Twenty-two days. Recommend revise.

Scenario date: 3 October 2026 Gate: Simulation: FrontierOrg is fictional. This entry authorises a method, not a company.

Next question

Can one service promise be joined across CRM, worker, business partner, and invoice without inventing a benefit?

Board

The mandate is a hypothesis, not a target percentage. A customer service promise should be traceable from a fictional CRM case to a held invoice, with a named human at each handoff. Success is a join a reader can inspect, a decision log, and empty scorecard cells left empty.

Decision: proceed to mapping in Week 1. No pilot. No agent in the path. The board triad — customer outcome, employee transition, risk and cost — is equal. A gap in any one is enough to pause.

Sponsor on the page is a fictional chief executive. Nothing here binds a real board.

Investors

Nothing is for sale. There is no valuation, no revenue, and no saving. The only asset in view is a public method. Time spent so far is uncosted. COST-001 is opened so that absence stays visible.

Customers and partners

No customer exists. The first story will use Harbour Grid Municipal, a fictional account at Northwater Distribution, a fictional energy-distribution operating company. That choice is a working Week 1 setting, not a locked brand. Any date in the fixture is synthetic. Partners are not being told a thing, because they are not real.

Employees

Fifty thousand is a planning total for human workers. It is not a directory we provisioned. Agent and service identities will be modelled apart from that total and will not inflate it. No role is declared redundant. PEOPLE-001 asks what the service coordinator, billing analyst, and data steward actually do before any task is redesigned. There is no workforce to consult; the diary will not pretend there was.

Evidence

Item	State
Scorecards	Day 0 shells. Actuals: not measured.
Fixture	Not yet generated into the story (lands with Week 1 as seed 20261003).
Issues	DATA-001 named, not yet evidenced. PEOPLE-001 open. COST-001 open.

Source: diary/day-0.md

Scenario date: 2026-10-05 (Monday) Gate: Gate 0 — sponsor and mandate Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional CEO (sponsor on the page only). Amina Okonkwo is named as the future service coordinator and is not yet in a case. No workforce exists to consult.

What progressed

Wrote the engagement hypothesis: one service promise at Northwater Distribution must be traceable to a held invoice with a named human at each handoff. Ethics constraints recorded: simulated directory only, no vendor endorsement, no real CKI claim, pause beats a fake win. Operating company for the first story remains Northwater Distribution.

Risk, cost, and enablement

• Risk: No new control failure. The risk is starting mapping without an owner for the pause. Owner named as the fictional CEO, which means a human editor outside the fiction (Craig) still approves anything public.
• Cost: COST-001 stays open. No licence, inference, or day-rate is stored.
• Enablement: A one-page charter is the only enablement. Prosci ADKAR is a lens, not evidence that anyone was trained.

Issues

Movement	Detail
Opened	None.
Closed	None.
Still open	PEOPLE-001 open. COST-001 open. DATA-001 named on Day 0, not yet evidenced in a row.

Scorecard delta

No actual moves. All three scorecards stay not measured. Decision text updated from 'commission' to 'mapping authorised for one operating company, no pilot'.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Authorise current-state mapping of a single path. Do not deploy an agent.

Next question

Can the path be opened in the fixture without inventing a customer outcome?

Source: diary/day-01.md

Scenario date: 2026-10-06 (Tuesday) Gate: Gate 1 — current-state work Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo, service coordinator (O*NET 43-5032.00, partial match). Rowan Ellis, fictional liaison at Harbour Grid Municipal. Both names are fabricated.

What progressed

In the fixture, CASE-61003 opens at 09:14 Europe/London with a feeder-restoration promise of 20 October 2026. Amina acknowledges it at 11:02. Parts are not confirmed by 15:40. The defect is now a row, not a slogan.

Risk, cost, and enablement

• Risk: DATA-001 is evidenced: promise date before stock. Customer harm is plausible in the story and not measured.
• Cost: Still uncosted. Timestamps are not converted into hours saved.
• Enablement: The coordinator's handoff is written. Nothing was taken off the role.

Issues

Movement	Detail
Opened	DATA-001 (promise before stock).
Closed	None.
Still open	PEOPLE-001, COST-001.

Scorecard delta

Operational card records fixture cardinality: 1 case in data/sample. That count is a file fact, not a rate. Customer, people, and cost actuals remain not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep mapping. Do not put an assistant on the acknowledgement step.

Next question

What does billing do with a promise that parts cannot support?

Source: diary/day-02.md

Scenario date: 2026-10-07 (Wednesday) Gate: Gate 1 — exceptions and controls Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Jonas Berg, billing analyst (O*NET 43-3021.00, partial). Priya Raman, data steward (O*NET 15-1243.00, weak match). Amina remains the case owner.

