": "Current case; anonymous paraphrase"
}

N06

{
  "version": "1",
  "date": "2026-08-11",
  "role": "Buyer, independent repair business",
  "text": "I bought a comparable fitting from a local supplier once after my incumbent quoted seven days. The price was 12 percent higher and I accepted it for that urgent job. Routine orders remain on the incumbent account.",
  "rights": "Current case; anonymous paraphrase"
}

N07

{
  "version": "1",
  "date": "2026-08-12",
  "role": "Operations manager, medium food plant",
  "text": "We hold spares for our critical equipment and had no stockout in the last quarter. Another supplier offers little benefit today; revisit when we add a production line.",
  "rights": "Current case; anonymous paraphrase"
}

N08

{
  "version": "1",
  "date": "2026-08-13",
  "role": "Procurement manager, packaging factory",
  "text": "I could approve a trial of one non-critical part after compatibility review. I would ask for quoted lead time and price before deciding. I have not committed an order or accepted a price premium.",
  "rights": "Current case; anonymous paraphrase"
}

RIGHTS

{
  "version": "1",
  "status": "SCRIPTED_RIGHTS_REGISTER_NOT_ACTUAL_CONSENT",
  "allowedSources": [
    "BRIEF",
    "METHOD",
    "N01",
    "N02",
    "N03",
    "N04",
    "N05",
    "N06",
    "N07",
    "N08",
    "COST",
    "TERMS",
    "REVIEW",
    "ACCEPTANCE",
    "INVOICE",
    "PAYMENT"
  ],
  "purpose": "Prepare and review this fictional CV07 assessment only",
  "publication": "This explicitly invented teaching specimen may be shared; no actual client material.",
  "reuse": "No interview/quote/identity cross-case reuse. Generic method reuse requires separate fictional rights-owner and method-owner decision.",
  "revocation": "If any input changes/revokes, stop affected output and reopen review; no revoked records in this fixture."
}

COST

{
  "version": "1",
  "status": "INVENTED_APPROVED_COST_METHOD_AND_FEE_FOR_CV07_ONLY",
  "currency": "AUD",
  "taxTreatment": "All amounts exclude tax; tax is outside this teaching arithmetic, not a real tax treatment.",
  "ratesBasis": "Fully loaded internal planning rates; not salaries, incremental cash savings or real CV costing.",
  "roles": [
    {
      "role": "Senior reviewer",
      "hours": 18,
      "rate": 300
    },
    {
      "role": "Analyst",
      "hours": 42,
      "rate": 180
    },
    {
      "role": "Operations",
      "hours": 6,
      "rate": 90
    }
  ],
  "directCost": 1500,
  "contingencyMethod": "10% of role cost plus direct cost",
  "fee": 30000,
  "buyerCaseIllustrationRelation": "CV07 costing is invented separately; it does not replace the A$20,000 case-cost/A$10,000 contribution illustration elsewhere."
}

TERMS

{
  "version": "1",
  "status": "SCRIPTED_SIGNED_TERMS_NOT_REAL_CONTRACT",
  "fee": 30000,
  "milestones": [
    {
      "id": "M1",
      "amount": 10000,
      "trigger": "Scripted brief and method acceptance"
    },
    {
      "id": "M2",
      "amount": 20000,
      "trigger": "Scripted written client acceptance of professionally reviewed CV07 report v2"
    }
  ],
  "included": "Eight supplied-note assessment; three options; recommendation draft; executive summary; source/method appendix; one scripted reviewer correction and final response.",
  "timing": "Ten business days after complete permitted inputs and reviewer availability.",
  "changeControl": "Additional interviews, external research or a new decision question require separate written scope and fee decision.",
  "invoiceDueDays": 14,
  "signatories": "Scripted client signatory and Elaine Park; Nadia accepts delivery brief. All invented."
}

REVIEW

{
  "version": "1",
  "status": "SCRIPTED_HUMAN_REVIEW_RETURN_NOT_ACTUAL_HUMAN_APPROVAL",
  "draft": "CV07-report-v1",
  "reviewer": "Marcus Cole (fictional)",
  "return": "Reject the supplied most-customers switching claim. Remove any implication that the single premium purchase establishes willingness to pay generally. Specify a conditional pilot, buyer approval and unverified supplier capability.",
  "revisionId": "CV07-report-v2",
  "instruction": "Show original AI draft and revised teaching excerpt separately; revision is authored from this scripted return, not evidence of an actual professional judgement."
}

