LLL · communication board

Verification and Constraints

● ACTIVE

Lovasember · Persona-led copy, faithful brand styling, eight Gemini-built page variants and complete campaign/funnel review.

Live owner: Sol xhigh executor Run: lovasember-rebuild-2026-09-27 Updated: 2026-09-27

Execution evidence · September 27

Independent strategy/copy critique is accepted by executor proxy authority. All eight drafts were frozen before generation. Source parity accepted before generation. Revised source-grounded copy has passed the depth review. The actual AI-generated creative selection and all96 copy variants are accepted. Shared forms have local matrix and transition-regression evidence. Hosted visual acceptance remains pending. Gemini: 2 / 8 complete first drafts, 0 / 8 current page builds with accepted QA.

10 / 23 criteria verified. Execution spend USD 0.7920, preparation reserve USD 1, shared cap USD 20. Production and campaigns unchanged. No client messages.

Inspect the current website review Inspect the accepted original-source brandbook

Current batch: repaired Self A/B published at fb6be68c. All86published files and96campaign comparisons pass. Three fresh Luna xhigh reviewers cover the full pair. Local repair accepted; hosted QA and separate blind comparison pending. Six sequential Gemini page cycles remain.

Goal and finish line

End goal: Create a persuasive, visually consistent website and campaign review for both Lovasember audiences.

Done means: Eight complete page variants, 32 image creatives, 96 tailored copy variants, targeting and multiple application/booking demos on a stable commentable URL. Sources, proof, email draft and next steps support the client review.

10 / 23criteria verified

8deliverables

0open decisions

Rules that stay fixed

Original website and working campaigns stay unchanged.
Gemini 3.1 Pro API creates the first drafts after the copy checkpoint.
Matt authorized execution; no client or lead messages; USD 20 shared cap.

Proof standard: Evidence before checkmarks. GUI proof includes actual screenshots, an independent Luna high description, and an explicit comparison. Full Luna section QA applies to brandbook, pilot and client-facing deployments.

Deliverable flow

Sources → complete review → feedback

Use the source evidence and approved copy to build one coherent review package.

Input 1 · confirmed or open

Existing homepage + 24 comments

Why: Preserve proven style, correct concrete failures.

Input 2 · constraint or source

Persona workbook + supplied template

Why: Choose relevant messages and useful layouts.

Deliverable 1 · main review item

Approved copy + checked brandbook

Why: Gemini receives meaning and proven style.

Deliverable 2 · evidence or artifact

Eight pages + campaigns + forms

Why: Review the full visitor journey.

Output · decision or next action

Matt review → Sanyi/Dóri feedback

Why: Choose variants and identify revisions.

Next: Prepare the client email, never send automatically.

End goal system

Green = settled direction · pink = assumption · dashed = evidence still needed

Route to the end state

The independent copy checkpoint and every-page learning loop are real dependencies.

Parent ↔ child messages

Newest message first

PARENT · accepted decisions2026-09-27

All ten grilling answers incorporated. One landing variant is generated first, visually checked and repaired. After EVERY page, full Luna visual QA and fixes update the next Gemini bundle, including page seven to eight. The campaign appendix follows the Analit reference.

PARENT · required checkpoint

The executor completes an independent persona/ad/copy critique and records a reasoned proxy decision under Matt’s delegated authority before Gemini page generation. All eight critiqued copy files must be complete before the first call. The four exact homepage sections in the brandbook must first pass visual comparison.

Parent read setSmall files first

Public-safe planning references. Executor read set remains deliverables.md, main-prompts.md, current-session.md and exact-session gist after completion/stall.

Read the complete goal Read all 24 staging comments Read the accepted decisions

Accepted choices and future optionsRequired choices · future integrations separate

Hook choice

Rank women recurring-pattern/self-neglect and leader control/work-spillover angles using evidence. They are candidates, not proven winners.

Paid continuation A/B

Compare transparent verified detail with an experience-and-next-step explanation. These are section variants within the eight-page scope.

Qualification choices

Show light and stronger forms. Include time commitment and budget/readiness in the stronger option. Contact details follow on step two.

Work and proof

One card per deliverable

Ground decisions in sources

Recover what works, understand the client and resolve every review comment.

ACTIVE1 / 2

Criteria, constraints and evidence

D1.1 When the existing campaign reports, persona workbook, latest recovered client meeting, current homepage and supplied staging are inspected, then source-ledger.md identifies dated facts, hypotheses, rejected drafts, missing facts and the strongest supported hooks for both audiences.