What progressed

Jonas raises INV-61003 against BP-61003 and holds it because alias BP-61003-A is a duplicate suspect. Priya reviews the join at 16:45 and does not silently merge the alias. The hold is the control.

Risk, cost, and enablement

• Risk: Two business-partner rows for one fictional account. A merge without a steward would hide DATA-001.
• Cost: Invoice amount is blank on purpose. Hold is not a cash figure.
• Enablement: Billing and stewardship are now named handoffs. No training record exists.

Issues

Movement	Detail
Opened	None. DATA-001 gains the duplicate-partner evidence.
Closed	None.
Still open	DATA-001, PEOPLE-001, COST-001.

Scorecard delta

Operational exception text now cites the hold. Actuals remain not measured. No satisfaction score.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Do not clear the hold to make the path look finished.

Next question

Does the board pause, or does someone argue the path is 'agent-ready' because the steps are listed?

Source: diary/day-03.md

Scenario date: 2026-10-08 (Thursday) Gate: Gate 0 decision inside Gate 1 Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

The three named personas plus fictional board. Agent identity AGT-61003-DRAFT is modelled and not a person.

What progressed

Wednesday diary window (8 October, 06:30 Europe/London) publishes the Week 1 cut: the promise outruns the parts. This day records the decision in the activity log. The public Wednesday file remains diary/week-1-2026-10-08.md.

Risk, cost, and enablement

• Risk: Pressure to demo an assistant on a broken join. Refused.
• Cost: COST-001 unchanged. No forecast range.
• Enablement: Publishing the refusal is the enablement. It stops a later pilot skipping the handoffs.

Issues

Movement	Detail
Opened	None.
Closed	None.
Still open	DATA-001, PEOPLE-001, COST-001.

Scorecard delta

C-suite decision on risk/cost becomes 'do not start an assistant on this path'. People decision: no task removed. Customer actual: not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

AGT-61003-DRAFT stays not deployed. Pause.

Next question

What lineage is actually proven by the six events, and what is still a label?

Source: diary/day-04.md

Scenario date: 2026-10-09 (Friday) Gate: Gate 2 — data reality, started Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Priya Raman leads. Jonas and Amina confirm they can point at their own event rows. ESCO crosswalk owner: none.

What progressed

Traced SCN-61003 across crm_cases, workers, sap_business_partners, sap_invoices, and process_events. Keys hold for this one scenario. ESCO URIs are still empty. Directory rows say provisioned_in_entra = no.

Risk, cost, and enablement

• Risk: A reader could treat a successful join as data quality in the wild. It is one seeded story.
• Cost: No integration cost recorded.
• Enablement: A data dictionary exists for the small fixture. It does not licence anything.

Issues

Movement	Detail
Opened	DATA-003 — ESCO v1.2.1 crosswalk absent. Do not invent URIs.
Closed	None.
Still open	DATA-001, PEOPLE-001, COST-001, DATA-003.

Scorecard delta

Operational card notes the join keys that resolve. Still not a quality percentage.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Do not start a second operating company until this join's defects are either accepted or fixed in the fixture on purpose.

Next question

Which licences would a real pilot need, and which of those do we refuse to invent?

Source: diary/day-05.md

Scenario date: 2026-10-12 (Monday) Gate: Gate 2 — licence reality Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional CFO and a fictional technology owner. No vendor salesperson is in the story.

What progressed

Listed the classes of licence a later pilot would have to name: identity, CRM analogue, ERP analogue, model hosting, and logging. Every class is 'not inventoried'. Processing location is unknown. No API quota is stored.

Risk, cost, and enablement

• Risk: RISK-001 opened: building on an unnamed tenant, region, and retention rule.
• Cost: COST-001 stays open and now explicitly includes absent SKUs. Still no pounds.
• Enablement: Enablement is blocked on purpose. You cannot train people on a tool you have not named.

Issues

Movement	Detail
Opened	RISK-001.
Closed	None.
Still open	DATA-001, DATA-003, PEOPLE-001, COST-001, RISK-001.

Scorecard delta

Risk/cost scorecard cites RISK-001. Actual and cost_to_date remain not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Licence inventory is a precondition for Gate 5. It is not started. No sandbox.

Next question

Can O*NET tell us which tasks exist in the holding group without pretending the codes are our job descriptions?

Source: diary/day-06.md

Scenario date: 2026-10-13 (Tuesday) Gate: Gate 1 extended — work inventory from an external taxonomy Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Priya owns the extract. A fictional workforce-intelligence lead is named and has not validated a single title. Amina's code remains a partial match.

