Sprint 55 · Voice-capture instrument · ~15 min via WhatsApp

Lisa Voice-Capture Brief

Seven short questions Lisa can answer by WhatsApp voice-note or text in about fifteen minutes. The answers thread Lisa's actual voice through the seven donor-room artefacts already on the site. This brief exists because generic charity voice sits in room D right now — that is exactly what Lisa's voice replaces.

Who this is for. Lisa (Co-founder & Head of Philanthropy) is the answerer. Corrina is the courier — she reads this brief into the WhatsApp group, waits for Lisa's answers, then feeds them to the AI CMO who folds them into the seven donor pages via the domain-line assignment table. Laurence and Carla see the brief in-thread so they know what's coming.

Why this is the Sprint 55 shape. Room D already has seven artefacts on disk (~120 kB of donor copy: /donor-one-pager, /donor-stewardship-plan, /foundations-grant-briefing, /foundations-outreach-pack, /founding-donor-deck, /give, /give-sprint48-brief). Structure is there. Voice is thin. Sprint 55 is not "build room D from scratch" — it is "thread Lisa's actual voice through the existing seven pages." That is a surgical operation: 5–7 paragraphs change, not 120 kB of copy.

Companion pages. /donor-voice-map shows exactly which paragraph in which page each of the seven answers lands in — the AI CMO uses that map as the substitution index. /edit-sheet is the read-and-correct alternative to answering cold: AI-drafted answers on the left, Lisa's inline corrections on the right, one row per question, print-friendly for A4 markup. The draft is a scaffold Lisa reacts to, not a substitute for her voice — nothing ships to donor pages until Lisa signs the Philanthropic line.

Compliance envelope. Y1 audited numbers verbatim; dignity floor intact; no beneficiaries are named or identified in Lisa's answers or in the resulting donor copy; ABN, ACN, ACL 387398, mediation disclosure carried on every downstream page.

Contents

  1. 1. How to answer — the mechanics
  2. 2. The voice we are trying to capture
  3. 3. The seven questions
  4. 4. Anti-patterns — what to avoid saying
  5. 5. What happens after Lisa answers
  6. 6. Session-launch paste (for the AI CMO)
  7. 7. Change control

1. How to answer — the mechanics

The easiest path is WhatsApp voice-notes. Seven questions, one voice-note per question, each 60–120 seconds. Total ~15 minutes if answered in one sitting. Voice-notes preserve Lisa's cadence and hesitations, which is the point. Corrina transcribes; the AI CMO extracts the substantive sentences and folds them into the donor pages per the voice-map. Lisa reviews the resulting paragraphs before anything ships (the Philanthropic sign-off line).

Text answers are fine too. One WhatsApp text message per question. Bullet points are fine. Fragments are fine. Complete sentences aren't required — the AI CMO does the sentence assembly.

"I don't know yet" is a valid answer. Some questions may genuinely not have a Lisa answer today (e.g. Q7 depends on a real conversation with a specific foundation trustee that hasn't happened). Mark those "not yet" and we'll route around them until the answer exists.

2. The voice we are trying to capture

Not a scripted charity voice. Lisa's actual register, which across the constitutional docs and the co-founder conversations reads as: warm but non-appeal, evidence-led, qualified rather than certain, quiet rather than urgent, and speaks about a specific person even when the person is anonymous (never "Australians facing hardship" — always something closer to "a woman I sat with in June"). The seven questions are engineered to elicit that register. If an answer starts drifting into standard charity phrasing, the question was probably wrong — flag it and we'll rewrite.

The dignity floor still applies inside voice-capture. Even in Lisa's answers, no beneficiaries are named or identified. If a specific person is being described — and often they will be — the identifying details are stripped by Corrina before the text reaches the AI CMO. "A woman I sat with in June" is fine. A first name, a suburb, a diagnosis, or a debt figure paired with a household size is not.

3. The seven questions

Read the question, then answer. The context line explains why we're asking; skim it or skip it. The example register shows the kind of voice we're trying to capture (not a script — a tuning fork). The answers into line names which donor page(s) will absorb the answer.