Required proof: Source ledger with exact paths/URLs, dates and claim-to-source references.

Verified evidence: copy/source-ledger.md, dated source snapshots, complete recovered meeting, historical campaign evidence boundaries.

D1.2 When the 24 saved homepage comments and fresh comments at launch are reconciled, then comments-disposition.md maps every comment ID to a specific copy/design/form requirement and its eventual page/section or reasoned non-applicability.

Required proof: Saved raw readback plus one row per record, including positive comment 17. Do not resolve the original comments.

Constraints to preserve

Keep original production website, working campaign and 5,000 Ft self-knowledge path unchanged.
Do not treat persona hypotheses, old testimonials or rejected staging claims as validated leadership outcomes.

Executor evidence: 1 / 2 criteria verified. Remaining criteria retain their stated evidence requirements.

Write persuasive journeys before design

Define the promise, objections and next steps before Gemini sees the copy.

VERIFIED3 / 3

Criteria, constraints and evidence

D2.1 When both persona profiles and four message angles per audience are reviewed, then strategy.md explains everyday pain, attention hooks, objections, trust, willingness to invest, relevant targeting and ad-to-landing message match, with evidence strength and audience self-selection explicit.

Required proof: Persona-angle-targeting matrix. Women A/B and leader A/C are preferred hypotheses to rank, not mandatory winners.

Verified evidence: copy/strategy.md, both personas, four angles each, targeting and message matching, independent critique.

D2.2 When each of the eight page-copy files is read without design, then at least 12 substantive sections per variant explain relevance, trust, the method, what application and consultation involve, and what can follow, with a stated purpose and conversion role for every section.

Required proof: Eight Hungarian Markdown copy files, sentence/section critique and two independently reasoned variants of home, About, self and leader. Count is a floor, not a quality score.

Verified evidence: copy/v2-acceptance.md, v2/acceptance.json, all eight expanded and individually critiqued files, independent Luna Max source review, explicit parent correction preserving both form modes per landing.

D2.3 When both persona/ad packs and all four plain-text landing variants receive a documented independent strategy/copy critique under Matt’s delegated decision authority, then checkpoint.md records the executor’s reasoned acceptance and applied revisions, and all eight completed, sentence-critiqued plain-text copy files exist before the first Gemini page-generation API call.

Required proof: Checkpoint receipt with reviewer findings, executor decisions and eight versioned copy files. Home/About copy derives from settled plain-text landing journeys. Matt’s September 27 launch instruction delegates human-gated decisions: complete the substantive quality review autonomously, never fabricate Matt approval or wait solely for a human click. All eight copy files must precede the first page call.

Verified evidence: copy/checkpoint.md and checkpoint.json, independent Luna max review, executor proxy acceptance before any Gemini generation, eight frozen versioned drafts.

Constraints to preserve

Sanyi and Dóri are equal partners, without inventing qualifications, attendance promises or results.
Problem-aware, coaching-sceptical visitors get human situations first, then experiential horse-assisted differentiation. Do not imply scientifically proven superiority, mystical claims or guaranteed outcomes.
Paid-continuation section A gives verified format, activities, time/location and available prices. Section B explains the experience and next step while leaving later prices for the consultation. Keep facts identical and do not invent a fixed leader package.

Executor evidence: 3 / 3 criteria verified. Remaining criteria retain their stated evidence requirements.

Extract and prove the brandbook

Give Gemini a faithful style specimen instead of a vague visual description.

ACTIVE2 / 3

Criteria, constraints and evidence

D3.1 When brandbook.html is opened from its saved monolithic file, then four identified sections copied from the current original homepage, plus its exact navbar/header/footer reference, render with the original CSS embedded in the HTML and source assets resolving.

Required proof: Source snapshot, section selectors/IDs, extracted fragment comparison, CSS hashes and asset/font manifest. Separate original-source specimen from explanatory guidance.

Accepted full matched desktop/mobile source-parity evidence, blind descriptions and executor comparison. Representative decoded footer pair: Original source Hosted specimen

Verified evidence: brandbook/acceptance.json and brandbook-comparison.md, literal source fragments/CSS, matched full desktop/mobile source-parity QA, blind descriptions and explicit executor discrepancy resolution.

D3.2 When the original homepage and extracted specimen are inspected at matched desktop/mobile sizes and corresponding section states, then all four sections and shell elements match typography, colors, spacing, widths, images and component styling in brandbook-comparison.md before any Gemini generation.

Required proof: Paired local PNG section screenshots, blind Luna high descriptions and parent comparisons, plus tailored full Luna visual QA reports. Document dynamic/source differences explicitly.

