Project 06 · Life Brain — pre-dawn Tokyo, scattered warm windows, the moment before a month begins
Project 06 · Context Grammar

Life Brain

A brain at the smallest possible scale — one person.

Meet Lena and Haruki — two strangers in the same Tokyo cafe, both declaring intent inside the same Life Brain
Cast · Two People, One Grammar

Meet Lena
& Haruki.

Two strangers in the same Tokyo cafe, on the same Day 1 of the same month — both declaring intent inside the same Life Brain. They will end up using it in two completely different rhythms.

Lena · 30
UX researcher, Tokyo
AI-collaborative · 60% AI
Haruki · 33
Architect, Tokyo
Driver style · 15% AI
Executive summary · 90 seconds

A brain at the smallest scale — one person — that holds across thirty days, two opposite users, and a non-personal domain.

Five rows. Decision-grade. Built for the recruiter, the strategist, and the engineer.

Row
What it says
Problem
Today's personal AI is four apps in different rooms. Apple Health, Google Calendar, your bank, your grocery list — each remembers a slice. None speaks for the person they belong to. There is no grammar to say "let AI drive here, not there."
Thesis
A Life Brain — one person's three-layer Context Brain, plus four Domain Agents — runs on a grammar that the user pre-declares. Autonomy is per-domain. Some moments are Protected Rituals the AI is forbidden to enter. Trust grows from explicit boundaries, not from undo buttons.
What's new
Protected Rituals (new AX Pattern · pre-declared zones AI cannot enter) · Drive-Me gesture (3-finger handoff that returns autonomy after the moment) · Forgotten Intent Retrieval (4-signal gate that surfaces saved intents only when the world finally matches).
Proof
Lena's 30 days: 17 rituals fired exactly as declared, zero misfires. The same grammar produced two opposite rhythms — Lena (UX researcher, 30 · AI 60%) and Haruki (architect, 33 · AI 15%) — both hitting every goal. Indicative cohort, simulated.
It generalizes
Same four-agent structure runs for chronic-disease self-management — meds, glucose, mood, mobility. The Protected Ritual Lena uses for "Friday frappuccino" becomes the patient's "Sunday dinner is mine — track but do not intervene." (Chapter 05.)

Three reading paths from here: 5 min skim (this row + chapter dividers + Close) · 15 min designer (everything except the dark Chapter 02) · 25 min full (top to bottom, including Backstage Architecture).

The problem · 2026

Personal AI in 2026 is four apps in four rooms — and no grammar to say which room AI is allowed in.

An honest accounting before the framework arrives. The gap is not "AI doesn't remember." The gap is what comes next.

What ships today

Apple Health holds biometrics. Google Calendar holds the day. Samsung Health holds sleep and steps. Apple Pay holds the wallet. Each is competent. Each is a silo.

Memory is no longer the moat. Claude remembers. Gemini remembers. ChatGPT remembers. Apple Intelligence remembers. The plumbing is done. The grammar is not.

Where it falls short
  • No cross-domain composition. Health knows the steps. Calendar knows the meeting. Neither composes "leave one stop early — you'll still make 9:30."
  • No per-domain autonomy. AI is on or off. Users want "let it pick lunch · ask me about dinner."
  • No declared protection. The user cannot say "Friday afternoon is mine." All boundaries are reactive.
  • Vendor-locked memory. What you save in Instagram doesn't surface in Maps when the place finally appears.

Context Grammar's contribution isn't memory. It's the language a single person can use to tell a system where AI is allowed and where it isn't — and the architecture that makes that language portable across agents, surfaces, and vendors.

The framework · 60 seconds

Three primitives. The rest of the case study reads on top of them.

If you already know Context Grammar, skip this. If you don't, this is enough.

Primitive 01
8 Context Tokens

The live signals that describe right now. Six situation tokens — Physical State, Cognitive Load, Social Exposure, Priority Weight, Form Factor, Feasibility. Two relationship dials — Autonomy Dial, Disclosure Dial.

Restaurant metaphor: the waiter's glance. "They're rushing today. They brought a child. They look stressed." No history needed — just open eyes.

Primitive 02
Context Brain · 3 Layers

Identity Layer — names, allergies, languages (months → years). Learning Layer — patterns from observation (days → weeks). Now Layer — live token state (seconds → minutes).

Restaurant metaphor: the reservation book + the waiter's memory + the waiter's glance. Three scales of remembering on top of each other.

Primitive 03
Two Dials · per domain

Autonomy Dial — Suggest → Confirm → Notify → Auto. How far AI may act. Disclosure Dial — how much AI may know. Per domain. Per person.

"Don't know × do it for me" is logically impossible. Disclosure is a prerequisite of Autonomy.

The rest of the case study uses these three names. Tokens are the signals. Brain is the memory. Dials are the boundaries the user sets. Lena's whole month is built from these three.