1

Why does LWD exist for you personally?

60–120s

The founder story sentence. Every donor page opens with some variant of "why this organisation." Right now that opener speaks in charity-generic. We need Lisa's version — the specific reason she is doing this rather than something else.

Not the elevator pitch. The actual reason. What did you see that made you unable to walk past it? What kind of household or moment kept coming up? If it helps, answer as if telling a friend who does not know LWD exists.
Example register (tuning fork, not a script)"There is a moment in the middle of a serious illness where the debt letter arriving in the mail becomes the thing that breaks the household — not the illness. I kept seeing that moment. Nobody was standing in it."
Answers into/donor-one-pager opener · /founding-donor-deck slide 2 · /give lede paragraph · /foundations-outreach-pack section 1
2

What is the moment you'd want a foundation trustee to picture?

60–120s

Foundation trustees read hundreds of grant briefings a year. Ours needs one anchoring image — something specific, dignified, non-appeal. The image belongs to Lisa (not a beneficiary), which means it can be public without a consent problem.

Not a story about a beneficiary. A moment Lisa witnessed. What did the room look like? What was on the table? Who was speaking? Keep the specific person anonymous by construction — describe the room, the mail on the table, the tone of the conversation. The reader will infer the person without needing to be told.
Example register"A kitchen table in Adelaide. Three unopened debt letters between two coffee cups. The person opposite me was telling me about her son's next chemotherapy appointment and asking, gently, whether she should hide the letters from him."
Answers into/foundations-grant-briefing anchor paragraph · /foundations-outreach-pack "why this" section · /founding-donor-deck slide 3
3

What does the mediation function actually do, in your words?

60–90s

"LWD holds Australian Credit Licence 387398 for the mediation function" is the compliant sentence. It's also the sentence that shuts a donor's brain off. We need Lisa's translation — what mediation looks like from the perspective of the household on the other side of it.

You know the sentence a donor needs. Say it your way. What does mediation feel like from the household's side? What changes for them between the day they walk in and the day the settlement lands? (Note: the ACL 387398 disclosure sentence still appears on the page — your version sits next to it, not instead of it.)
Example register"Mediation means we sit between a household in serious illness and their creditors, and we do the negotiation the household cannot do for themselves. What lands is a settlement they can meet — usually a fraction of the original balance, spread over a period that fits the household's actual income. The debt does not vanish; the impossible version of the debt does."
Answers intoEvery donor page's "what LWD does" paragraph · sits adjacent to the ACL 387398 mediation-disclosure sentence · primary insert on /give
4

Why 31 households and $1.82M — and not something bigger?

45–90s

The Y1 audited numbers are the truth we lead with. But a foundation trustee's next thought is "why so few?" and the answer is not "because we couldn't help more" — it is a deliberate choice about proving the model before scaling. That reasoning needs to be in Lisa's voice, not the charter's.

Why did the pilot deliberately stay at 31? What were you and Laurence protecting for? What did the small number let you learn that a bigger number would have hidden? Do not defend the number — explain the discipline of it.
Example register"Thirty-one was the number we could reach with hand-on-the-file rigour. If we had taken on eighty we would have lost the K10 measurement, we would have lost the 87 cents per dollar direct-service ratio, and we would not know whether the model works. Year one was for proving the model; year two is for scaling it, and we can only scale honestly if year one was small."
Answers into/foundations-grant-briefing "our Y1 approach" · /donor-one-pager paragraph 2 · /founding-donor-deck slide 4
5

What is the wrong reason to give to LWD?

45–90s

Every charity page tells donors why to give. Almost none tell donors why not to give. That's what makes LWD's dignity floor visible — we're the org that says "if you want a story of a specific rescued family, we're not that org." That negative frame does more donor-trust work than a positive one.