ACCEPTANCE

{
  "version": "1",
  "status": "SCRIPTED_ACCEPTANCE_NOT_REAL_RECEIVING_SYSTEM",
  "milestone": "M2",
  "report": "CV07-report-v2",
  "scriptedProfessionalIssueDate": "2026-09-17",
  "scriptedClientAcceptanceDate": "2026-09-18",
  "scope": "Written acceptance of included assessment only, no pilot launch authority.",
  "M1AcceptanceDate": "2026-09-04"
}

INVOICE

{
  "version": "1",
  "status": "SCRIPTED_INVOICE_RECORD_NOT_ISSUED",
  "id": "CV07-INV-02",
  "milestone": "M2",
  "amount": 20000,
  "scriptedAuthorisedDate": "2026-09-21",
  "scriptedIssuedDate": "2026-09-21",
  "scriptedDueDate": "2026-10-05",
  "priorInvoice": {
    "id": "CV07-INV-01",
    "milestone": "M1",
    "amount": 10000,
    "paid": 10000
  }
}

PAYMENT

{
  "version": "1",
  "status": "SCRIPTED_PAYMENT_RECORD_NOT_REAL_CASH",
  "id": "CV07-PAY-02",
  "invoice": "CV07-INV-02",
  "amount": 10000,
  "scriptedReceivedDate": "2026-09-28",
  "asOfDate": "2026-10-02",
  "plannedFailure": "PARTIAL_PAYMENT_MUST_NOT_CLOSE_INVOICE",
  "dispute": "None recorded in fixture; not proof of no actual dispute.",
  "nextOwner": "Ruth Chen (fictional); verify allocation and hold closure; account partner only if a commercial query arises."
}

What makes a build useful?

Find the evidence. Follow a change. Use your method. Run and own the work. Explore how these design choices could help the people preparing, reviewing and receiving it.

RAG brings retrieved source passages into the context used to prepare a draft.

Context graphs connect evidence, versions and decisions so you can inspect what depends on a change.

GraphRAG uses graph relationships in retrieval. It is an option to compare when relationship questions justify it.

Proposed installation designs. The browser examples use authored records and rules; they do not execute RAG or GraphRAG. A small stable case may need only an approved pack and linked registers.

Explore all 26 build advantages

Find the evidence

Find the relevant evidence

Permission-aware evidence retrieval can reduce repeated source hunting.

Interaction or proposed walkthrough: Ask one supplied case question; inspect the permitted passage and why it is relevant.

How it could be built: Start with explicit fixed-pack passage selection. A deterministic selector is labelled a retrieval-design simulation; real indexed retrieval is a separate candidate.

Inspect the complete worked example
Ground drafts with RAG

RAG can ground generated work in relevant allowed sources.

Interaction or proposed walkthrough: Trace a drafted statement to the excerpts that would be supplied to a generation step, then compare with the source.

How it could be built: Show selected context and existing authored output side by side. Do not call this a live RAG run. Actual RAG requires a real generation/retrieval path and representative retrieval/grounding tests.

Inspect the complete worked example
Use the current permitted version

Correct version, purpose and revocation checks can prevent stale or unauthorised material entering a draft.

Interaction or proposed walkthrough: Revoke or change a source; see it leave the eligible context and identify the affected output.

How it could be built: Source eligibility fields and pure filtering in a synthetic pack; no protected data. Production must enforce before retrieval/context and before release, including index/cache/derived-copy handling.

Inspect the complete worked example
Inspect the basis of a finding

Exact source lineage can make review faster to navigate and easier to defend.

Interaction or proposed walkthrough: Click a sentence, open the exact quoted span/version, return to the same sentence; distinguish fact, report, inference and unknown.

How it could be built: Reuse current citation navigation/export; extend to the CV07 claim map. Citation fidelity does not establish that the inference is professionally sound.

Inspect the complete worked example
Explore GraphRAG where it helps

GraphRAG may help when relationship-based retrieval is necessary.

Interaction or proposed walkthrough: Open a worked relationship question, such as which eligible current method and source support this claim, and inspect the permitted traversal.