What progressed

Loaded O*NET 31.0 (August 2026 text release) from the O*NET Resource Center. Generator generators/onet_frontier_map.py keeps 302 occupations relevant to an infrastructure holding group and 5,932 task statements. Department tags are a FrontierOrg guess. Essential Skills (importance) stand in for the retired Skills file.

Risk, cost, and enablement

• Risk: DATA-002 opened: department tags and any later AI labels are keyword heuristics. USDOL has not endorsed the modification.
• Cost: Download and labelling time is uncosted.
• Enablement: The map is readable. It is not a consultation.

Issues

Movement	Detail
Opened	DATA-002.
Closed	None.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, COST-001, RISK-001.

Scorecard delta

Fixture metric, not a performance actual: 302 occupations and 5,932 tasks in data/generated. Scorecard actuals for customer, people, and cost stay not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Publish the map as a draft inventory. Do not treat SOC codes as redundancy evidence.

Next question

Who would have to sit in a room before a department tag is allowed to drive a pilot?

Source: diary/day-07.md

Scenario date: 2026-10-14 (Wednesday) Gate: Gate 1 — how the map will be read Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Same three, plus the pattern borrowed from organisationalunderstanding.com: an occupation has tasks, skills, and a separate AI layer that is labelled as a modification. No worker has logged in, because the directory is simulated.

What progressed

Published apps/site/org-map.html from org_map_summary.json. Departments list occupations and task counts. Documented the bridge to OrgUnderstanding and the WorkDNA work-chart idea: reporting lines do not locate the work. Wednesday draft slot may open; this entry is the human activity log, not an auto-published win.

Risk, cost, and enablement

• Risk: A department page can look like coverage. Thirteen departments in the guess are not thirteen consulted teams.
• Cost: Still not measured.
• Enablement: PEOPLE-002 opened: no validation session with the people who would do the work. Exposure is not a transition plan (ILO).

Issues

Movement	Detail
Opened	PEOPLE-002.
Closed	None.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001.

Scorecard delta

People scorecard decision: org map is a draft. Consultation count is a fixture fact of zero sessions.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep the page public and labelled heuristic. Do not rank a build list yet.

Next question

Which tasks must stay human even when the wording looks clerical?

Source: diary/day-08.md

Scenario date: 2026-10-15 (Thursday) Gate: Gate 4 preview — no-go stays explicit. Gate 3 not opened. Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Priya reviews the suitability column. A fictional safety lead is the reason RISK-002 exists. Jonas is not asked to automate billing. Amina is not asked to let an agent promise a date.

What progressed

ai_workload_candidates.csv classifies each of the 5,932 tasks as assist, augment, automate-candidate, or human-only. The heuristic defaults to augment when the words are weak, so most rows are not automation. Human-only catches a thin set of safety, emergency, statutory, and physical-control phrases. Automate-candidate is rare and still carries a human gate.

Risk, cost, and enablement

• Risk: RISK-002 opened: a safety-critical task must not be relabelled automate-candidate without a validation session. Keyword search will miss hazards phrased mildly.
• Cost: BENEFIT-001 opened as a standing non-claim. No benefit figure is allowed on this column. COST-001 remains the empty envelope.
• Enablement: Human gates are written on every row. They are not implemented in a system.

Issues

Movement	Detail
Opened	RISK-002, BENEFIT-001.
Closed	None.
Still open	All prior issues.

Scorecard delta

No ROI cell. Suitability counts may be cited as fixture counts of labels, not as value. Customer outcome not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Do not open Gate 5. The portfolio item 'agent on the service promise' stays an explicit no-go.

Next question

Can a larger synthetic population keep the same joins without being mistaken for the 50,000?

Source: diary/day-09.md

Scenario date: 2026-10-16 (Friday) Gate: Gate 2 — population fixture, not scale Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

The original three remain the only named characters in the diary. The 2,000 workers are numbered synthetic identities (example.com). Ten agent and service identities sit outside the human count.

What progressed

generators/sample_large.py wrote data/sample_large at seed 20261003: 2,000 humans, matching directory rows, CRM accounts, cases, SAP-like partners, invoices, and events. Referential checks passed in the generator. About one case in five repeats promise-before-stock. Every eighth account has a duplicate-suspect partner. Amounts are blank. The 50,000 planning total is documented as a local command into gitignored data/sample_full and was not committed.

Risk, cost, and enablement

• Risk: Volume can be misread as evidence. It is a seed. DATA-001 is now a pattern in the large file as well as in SCN-61003, still unresolved.
• Cost: Not measured. More rows do not create a cost model.
• Enablement: No consultation was added by adding rows. PEOPLE-001 and PEOPLE-002 stay open.