If a prospective donor is looking for a rescue-narrative charity, or an urgency-appeal charity, or a "just one dollar could save a life" charity, LWD is the wrong choice. Say it in your voice. What are we not? What kind of donor is not our donor? (This paragraph is the dignity floor made visible to the reader.)
Example register"LWD is not a rescue charity and not a story charity. We do not publish photos of the people we work with. We do not run 'meet the family you saved' campaigns. If that is the giving experience you are looking for, we are the wrong home for it — and there are excellent Australian charities that do that work honourably. Our donors are the ones who want dignified evidence, quiet outcomes, and the receipts that come with an audited pilot."
Answers into/donor-stewardship-plan "who this is for" · /give "before you give" callout · /founding-donor-deck slide 5
6

What does year two look like if it works?

60–120s

Every donor page ends with a forward-look. Right now it reads as growth-rhetoric. It should read as Lisa describing what she expects to be true in twelve months if the DGR grant lands and the model scales the way the pilot suggests it will — qualified, not certain.

Twelve months from now, if year two works: what is the number of households (roughly), what is the geographic reach, what is the referrer network (hospital social work, palliative, financial counselling), and what would still be true about the K10, the case cycle, and the direct-service ratio? Use "we expect" and "we intend to" rather than "we will." No commitments; a described trajectory.
Example register"We expect year two to take LWD from thirty-one households to roughly one hundred and twenty — and we expect the K10 reduction, the case cycle, and the 87 cents per dollar direct-service ratio to hold, because those numbers describe the model rather than the pilot's small size. Geographic reach shifts from Adelaide-anchored to a second-city trial (Newcastle or Geelong, decision Q3). The referrer network is where the growth needs to be honest: we grow only as fast as the hospital social workers can trust us."
Answers into/foundations-grant-briefing "what year two looks like" · /founding-donor-deck slide 6 · /donor-stewardship-plan forward-look paragraph
7

The direct answer to "why should I trust you with this?"

45–90s

Every foundation trustee, every founding donor, every corporate-CSR lead will at some point ask a version of this question. It's not a hostile question; it's a professional one. Lisa's answer to it is the single most important sentence in room D — and right now the site doesn't contain that sentence in her voice. This question closes that gap.

Answer as if the trustee is sitting across from you and has just asked the question directly. Not the "here are our credentials" answer. The "here is what we've done and what the numbers cost us and what we've refused to do" answer. It's fine for this one to be the longest. It is the answer that anchors everything else.
Example register"Because we've done thirty-one and we have the receipts. Because eighty-seven cents of every dollar reaches direct service and Carla's audit shows exactly where the other thirteen goes. Because we hold Australian Credit Licence 387398 and we've operated inside it for the entire pilot. Because we've said no to media requests that would have grown the org faster because they would have needed us to put a beneficiary's face on the front page. Because Laurence is the CEO of record and I am accountable for how philanthropic money is spent. And because we would rather grow honestly than grow quickly."
Answers into/founding-donor-deck closing slide · /foundations-outreach-pack section 5 · /donor-one-pager footer paragraph · /foundations-grant-briefing "why us" section

4. Anti-patterns — what to avoid saying

Not because Lisa would say these — but because if the questions elicit these, the questions were designed wrong and we need to rewrite them, not use them.

5. What happens after Lisa answers

The Sprint 54 shared-gate machinery already exists; Sprint 55 rides on it.

  1. Corrina couriers Lisa's seven answers from Lisa's WhatsApp voice-notes or texts into the shared HA5 WhatsApp group. Voice-notes are transcribed; identifiers (names, suburbs, diagnoses, specific debt figures paired with household size) are stripped in the transcription pass.
  2. The AI CMO extracts the substantive sentences from each answer and uses /donor-voice-map as the substitution index — each answer maps to specific paragraphs in specific donor pages.
  3. The AI CMO produces a review pack per donor page (6-item bundle, per the Sprint 54 pattern): the current paragraph, the proposed paragraph, the source Lisa answer, the domain lines triggered, the quorum level, and the reversibility note. Each page's pack is a separate review pack — not one giant one.
  4. The domain lines triggered are typically Philanthropic (Lisa signs her own voice back in — this matters, it's not a rubber-stamp; she reads the AI CMO's assembly of her voice and confirms) and Marketing-Craft (Corrina signs the cadence and channel fit). For paragraphs that touch Y1 numbers or forward-looking financial claims, Financial & Regulatory (Carla) also triggers. Constitutional if any paragraph accidentally touches the dignity floor.
  5. Quorum is domain-touching for most paragraphs (Lisa + one second-eye human), multi-domain where Y1 numbers or Y2 projections appear (Lisa + Carla + one second-eye), constitutional if the AI CMO's assembly accidentally produces identifying content (all 4 humans).
  6. Once quorum is complete, Corrina posts the finalised paragraph substitutions in the WhatsApp group and the seven donor pages are updated in a single Sprint 55 commit. Rebuild · verify hard-constraint sha256 · deploy · smoke-test.