Accepted full matched desktop/mobile source-parity evidence, blind descriptions and executor comparison. Representative decoded footer pair: Original source Hosted specimen

D3.3 When a Gemini input bundle is assembled, then it contains the checked brandbook HTML, brandbook-guide.md, the exact supplied website_template_v1.html, approved relevant copy, verified facts and page-specific instructions.

Required proof: Bundle inventory and SHA256 comparison to /Users/agency/Desktop/website_template_v1.html. Guide says original style wins over template styling. Each home generation uses a fresh Gemini context containing both settled persona/ad/targeting packs and refined landing outputs, alongside its prewritten copy. Any new copy refinements are completed before that page call. Supply the exact HTML/CSS of brandbook and template as labeled text parts, not a URL-only reference or unsupported raw-byte attachment. Count the full bundle and record source-byte hashes.

Constraints to preserve

The four source sections must be extracted faithfully, not reconstructed or redesigned. Embed CSS and preserve working image/font references or bundled assets.
Template /Users/agency/Desktop/website_template_v1.html supplies layout options only. Do not replace it with the older reusable-template-kit/template-v2.html.
Do not reproduce unrelated live tracking or form submission side effects in the reference demo. Record any removed runtime behavior without silently altering appearance.

Executor evidence: 2 / 3 criteria verified. Remaining criteria retain their stated evidence requirements.

Generate eight consistent Gemini drafts

Learn from every completed page before generating the next, including page seven before page eight.

ACTIVE2 / 3

Criteria, constraints and evidence

D4.1 When the first approved landing-page variant is requested through the Gemini 3.1 Pro API using the complete bundle, then its saved HTML and generation-receipt.json identify the actual model, input versions, request time, response and token/cost usage.

Required proof: Native API receipt and saved raw response, with credentials removed. Choose the pilot from the accepted two landing journeys and explain why. Preflight records documented endpoint gemini-3.1-pro-preview, preview status, selected project access/quota, bundle token count, configured output ceiling and aggregate/per-call budget. Record returned model version and finish reason; truncated HTML is a failed draft, not a completed variant.

Verified evidence: generation/self-a/generation-receipt.json and immutable first-draft.html. Actual gemini-3.1-pro-preview,200, STOP,126798 input5939 output6339 thinking, USD0.400932. Exact bundle inventory and request/raw response hashes. Copy36/36 and12/12 sections retained.

D4.2 When the first page is visually inspected and repaired, then pilot-review.md records complete section/state coverage and design comparison, and versioned brandbook guidance plus next-page prompt contain the useful corrections before the second generation call.

Required proof: Tailored Luna xhigh QA, Luna max fixes as needed, fresh QA, before/after screenshots, ordered timestamps and prompt/brandbook hashes. Preserve faithful source specimens during guide revisions.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

Verified evidence: Self A full fresh r2 XHIGH QA:476 inspected PNGs, separate503-frame blind review with resolved comparisons, pilot-review.md, immutable guidev2 hash90b1f263c5c7a49429aad9bf32fca5dfb11258775048897199181e161adb1713 and self-b prompt/bundle saved before call2. generation/self-a/qa-acceptance.json.

D4.3 When the remaining variants are generated sequentially, then eight distinct first-draft API outputs and eight refined pages exist as home A/B, About A/B, self A/B and leader A/B, each using the latest accepted style guidance and its own approved copy.

Required proof: Eight model receipts and input bundles, generation order, change log, full page inventory. After EACH Gemini page, apply luna-visual-qa-section-screehoshots fully: section screenshots, independent QA, fixes and fresh QA plus design-consistency review. Improve versioned brandbook guidance and the next Gemini prompt before the next call, explicitly including page seven to eight. Preserve the exact source specimens. Harmonise earlier pages when shared rules improve.

Constraints to preserve

Use Gemini 3.1 Pro API for the first drafts, not browser Gemini or another model silently. Verify the current exact model identifier and access.
Generate one page variant first. Do not batch all eight before the pilot QA and guidance update. Finish landing journeys before deriving final home/About design.
Gemini must not drop approved meaning, invent client facts, overwrite the source brandbook or mix template typography/colors into the established brand.

Executor evidence: 2 / 3 criteria verified. Remaining criteria retain their stated evidence requirements.

Show campaign combinations below landings

Make every ad, message and audience reviewable below the landing footer, using the Analit appendix as the structural template.