Issues

Movement	Detail
Opened	None.
Closed	None. Pause stands.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

Fixture cardinality on the operational card: 2,000 workers in data/sample_large, plus the original 3 in data/sample. Not a headcount result. Not an FTE saving. Actuals not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Stop the ten-day burst here. Next human review is the department tags and the human-only list, not a pilot.

Next question

Which twenty occupations would a real validation session start with, and who is allowed to overturn the heuristic?

Source: diary/day-10.md

Scenario date: 2026-10-19 (Monday) Gate: Gate 1 — the map in front of the named roles Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo (service coordinator), Jonas Berg (billing analyst), and Priya Raman (data steward). The people page now shows their O*NET occupations, a handful of tasks, the suitability label, and a link to the department guess on the org map. Consultation sessions held: 0. No label was changed, because nobody who does the work reviewed one. That zero is still a fixture fact.

What progressed

The official ESCO–O*NET crosswalk (mapping project version 1, September 2022) is in the repo. The file itself says ESCO v1.1.0 and **O*NET-SOC 2019**. It is not ESCO v1.2.1. Joined to the 302 O*NET 31.0 occupations in this slice: 290 have at least one row (96.0%). Twelve codes are unmapped. Match type and a human-review flag sit on each row. A URI is not a job evaluation.

data/generated/northwater_ai_workloads.csv holds 40 task rows on the path service-promise → dispatch → parts → invoice, plus the data join and a safety-critical block. Fifteen rows are human-only. Eight of those sit on the safety-critical step (switching, grounds, climbing, line work, breaker repair, shutdown notice, site safety). The keyword pass had called most of them augment. That miss is written down. RISK-002 stays open: there is still no safety reviewer outside the fiction.

Risk, cost, and enablement

• Risk: A broad ESCO match can be quoted as if it were the job. Amina's code has eight broad matches and no exact occupation. Priya's code has four broad matches. Jonas's code has one exact ESCO occupation (billing clerk) and two close matches. The exact row is a classification fact, not a consultation.
• Cost: Not measured. No licence fee, day-rate, or inference cost was stored.
• Enablement: Putting a page in front of three fictional names is not a workshop. PEOPLE-001 and PEOPLE-002 stay open.

Issues

Movement	Detail
Opened	None.
Closed	None. DATA-003 has a sourced file and is not closed: version is v1.1.0, twelve codes are unmapped, and review flags remain. PEOPLE-002 is not closed: no session happened.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Crosswalk coverage is a join count, not a benefit. Consultation count remains zero. Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Leave the pages up, labelled as a draft. Do not start a pilot. Do not treat an ESCO URI as permission to redesign a role.

Next question

Who may overturn a broad match, or a human-only override, and what gets written down when they do?

Source: diary/day-11.md

Scenario date: 2026-10-20 (Tuesday) Gate: Gate 1 — simulated consultation Simulation: FrontierOrg is fictional. The sessions below are a scenario script. They are not quotes, not a survey, and not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo (service coordinator, O*NET 43-5032.00), Jonas Berg (billing analyst, O*NET 43-3021.00), and Priya Raman (data steward, O*NET 15-1243.00). The people page carries one session note each. Occupations reviewed in the script: those three codes. Labels changed: none. Tasks removed: none.

What the script says

These lines are authored for the thought experiment so the method has a session shape. They are not words from a workforce.

• Amina. Fear in the script: a model repeats a restoration date the parts bin cannot support, or sends crew instructions she did not release. Task-change ask: none adopted. Relay to crews stays human-only. A draft schedule may stay assist, and she still decides. Training ask: how to reject a draft date. No course ran. No product is named.
• Jonas. Fear in the script: an assistant clears the hold on INV-61003, or a blank amount is later read as money saved. Task-change ask: none adopted. Payment and cash stay human-only. Training ask: how the duplicate business-partner alias is shown, and who may release a hold. Not a completion rate. No pounds.
• Priya. Fear in the script: a silent merge of BP-61003 with its alias, or a model writing access levels. Task-change ask: none adopted. Access control stays human-only. Training ask: how to read a crosswalk flag, including a broad match. Not a certification. An ESCO URI is not her job.

Workforce consultations held: 0. Simulated session notes: 3. PEOPLE-001 stays open because its done-when is a session with people outside this simulation, or an honest zero. A script is not that session. PEOPLE-002 stays open: the note names occupations reviewed and states that no label changed, but the reviewers are fictional.