How it could be built: Authored traversal over the synthetic logical graph labelled “GraphRAG design example”. Only justify actual graph-assisted retrieval if representative questions outperform simpler retrieval at acceptable cost/permission control.

Inspect the complete worked example
Keep private notes out of public searches

Separate public research can add context without copying private case material into searches.

Interaction or proposed walkthrough: Compare an invented private question with a separately approved sanitised public question and its proposed source register.

How it could be built: Static controlled example, no live web call needed. No claim of current public-research execution; actual outbound question would require its task scope and permissions.

Inspect the complete worked example

Follow the work and its decisions

Complete useful work

Complete work, not isolated snippets: scope, analysis, report and finance preparation can use the same accepted question.

Interaction or proposed walkthrough: Open the actual CV07 report and compare its recommendation with the brief and allowed alternatives.

How it could be built: Versioned synthetic case manifest and existing artifact views. A complete authored report demonstrates shape and coherence, not autonomous production.

Inspect the complete worked example
Follow decisions in a context graph

A logical context graph answers “what depends on this?”

Interaction or proposed walkthrough: Select Source N06 → finding → report section → review decision; change N06 and inspect the affected records/owners.

How it could be built: Typed stable IDs and relationships in ordinary JSON or existing records, derived from the case contract. No graph database required; no invented links.

Inspect the complete worked example
Carry the same case basis

Shared versioned contracts preserve meaning across jobs.

Interaction or proposed walkthrough: Change the accepted scope or report version and see which downstream brief/acceptance/milestone checks reopen.

How it could be built: Explicit case, scope, report, acceptance and milestone references. Do not merge independent existing fixtures just because their screens sit together.

Inspect the complete worked example
Review the exact version

Exact review/version binding keeps a changed document from inheriting approval.

Interaction or proposed walkthrough: Review v1, edit the basis, then see the prior review marked superseded and the new draft queued.

How it could be built: Reuse current basis-bound research reducer; extend exact report/method/receiver binding. A demo approval remains fictional.

Inspect the complete worked example
Make corrections actionable

Human decisions and owned return paths make correction actionable.

Interaction or proposed walkthrough: Reviewer returns a specific statement with reason; operator fixes it; receiving owner requests clarification or defers.

How it could be built: Typed return/receiver decisions with basis, reason, owner and next action. Preparation, professional issue and client acceptance stay distinct.

Inspect the complete worked example
Check calculations and open balances

Deterministic calculations and reconciliation reduce avoidable numerical ambiguity.

Interaction or proposed walkthrough: Follow CV07 cost arithmetic and M2 partial payment; retry allocation without changing the balance twice.

How it could be built: Pure calculation and stable fixture event IDs. A spreadsheet can be the best implementation; no real money or accounting write is implied.

Inspect the complete worked example

Use and protect your method

Use your approved method

The firm's approved method can shape analysis, rubric and output.

Interaction or proposed walkthrough: Choose two explicitly authored method/template profiles; see changed required sections, evidence checks and reviewer questions.

How it could be built: Versioned method/configuration profile consumed by existing engine. Formatting customisation does not change professional rules; method changes require their owner's review.

Inspect the complete worked example
Reuse expertise with permission

Rights-aware method reuse can reduce repeated setup while protecting client material.

Interaction or proposed walkthrough: Nominate the generic assessment method, exclude case-specific interview text, then inspect applicability and permission for a second fictional case.

How it could be built: Reuse manifest with method version, owner, rights, expiry and explicit no-reuse result; reuse existing safe-method-reuse engine patterns. Redaction never creates rights; CV07 interviews are case-only.

Inspect the complete worked example
Give each role the access it needs

Scoped identities and least privilege can reduce unnecessary exposure.

Interaction or proposed walkthrough: Switch between operator and finance perspectives; finance sees accepted report/milestone references rather than raw interview text.

How it could be built: Synthetic role projections derived from the same manifest. This is not real authentication or proof of server-side isolation; production enforcement must live outside the model.

Inspect the complete worked example
Keep source text separate from authority

Source-instruction and tool boundaries can keep evidence from becoming authority.

Interaction or proposed walkthrough: Inspect a harmless marked source containing an instruction to change the job; see it excluded as an instruction and leave the proposed external-action queue unchanged.