ACTIVE1 / 2

Criteria, constraints and evidence

D5.1 When the two campaign asset manifests are counted and opened, then each campaign has 16 actual new image creatives grouped as four message angles by four visual executions, with three tailored copy variants per creative, totaling 32 assets and 96 copies.

Required proof: Asset files, concept/copy matrix, source-photo provenance, current top-performer evidence and generation receipts. SVG text cards or prompts alone are not finished image creatives.

Verified evidence: campaign/ai/selected-manifest.json, native originals/prompts/receipts, 32 selected assets and96 unchanged copies, full390px parent inspection, independent blind image descriptions and parent comparison, revision2 polish and rejected/superseded history.

D5.2 When either variant of each landing is opened and scrolled past its footer, then its campaign appendix displays all 16 matching creatives, their three selectable copy variants and audience/targeting rationale as readable mobile Facebook-feed-style previews.

Required proof: Actual hosted screenshots of every creative/copy state in inventory, no distorted/cropped assets, working switching and campaign mapping. Appendix is visibly separate from customer copy. Matrix: two audiences × two landing variants × 16 creatives × three copies = 192 placements/states backed by 32 unique assets and 96 unique copies. If one verified shared appendix renders both variants, document code/data equivalence and test each variant’s correct audience mapping; inventory every state and retain screenshot proof of each unique rendered state plus each mounted placement.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

Constraints to preserve

Use existing best-performer patterns and client-supplied photos where appropriate. Do not fabricate client portraits, testimonials, endorsement or performance claims.
Use the Analit page as structural reference, not its travel claims/audiences. Keep proposed campaigns as review-only drafts and make no live targeting, budget, tracking, activation or spend changes. Existing campaigns remain in their current state.

Executor evidence: 1 / 2 criteria verified. Remaining criteria retain their stated evidence requirements.

Demonstrate alternative lead-capture journeys

Let Sanyi compare the full application-to-booking experience.

ACTIVE0 / 4

Criteria, constraints and evidence

D6.1 When reviewers exercise the light and stronger qualification variants, then short interactive cards/sliders/questions lead to contact details on a second step, validation, a demo submission confirmation and a thank-you booking choice, with back-navigation preserving entries.

Required proof: Local and hosted interaction screenshots covering both audiences and each variant. Stronger version includes time commitment and budget/readiness without inventing package prices. Before building, enumerate both light and strong modes for each audience in a closed route/state manifest; both landing variants expose their audience’s two modes without multiplying pages. Cover contact validation, back-navigation, confirmation and booking for every applicable branch, and mark route choices inapplicable only with an explicit reason.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

D6.2 When the booking options are compared, then a booking-button version, an embedded-calendar frontend demo and future 5,000/10,000 Ft leader paid-path design states can be reviewed, with the optional 30,000 Ft calendar-backend integration explained separately.

Required proof: Screenshots of free/current/future-paid journeys and review labels. Payment screens are prototypes with no real charge or live availability claim. Present the exact 30,000 Ft as Matt’s proposed optional calendar-backend upgrade, not a purchased service or a new binding commitment. This is separate from undefined paid coaching continuation.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

D6.3 When a reviewer chooses the self, leader or unsure route, then consultation terms remain explicit before submission: self introduction 5,000 Ft, leader introduction initially free, and unsure visitors choose a clearly priced route rather than an invented third price.

Required proof: Route matrix and rendered screenshots. Demo submits do not send emails, save to production Sheets or book live calendar slots. Close the self/leader/unsure branch matrix against the form manifest, record expected totals and actual receipts, and verify no storage, email, payment or live-booking request is issued.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

D6.4 When reviewers compare paid-continuation disclosure for each landing family, then both A and B section alternatives render and can be selected or compared within the existing eight-page review scope.

Required proof: A/B state inventory and hosted screenshots for both audiences. A shows verified detail and available prices; B explains the experience and leaves later prices to consultation. No extra full-page variant matrix. GUI screenshot/independent description/comparison required.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

Constraints to preserve

Keep application before optional booking. Live storage, Sanyi notification, Sheets, calendar integration and payment backend are later implementation steps.
Remove the rejected demo terms-acceptance checkbox, retain clear prototype status, and record that actual production consent/legal text requires a later check rather than silently removing production obligations.
No actual leads or sensitive answers are collected during public review. Any stronger readiness wording remains tactful and relevant to the verified offer.

Executor evidence: 0 / 4 criteria verified. Remaining criteria retain their stated evidence requirements.

Verify and publish the complete review

Prove visual coherence and the whole funnel on the actual hosted build.