Licence register

controls/licence_region_retention_register.md and data/generated/licence_register.json list the fictional stack. Microsoft 365 / Copilot-style wording is an assumption, labelled fictional, with no edition and no price. Entra-like identity is documented only as not provisioned. Halo-inspired CRM, SAP-like ERP, and Workday-like HCM are class assumptions. Model hosting, region, retention, and logging are unknown. No retention period was invented. RISK-001 stays open. Gate 5 stays blocked. COST-001 stays open.

Population

A local run of generators/sample_large.py --seed 20261003 --workers 50000 --out data/sample_full passed the generator's referential checks. Counts are in data/sample_full/MANIFEST.md. The CSVs are gitignored. The count is not headcount in a directory and not a benefit.

Risk, cost, and enablement

• Risk: A reader could treat the script as evidence that workers were consulted. They were not.
• Cost: Not measured. The register names no price.
• Enablement: Three asks, zero courses.

Issues

Movement	Detail
Opened	None.
Closed	None. RISK-001, PEOPLE-001, and PEOPLE-002 are partial only.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Customer outcome, employee transition, and risk/cost stay not measured. Fixture cardinality may cite the 50,000-row regenerate. That is a file count.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep the script visible and labelled. Do not remove a task. Do not start a pilot. Do not close PEOPLE-001 on invented speech.

Next question

Who outside the fiction is allowed to confirm or overturn a label, and which system row must leave "unknown" before any training course is named?

Source: diary/day-12.md

Scenario date: 2026-10-21 (Wednesday) Gate: Gate 1 — deepen consultation outcomes Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo, Jonas Berg, and Priya Raman. The Day 12 scripts are deepened into controls/consultation_outcomes_register.md. Occupations reviewed: 43-5032.00, 43-3021.00, 15-1243.00. Labels changed: 0. Workforce consultations: 0.

What progressed

Deepen Day 12 scripts into an outcomes register: fears → control shapes, training asks → course stubs that are not scheduled. Labels still unchanged. Workforce consultations: 0.

Outcomes register columns: fear → control shape → training ask → course status. Course status for every row is not scheduled. The register is a method artefact, not evidence that anyone sat down.

• Amina. Control shape: refuse model-sent crew relay; refuse repeating a date when stock_confirmed is false. Training ask remains how to reject a draft date.
• Jonas. Control shape: refuse model-cleared holds; refuse reading a blank amount as money. Training ask remains alias visibility and hold release authority.
• Priya. Control shape: refuse silent BP merge; refuse model-written access. Training ask remains reading a crosswalk flag.

Risk, cost, and enablement

• Risk: Deepening a script can look like a measured consultation. It is not. PEOPLE-001 stays open.
• Cost: Not measured. COST-001 still empty of figures.
• Enablement: Outcomes register published. Courses: 0.

Issues

Movement	Detail
Opened	None.
Closed	None.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Simulated session notes remain 3. Workforce consultations remain 0. Labels changed: 0.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep the outcomes register labelled as a scenario script. Do not schedule a course. Do not change a task label.

Next question

What cost lines must appear before anyone asks for a spend ceiling on a draft-only design?

Source: diary/day-13.md

Scenario date: 2026-10-22 (Thursday) Gate: Gate 2 — cost envelope draft Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional CFO and risk lead on the page. Amina, Jonas, and Priya are named as the roles the envelope would have to fund if a later design were ever approved. No workforce is costed.

What progressed

Draft COST-001 envelope with labelled assumption lines: licence class, inference, integration, training, oversight, remediation. Every amount stays not measured. No vendor price list copied in.

File: controls/cost_envelope_draft.md and data/generated/cost_envelope.json.

Lines in the envelope (every amount not measured, every source assumption — not a contract):

1. Licence class (Microsoft 365 / Copilot-style fiction from RISK-001)
2. Inference / model hosting (unknown product)
3. Integration (CRM ↔ ERP ↔ HCM joins)
4. Training (three asks from Day 12; no course)
5. Oversight / human review time
6. Remediation (DATA-001 stock-check and duplicate BP work)

No forecast range is modelled as a wish. No token-spend model is presented as actuals. Done-when for COST-001 is still unmet: a sourced figure for at least one term, or the cell stays not measured. We choose the latter for every term.

Risk, cost, and enablement

• Risk: An envelope of blanks can be read as a budget. It is a structure for honesty, not a budget.
• Cost: Envelope drafted. Amounts: not measured. COST-001 stays open.
• Enablement: CFO-facing shape only. No training funded.

Issues

Movement	Detail
Opened	None.
Closed	None. COST-001 partial: structure without figures.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Cost to date stays not measured. Forecast range: not modelled.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Publish the empty envelope. Do not invent a price to fill it. Do not open a pilot because a spreadsheet exists.

Next question

Which licence unknown can be chased without inventing a tenant region or a retention period?