Chapter 02 · Backstage Architecture — a quiet desk at the hour the framework was figured out
Chapter 02 · Opt-in
Backstage Architecture.
Six panels for engineers. Skip if you're here for the story — the next chapter starts in Lena's morning.
Backstage · Tokens as Contract

A token is human-readable AND machine-readable. Same string, two audiences.

Samsung's "tokenized design patterns" requirement, made concrete. Without this, the framework reads as concept. With it, it ships.

For the reader · prose

The Day-4 Moment Composer fuses four signals into one ten-second proposal. To do that, it must hand the Watch a state — not a layout.

The state is a token. The token is a JSON contract. Any surface that knows the contract can render it.

"1 token in. 6 surfaces out." — the projection contract.

For the machine · schema
// life-brain · v2.0 · 2026-04
{
  "token": "composer.proposal",
  "emitted_at": "2026-04-04T08:30:14Z",
  "summary": "1駅早く降りて歩く?",
  "contributing": [
    {"agent":"weather", "weight":0.18},
    {"agent":"location", "weight":0.32},
    {"agent":"calendar", "weight":0.22},
    {"agent":"health", "weight":0.28}
  ],
  "window_seconds": 10,
  "render_hint": "glance",
  "actions": ["accept", "defer"]
}

Backstage · Tokens as Contract Same string. Read by Lena's narrative ("leave one stop early"). Read by the Watch SDK ("glance, 10s, two actions"). Read by Apple Health, Google Calendar, the bank — every surface that subscribes to composer.proposal.

Backstage · Brain API · Read / Write

Permissions are not a settings page. They are enforced at the subscribe call.

Every Domain Agent declares what it reads and what it can write. The Brain enforces it. The user never has to police a long list.

Subscribe call
// Health Agent · Day 1
brain.subscribe({
  agent: "health",
  read: [
    "now.physical_state",
    "now.cognitive_load",
    "learning.weekly_steps",
    "identity.weight_target"
  ],
  write: [
    "learning.steps",
    "now.energy_estimate"
  ],
  disclosure: "household",
  autonomy: "confirm"
});
Permission matrix · Day 1
AgentReadWrite
health4 paths2 paths
finance3 pathsDENIED
location2 paths1 path
shopping5 paths3 paths

Backstage · Brain API Disclosure isn't an opinion in copy — it's a parameter on the subscribe call. The Finance Agent can read three paths and write nothing. That decision lives in code, not in a settings screen Lena will never visit.

Backstage · Federation · vendor-neutral

The Brain is a layer above vendors — like Matter for smart-home, OAuth for sign-in, Passkeys for credentials.

Lena's day touches Apple Watch, Samsung Health, Google Calendar, her bank, her grocer. The Life Brain doesn't replace any of them. It speaks the contract above them.

Honest aspirational note: federation across consumer-AI vendors does not exist today. Matter took five years from announcement to ship. This proposal would be similar — referenced precedents below.

One day · five vendors
  • 07:50 ▸ Apple Watch reads heart_rate  (Apple)
  • 08:12 ▸ Samsung Health emits steps token  (Samsung)
  • 08:30 ▸ Google Calendar resolves 9:30 mtg  (Google)
  • 12:18 ▸ bank API confirms ¥980 lunch  (MUFG)
  • 22:00 ▸ Brain emits retrieval.surface  (Life Brain)
Federation contract
// vendor-neutral · 2026 proposal
brain.connect({
  contract: "life-brain/v2.0",
  vendors: [
    "apple/healthkit",
    "samsung/health",
    "google/calendar",
    "mufg/finance-v3"
  ],
  disclosure_boundary: "per_vendor",
  precedent: "Matter, OAuth, Passkeys"
});
Apple adopts because

Privacy is the disclosure boundary, enforced at the contract level. Apple's existing posture, formalized.

Samsung adopts because

"Tokenized design patterns" — the JD line. Watch + Health + Family Hub speak the same contract.

Google adopts because

Health Connect + Calendar + Maps already cross-pollinate. The contract names what's already implicit.

Microsoft adopts because

Copilot + Health Vault history + Outlook. Enterprise-grade audit trail of every cross-vendor decision.

Backstage · Federation No single vendor owns Lena. The Brain is the layer where they cooperate — like email between providers, calendars across companies, payments across banks. Boring infrastructure thinking, applied to personal AI.

Backstage · Multi-modal Projection

Same Token state. Four projection contracts. The Brain hands surfaces a state — not a layout.

The Day-4 proposal renders four ways depending on which surface is closest to Lena's hand.

Visual · Watch glance

320×320 dot face. 16px Japanese, two action chips, one swipe affordance. 10-second window.

render("glance", {
  text: summary,
  actions: ["yes","later"]
});
Voice · earbud

No screen — earbud whispers in Lena's left ear during her commute. Bone conduction, half-volume.

render("voice", {
  utterance: summary,
  reply: "yes/later"
});
Haptic · Watch tap

Single amber pulse. No words. Lena already knows what it is — a proposal exists, glance when ready.

render("haptic", {
  pattern: "single-amber"
});
Ambient · mirror

Bathroom mirror surfaces it the next morning during teeth-brushing — a single line, no buttons. She'll act later or never.

render("ambient", {
  surface: "mirror",
  ttl: 90
});

Backstage · Multi-modal One Token. Four renderers. The Brain doesn't decide layout — it picks modality based on Form Factor + Cognitive Load + Social Exposure (three of the eight Tokens). The same proposal whispers, taps, glances, or waits.