PENDING0 / 3

Criteria, constraints and evidence

D7.1 When all eight pages are reviewed at desktop/mobile viewports and meaningful interaction states, then section-coverage.md contains every header, section, footer, tall-section segment, campaign preview and form state with inspected PNGs and no unresolved visual errors.

Required proof: At least two fresh Luna xhigh QA workers with disjoint page/viewport partitions, actual model receipts, Luna max fixes where needed, fresh complete re-QA. Blind high screenshot descriptions and criterion comparisons attached separately.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

D7.2 When the full website is opened in a fresh unauthenticated client at its stable review URL, then all eight variants, navigation, form demos, campaign appendices and comment controls work and comment/rewrite persistence passes using a disposable/intercepted document.

Required proof: Anonymous HTTP readbacks, desktop/mobile actual postdeployment screenshots and interaction receipts. Preserve existing review host pages and document identity.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

D7.3 When original-brand references and all eight final pages are compared together, then consistency-review.md verifies a shared content width, nav alignment, type scale/body style, darker green palette, image treatment, icon weight and section rhythm, with all 24 comments dispositioned.

Required proof: Side-by-side screenshots and comment-ID evidence links. Do not call section count, DOM checks, a successful build or one desktop screenshot sufficient quality proof.

Screenshot pending · actual URL/build + viewport + state
Independent Luna high description pending · expected result withheld
Executor comparison and mismatch resolution pending

Constraints to preserve

Publish through comment-html-review-host at a bare URL with no login/token/VPN/IP gate. Keep secrets and sensitive source data off public pages.
Preserve the original successful site/campaign, rejected staging and its existing comments. Use a distinct new review surface and retain all prior QA rounds.

Executor evidence: 0 / 3 criteria verified. Remaining criteria retain their stated evidence requirements.

Prepare the client handoff and continuation

Finish with clear review instructions and a usable next-work state.

ACTIVE1 / 3

Criteria, constraints and evidence

D8.1 When the review handoff is opened, then README.md and the review index list verified URLs, deliverables, status, remaining client choices and the exact workflow after Sanyi/Dóri comment, with editable sources and generation inputs available.

Required proof: URL manifest, deliverable list, main-prompts file, current-session file, final report, updated project state/changelog, reusable next-step checklist.

D8.2 When client-email-draft.md is read, then it concisely links the full review, explains the ad/copy/targeting and funnel choices, requests consolidated feedback and asks Sanyi whether to issue a small partial invoice now or arrange payment differently. It proposes weekly reporting/check-in without inventing dates or binding commitments.

Required proof: Draft only, no send receipt. Clearly state demo forms, optional calendar fee, and separate later approval of campaign launch/spend. No invoice issued. Retain Matt’s exact proposed optional 30,000 Ft calendar-backend upgrade without presenting it as purchased or already connected.

D8.3 When the continuation plan is read after review, then it separates feedback revisions, approved production publication, storage/notifications/Sheets, calendar/payment options, tracking verification, Cloudflare migration and campaign activation into ordered next steps with dependencies and unresolved facts.

Required proof: next-steps.md, no claim these later integrations or migration are implemented. Include reporting/check-in proposal without inventing dates or client commitments.

Verified evidence: next-steps.md, nine ordered stages with dependencies and open facts, inspected by executor.

Constraints to preserve

No emails to Dani or client, no invoice, no binding price changes, no campaign activation and no production migration in this run.
Do not mark the run complete until all required evidence is attached or an exact blocker and resume point are recorded. Keep rejected drafts clearly labelled.

Executor evidence: 1 / 3 criteria verified. Remaining criteria retain their stated evidence requirements.

Open decisions and blockers

Only unresolved items

No further strategic question is needed to prepare the run. Evidence still needed during execution:

Public model: gemini-3.1-pro-preview (Preview). Actual project access, quota and aggregate/per-call cost still need preflight.
Verified details of paid follow-on work and usable client photos.
Four extracted source sections that pass visual parity before use.
Shared external spend stays within USD 20 unless Matt approves more.

Nothing here authorizes a substitute model, invented offer or skipped proof.

Recovery state

Only inspect on stall or completion

0consecutive stalls

ACTIVErecovery state

Complete hosted QA and guidance for self-bresume point

Current evidence: 10 / 23 criteria verified, 2 / 8 actual Gemini drafts and 0 / 8 current page builds with accepted QA. Complete hosted QA and guidance for self-b. Revised source-grounded copy has passed the depth review. The actual AI-generated creative selection and all96 copy variants are accepted.

Executor continues autonomously under the latest parent steering. Parent checks follow the authorized 60-minute idle interval.