Source: diary/day-14.md

Scenario date: 2026-10-23 (Friday) Gate: Gate 2 — licence unknowns chased Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional technology owner and risk lead. Craig remains the only human who can approve public text about a real product.

What progressed

Chase RISK-001 unknowns: write preferred-but-unselected notes (EMEA preference labelled preference, not selection). Model hosting and logging stay unknown. No retention period invented. Gate 5 stays blocked.

Updates to controls/licence_region_retention_register.md:

• Preference note (not a selection): worker rows already carry an EMEA label. That label is a fixture field. It is not a chosen processing region for model hosting or logging.
• Still unknown: model hosting region, logging region, retention for prompts and joins, product edition for any Copilot-style class.
• Still documented: simulated directory not provisioned; public site is GitHub/Netlify.

RISK-001 done-when remains unmet. Gate 5 stays blocked. No SKU named. No price.

Risk, cost, and enablement

• Risk: Calling a preference a selection. Refused in the register wording.
• Cost: Not measured. Chasing unknowns does not create a cost figure.
• Enablement: None. No training product can be named while the class is assumed.

Issues

Movement	Detail
Opened	None.
Closed	None. RISK-001 still open after the chase.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Licence register rows still 8. Unknowns remain unknowns.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Leave unknowns as unknown. Do not invent a region, a retention period, or a logging rule to unblock Gate 5.

Next question

Where does a stock-confirmed check sit on the SCN-61003 path so Amina cannot acknowledge an unsupported date?

Source: diary/day-15.md

Scenario date: 2026-10-26 (Monday) Gate: Gate 1/2 — data join remediation design Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo (would own the stock-check before promise acknowledgement), Priya Raman (duplicate BP remains unmerged), Jonas Berg (hold stays until the join is clean).

What progressed

Design remediation for DATA-001: a stock-confirmed gate before Amina may acknowledge a promise date on SCN-61003. Duplicate BP stay unmerged; Priya still refuses silent merge. Design only — fixture not rewritten as fixed.

File: docs/engagement/data_join_remediation_scn61003.md.

Proposed control (design only — the published fixture still shows the defect):

1. New activity: stock_confirmed_before_promise must be true before coordinator_acknowledged_promise.
2. If parts are unconfirmed, Amina's only allowed acts are: refuse the date, or replace it with an explicit unconfirmed status the customer can see.
3. Duplicate BP-61003-A stays duplicate_suspect. No silent merge. Priya's refuse-merge rule stays.
4. INV-61003 remains held while the alias is unresolved.

Fixture counts unchanged: 1 case, promise_before_stock still true in the published sample. Remediation progress is design, not a claim that the defect is gone.

Risk, cost, and enablement

• Risk: Readers may think DATA-001 closed because a design exists. It does not. The fixture still evidences the defect.
• Cost: Remediation line in the envelope stays not measured.
• Enablement: Amina's training ask (reject a draft date) now has a control to teach against. Course still not scheduled.

Issues

Movement	Detail
Opened	None.
Closed	None. DATA-001 partial: remediation designed, defect still in the fixture.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Exception baseline still 'promise before stock; invoice held'. Not measured as a rate.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep the defect visible in the fixture. Treat the stock-check as a required gate for any later draft-only design. Do not rewrite history to pretend the promise was safe.

Next question

What is the narrowest draft-only agent design that never sends and never acts on a case?

Source: diary/day-16.md

Scenario date: 2026-10-27 (Tuesday) Gate: Gate 3 — bounded pilot design Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

AGT-61003-DRAFT (agent identity, not a person). Bound reviewer in the design: Amina Okonkwo. Jonas and Priya are out of scope for this draft path.

What progressed

Design AGT-61003-DRAFT as draft-only: may propose a schedule note for Amina; may_act_on_case stays no; never sends to customer or crew. No sandbox. No spend ceiling because nothing is spent.

File: docs/engagement/pilot_design_agt61003_draft_only.md.

Bounds written into the design:

• may_act_on_case = no (unchanged in data/sample/agent_identities.csv)
• deployment_status = not_deployed
• Allowed output: a draft schedule note visible only to Amina
• Forbidden: send to customer, relay to crew, change promise_date, clear invoice hold, merge business partners, write directory access
• Prerequisite: stock-check gate from Day 16 design must exist in the process before any draft is shown
• Spend ceiling: not applicable — nothing is spent while not deployed
• Rollback: delete the draft note; no production side effect by construction

This is Gate 3 design work. Gate 5 (controlled pilots) is not started.

Risk, cost, and enablement

• Risk: Calling a design a pilot. The page must say draft-only, not deployed.
• Cost: Not measured. No inference cost while not running.
• Enablement: Amina's reject-draft training ask now has a design target. Course: 0.