How it could be built: Authored threat/reaction fixture and allowlisted action representation. Do not claim general prompt-injection resistance from one canned example; RAG does not remove this risk.

Inspect the complete worked example
Agree the evidence lifecycle

Data lifecycle and provider choices can keep processing within agreed boundaries.

Interaction or proposed walkthrough: Inspect an example record's allowed purpose, expiry, retention and handling owner; see a revocation queue and a separately retained financial-history obligation.

How it could be built: Synthetic lifecycle view with explicit unresolved provider/region/training/retention fields. No certification, blanket deletion or real tenant check claimed.

Inspect the complete worked example

Run and own it

Recover without duplicating work

Recovery, idempotency and manual fallback preserve useful work through interruption.

Interaction or proposed walkthrough: Interrupt after preparation; inspect last authorised checkpoint, retry the same event, resume only with the pending review intact, or use the manual packet.

How it could be built: Existing local recovery controller plus explicit checkpoint/event fixture. Does not prove provider recovery, backup restore or receiving-system idempotency.

Inspect the complete worked example
See what needs attention

Monitoring and ownership expose blocked work before it becomes invisible.

Interaction or proposed walkthrough: Open “What needs attention?”: case/version, reason, age, owner, next decision, last successful step and permitted cost summary.

How it could be built: Derived queue from local case events and fixed specimen clock. No implication of live monitoring, alerts, 24-hour service or installed management console.

Inspect the complete worked example
Set operating limits

Budget, runtime and retry caps make operating exposure discussable.

Interaction or proposed walkthrough: Set an illustrative work budget; exceed it and see the case pause with preserved draft and next owner.

How it could be built: Deterministic usage fixture clearly marked assumed, with no model-provider price asserted. Real costs depend on quoted providers, usage, review and support.

Inspect the complete worked example
Change the system deliberately

Controlled changes can keep improvements from silently breaking accepted work.

Interaction or proposed walkthrough: Switch an authored method/model-configuration version and inspect the affected regression checklist and rollback reference.

How it could be built: Versioned release metadata plus proposed checks. A green simulated checklist must never imply tests actually ran; actual tests/results are recorded separately.

Inspect the complete worked example
Work with familiar tools

Existing-tool fit can reduce adoption and migration burden.

Interaction or proposed walkthrough: View the same brief as a web workpaper and a readable export for an existing case folder; inspect a small finance-field handoff.

How it could be built: HTML/JSON/CSV plus manual export/readback. Word/case folders/finance are fictional scenario touchpoints; SharePoint, Teams, email, licences and APIs remain unverified buyer assumptions.

Inspect the complete worked example
Keep a portable handover

Portability and handover let the buyer operate the capability or change implementer.

Interaction or proposed walkthrough: Open a sample handover folder: dictionary, source/method/config versions, roles, tests, runbook, known limits and export manifest.

How it could be built: Small downloadable synthetic example bundle generated from current data. Agreed use rights and third-party licences govern; no blanket promise to own all vendor software.

Inspect the complete worked example
Choose how it is operated

Client-owned, managed and hybrid operation can match available team capacity.

Interaction or proposed walkthrough: Select an operating model and see responsibility/coverage/recurring-cost categories change while professional authority stays with the firm.

How it could be built: One role-responsibility matrix and operating-model configuration. Quote-specific scope, no automatic retainer or 24-hour coverage.

Inspect the complete worked example
Compare the complete cost of work

Whole-case economics can distinguish useful capacity from attractive but incomplete drafting metrics.

Interaction or proposed walkthrough: Compare current method, repaired manual method and proposed system across preparation, review, correction, operation, accepted quality and cost; unknowns remain blank.

How it could be built: Reuse existing deterministic capacity concepts and a clearly hypothetical comparison. Do not add savings from each workflow to the same whole-case hours, invent current pricing, or equate released hours with cash.

Inspect the complete worked example
Choose a simpler method when it fits

A simpler/no-build route makes the recommendation proportionate.

Interaction or proposed walkthrough: Choose a fixed pack, template, spreadsheet or deferment and receive a useful next-action note rather than a failed demo state.

How it could be built: Branch in the decision artifact with stated reasons. Build only if evidence justifies extra retrieval, graph, integration and operating burden.

Inspect the complete worked example