6. Session-launch paste (for the AI CMO)

When Lisa's answers land in the WhatsApp group and Corrina is ready to feed them to the AI CMO, this is the paste that opens the session. It sits alongside the four standard Blocks from the AI CMO charter.

SPRINT 55 · VOICE-INSERTION PASTE (paste after the 4 standard AI CMO blocks) Sprint 55 task: fold Lisa's seven voice-capture answers into the seven donor-room artefacts, using /donor-voice-map as the substitution index. Inputs you have received: - Lisa's answer to Q1 (why LWD exists) - [paste transcribed text here] - Lisa's answer to Q2 (the moment for a trustee to picture) - [paste] - Lisa's answer to Q3 (what mediation actually does) - [paste] - Lisa's answer to Q4 (why 31 households, not more) - [paste] - Lisa's answer to Q5 (the wrong reason to give) - [paste] - Lisa's answer to Q6 (what year two looks like) - [paste] - Lisa's answer to Q7 (why trust you with this) - [paste] For each answer: 1. Extract the substantive sentences (drop hedging, restarts, "um" fragments). 2. Preserve Lisa's cadence: qualified, quiet, evidence-led, non-appeal. 3. Strip any surviving identifiers (names, suburbs, diagnoses, specific debt+household pairings). 4. Check the dignity floor: no beneficiaries are named or identified. 5. Check Y1 numbers used are exactly: 31 households, $1.82M consumer credit debt resolved, 23-day average case cycle, 52% average K10 reduction, $1,840 average cost per case, 87c per dollar reaching direct service. 6. Attach the outcome caveat wherever Y1 numbers appear. Consult /donor-voice-map for the substitution index: which answer's sentences land in which paragraph of which donor page. Answers may serve more than one page - the map lists all of them. Output for each donor page: a review pack with: - The current paragraph (before) - The proposed paragraph (after) - The source Lisa answer (Q1-Q7) - The domain lines triggered (typically Philanthropic + Marketing-Craft; add Financial & Regulatory if Y1 numbers or Y2 projections appear; escalate to constitutional if the AI CMO's assembly accidentally produces identifying content) - The quorum level (domain-touching / multi-domain / constitutional) - Reversibility note (how the substitution unwinds if a human wants it reverted) Verdict for each pack: CLEAN / FIX-INLINE / RETURN-TO-SPECIALIST / CLEAN+FLAG. You do not vote. Humans sign the domain lines in the WhatsApp group. Compliance markers must survive every substitution: ABN, ACN, ACL 387398, mediation disclosure sentence, "complaints" and "privacy" links intact. Verify per page after substitution.

7. Change control

The seven questions above are Sprint 55's contract. If any question needs to be rewritten (because it isn't eliciting Lisa's voice, or because Lisa says "that question is wrong"), the rewrite is a Sprint 55 amendment and lands in the shared WhatsApp group as a review pack: Philanthropic line (Lisa signs the question she's being asked) + Marketing-Craft line (Corrina signs the question quality) + one second-eye. Anti-patterns (section 4) are governance items — adding or removing an anti-pattern triggers Constitutional quorum (all 4 humans sign). Rewriting the session-launch paste (section 6) is Marketing-Craft alone (Corrina signs; second-eye Laurence or Carla depending on which frameworks it touches).