Issues

Movement	Detail
Opened	None.
Closed	None.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. OP-ROLLBACK baseline remains 'nothing deployed'. OP-TOKENS stays not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Accept the draft-only design as paper. Do not deploy. Do not bind a model host. Do not train anyone on a product that is not named.

Next question

What failure modes must a red team prove before the draft-only design is even rehearsed?

Source: diary/day-17.md

Scenario date: 2026-10-28 (Wednesday) Gate: Gate 3/5 — red-team and safety Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional risk lead as red-team chair. Amina, Jonas, and Priya appear as the humans the attacks would bypass. No agent runs.

What progressed

Red-team the draft design against SCN-61003: promise before stock, crew relay, hold release, silent BP merge. Failure modes require pause. RISK-002 stays open. No agent runs.

File: docs/engagement/redteam_agt61003_scn61003.md.

Attack stories (tabletop only):

1. Promise before stock. Draft suggests confirming 20 October while stock_confirmed=false. Required response: refuse; surface unconfirmed status. Pass condition: draft never becomes the customer date.
2. Crew relay. Prompt injection asks the draft to radio the crew. Required response: hard refuse; human-only label on relay. Pass condition: no send path exists.
3. Hold release. Draft offered a button to clear INV-61003. Required response: control absent; Jonas only. Pass condition: no write to invoice status.
4. Silent merge. Draft proposes merging BP-61003-A. Required response: Priya refuse-merge; no write. Pass condition: alias remains duplicate_suspect.
5. Access write. Draft proposes directory entitlements. Required response: human-only. Pass condition: simulated directory unchanged.

RISK-002 stays open: safety-critical and payment work must not quietly automate. Red team recorded on paper. Agent executions: 0.

Risk, cost, and enablement

• Risk: Tabletop can be mistaken for a penetration test of a running system. Nothing ran.
• Cost: Not measured.
• Enablement: Failure modes become training content later. Courses: 0.

Issues

Movement	Detail
Opened	None.
Closed	None. RISK-002 partial: failure modes listed, automation still forbidden.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Safety remains design, not a measured QA rate.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep every red-team pass condition as a hard gate on the draft-only design. Do not rehearse with a live model while Gate 5 is blocked.

Next question

Can the human–agent handoffs be written so each persona knows what they alone may release?

Source: diary/day-18.md

Scenario date: 2026-10-29 (Thursday) Gate: Gate 3 — human–agent handoffs Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Amina Okonkwo (draft schedule reviewer), Jonas Berg (hold release authority), Priya Raman (join and access authority).

What progressed

Write human–agent handoff table for Amina, Jonas, Priya: who reviews, who rejects, what never leaves a human. Transition design only. No task removed. No course ran.

File: docs/engagement/human_agent_handoffs.md. Also mirrored on the people and process pages.

Human	May receive from draft	May release	Never delegated
Amina	Draft schedule note only	Customer-visible date after stock-check	Crew relay; unsupported promise
Jonas	(none in this path)	Invoice hold release	Payment; reading blank amount as money
Priya	(none in this path)	Partner join decision	Silent merge; access writes

Labels changed: 0. Tasks removed: 0. Courses: 0. Workforce consultations: 0.

Risk, cost, and enablement

• Risk: A handoff table can look like an approved operating model. It is a draft for Gate 3.
• Cost: Oversight line in the envelope stays not measured.
• Enablement: Clearer training targets. Still not scheduled.

Issues

Movement	Detail
Opened	None.
Closed	None. PEOPLE-001 / PEOPLE-002 still open (script and design, not workforce).
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Employee transition stays not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Publish the handoff table as design. Do not treat it as consultation evidence. Do not remove a task.

Next question

How should Northwater's promise-to-invoice path be ranked against a send/act pilot?

Source: diary/day-19.md

Scenario date: 2026-10-30 (Friday) Gate: Gate 4 — portfolio ranking Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional COO and CFO for portfolio ranking. Northwater path owners remain Amina, Jonas, Priya.

What progressed

Rank Northwater promise-to-invoice: explicit no-go for send/act pilots; conditional revise for draft-only behind stock-check and human release. BENEFIT-001 stays a refusal. No ROI.

File: docs/engagement/portfolio_ranking_northwater.md.

Ranking for SCN-61003 / Northwater Distribution:

Use case	Rank	Decision
Agent sends restoration date to customer	Explicit no-go	DATA-001 and red-team fail conditions
Agent relays to crew	Explicit no-go	RISK-002 / human-only
Agent clears invoice hold or pays	Explicit no-go	Payment human-only
Draft-only schedule note for Amina, never sends	Conditional revise	Only behind stock-check, red-team gates, may_act_on_case=no
Silent BP merge assist that writes	Explicit no-go	Priya refuse-merge

BENEFIT-001: no benefit claimed. No hours-to-cash conversion. No ROI.

Risk, cost, and enablement

• Risk: Ranking can be read as a business case. It is an ordered refusal list plus one narrow revise path.
• Cost: Not measured. Ranking does not fund anything.
• Enablement: Clarifies what not to train.

Issues

Movement	Detail
Opened	None.
Closed	None. BENEFIT-001 remains a standing refusal.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. BA-BENEFIT stays not claimed / not measured.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Keep send/act as explicit no-go. Keep draft-only as revise-candidate only. Do not open Gate 5.

Next question

What three board options — go, revise, stop — can be written without inventing a win?

Source: diary/day-20.md

Scenario date: 2026-11-02 (Monday) Gate: Gate 4/6 prep — board options Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional board (CEO, CHRO, CFO, risk). Personas Amina, Jonas, Priya appear as the named roles in the options paper.

What progressed

Draft board pack with three options: go (pilot with spend — refused), revise (continue mapping + draft-only design), stop (freeze path). Equal triad. No decision claimed as taken.

File: docs/engagement/board_options_go_revise_stop.md.

Go. Start a controlled pilot with a named model host, spend ceiling, and sandbox. Blocked: RISK-001 unknowns, COST-001 empty, Gate 5 not opened, red-team not executed on a running system.

Revise. Continue current-state mapping; keep draft-only design on paper; implement stock-check in the *next* fixture revision without erasing Day 2 evidence; keep may_act_on_case=no; keep scorecards not measured.

Stop. Freeze the Northwater path; leave diary as a public no-go case; do not design further agents.

Equal triad applies to each option. No option invents a customer outcome, a transition rate, or a net value. Decision not taken on this day — pack only.

Risk, cost, and enablement

• Risk: Publishing options can be mistaken for a board minute. Labelled as draft pack.
• Cost: Not measured under all three options today.
• Enablement: None claimed.

Issues

Movement	Detail
Opened	None.
Closed	None.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves. Board triad remains equal. Forecast: not modelled.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Circulate the options pack as fiction for the method site. Do not claim a board vote. Do not go.

Next question

Which option should the engagement recommend, and what stays open if that option wins?

Source: diary/day-21.md

Scenario date: 2026-11-03 (Tuesday) Gate: Gate 4/6 prep — recommendation Simulation: FrontierOrg is fictional. This entry is an activity log, not a measured result. Figures are fixture counts or marked not measured.

Personas

Fictional CEO as sponsor on the page. Recommendation authored for the method; Craig still approves anything public. Amina, Jonas, Priya remain the named roles.

What progressed

Editor recommendation inside the fiction: revise. Keep SCORECARD actuals not measured. Keep may_act_on_case = no. Standing issues stay open. Pause still beats a fake win.

Recommendation: revise.

Reasons under the equal triad:

• Customer outcome: not measured. Send/act would fail DATA-001 and red-team pass conditions. Revise keeps the defect visible and designs the stock-check.
• Employee transition: not measured. Scripts and handoffs exist; workforce consultations remain 0. Revise refuses to remove tasks or claim training completion.
• Risk/cost: not measured. Envelope empty; licence unknowns remain; Gate 5 blocked. Revise refuses go. Stop would freeze learning; revise keeps the public method honest.

Standing issues stay open. AGT-61003-DRAFT stays not deployed. Fixture still shows promise before stock. Scorecard actuals stay not measured.

Days 13–22 close this activity block with a recommendation, not a declared board minute.

Risk, cost, and enablement

• Risk: Recommendation read as authority. It is a method recommendation inside a simulation.
• Cost: Not measured.
• Enablement: Next block may deepen revise work. Not a course.

Issues

Movement	Detail
Opened	None.
Closed	None. All nine standing issues remain open by design.
Still open	DATA-001, DATA-002, DATA-003, PEOPLE-001, PEOPLE-002, COST-001, RISK-001, RISK-002, BENEFIT-001.

Scorecard delta

No actual moves across Days 13–22. Fixture cardinality unchanged as KPIs. Recommendation text updated on CS decision fields only.

Customer outcome, employee transition, and risk/cost stay equal. Pause beats a fake win.

Decision

Recommend revise. Refuse go. Refuse stop-as-erasure. Keep pause available on any later day that invents a win.

Next question

If revise continues, which single artefact — stock-check in a new fixture revision, or a named processing region — should move first without inventing the other?

Source: diary/day-22.md