Backstage · Decision Trace

Every AI decision is debuggable. Down to the Token. Down to the rule. Down to the candidate not chosen.

The Brain isn't a black box. The Day-4 proposal arrived because four signals passed and two alternatives lost.

2026-04-04 · 08:30:14.213 decision_id: cmp.42a91f execution: 84 ms
▸ emitted  "1駅早く降りて歩く?"  → Watch glance · 10s window
▸ trace
  TOKEN ✓  Form Factor → watch · Lena's wrist · 320×320 face
  TOKEN ✓  Cognitive Load → low (commuting · headphones in · no calendar density)
  RULE ✓  health.steps_gap > 1000 within 24h → propose movement opportunity
  RULE ✗ (skipped)  finance.budget_warn → no proposal cost
▸ alternatives weighed
  "leave one stop early"  confidence 0.78 ✓ chosen
  "text reminder · evening walk"  confidence 0.51 · cognitive load too low to justify async
  "hold proposal · already 1500 steps below"  confidence 0.34 · contradicts Lena's goal token
trace_id: brain.l.4c.cmp.42a91f · vendor: federated · disclosure: household

Backstage · Telemetry "Why did the Watch propose this?" — answerable in one trace. Every decision the Brain emits has this fingerprint. Engineers can audit it. Lena can request it. Regulators can subpoena it.

Backstage · AX Pattern Composition

A Protected Ritual is not a primitive. It is three smaller patterns standing on each other's shoulders.

The pattern library is a vocabulary. Patterns compose. Bigger AX moves are built — never invented.

Pattern · D2
Disclosure Lock

User explicitly closes one Disclosure path. AI cannot see what happens during the locked moment — only that it happened.

Pattern · A2
Approval Gate Skip

Autonomy Dial is forced to Suggest only for the duration. AI may observe but cannot act, even if normally trusted.

Pattern · T4
Time-Box · place × time × cadence

Pre-declared trigger window — Friday 15:00–17:00 within 100m of Starbucks, max 4×/month. Inside the box, the other two patterns activate.

↓ compose ↓
Composed AX Pattern
Protected Ritual

D2 + A2 + T4. Triggered by place × time × cadence; locks Disclosure; forces Autonomy to Suggest-only. The user is not interrupted, not nudged, not optimized.

Backstage · AX Composition Same three primitives, recombined, become the Driver Mode in the next chapter — except the Time-Box is bigger, the Disclosure Lock is partner-specific, and the Approval Gate Skip is total. Patterns are vocabulary, not screenshots.

Day 01 · Setup

On the first morning, Lena (UX researcher, 30) declared three intents — and locked two rituals AI must not touch.

Goals say what to reach. Rituals say where AI must stay silent. Both live at the same level — that's what makes Project 06 different.

Intent Declaration is where Context Grammar starts. Lena names the direction of the month and hands it to the Life Brain. Four Domain Agents spin up — Health, Finance, Location, Shopping — each with an initial Dial setting. The agents observe the world; Lena keeps the wheel.

Goal says what to achieve. Ritual says where AI is forbidden to step in. Project 06 lets both be declared at the same level — a first.

User UI · Intent Declaration screen What Lena actually taps on Day 1 — three goals, two protected rituals, four agents to spin up. One commitment for the next thirty days.

Architecture

Life Brain a personal-scale Brain plus four Domain Agents.

Lena's intent flows down into the centre; four specialist agents observe the world and report back. The two-way flow is what makes the Brain learn.

CONCEPT · Life Brain Architecture
HEALTH AGENT
Observes sleep, steps, heart-rate, nutrition. Reports the gap to Lena's goal.
FINANCE AGENT
Tracks budget burn. Predicts month-end landing and over-spend risk.
Life Brain
Personal Scale · 3 Layers
Identity Lena's values
Learning 30 days of observed behaviour
Now This very moment
↕ Intent in · Observation out
LOCATION AGENT
Watches position, movement patterns, distance to saved places.
SHOPPING AGENT
Picks daily goods and meals on Lena's behalf — nutrition × budget × taste.
P1 Family Brain (multi-person) · P4 Project Brain (organisation) · P6 Life Brain (one person). Same three-layer structure. Different scale. Personal scale is the most universal — and the most felt.
Chapter 02 · A Day in the Month — Lena on a Tokyo platform at 8:30 AM
Chapter 03
A day in the month.
Four agents. One person. Twelve hours of small choices.
Day 04 · Moment Composer

8:30 AM, transfer station. Four agents fuse into a single ten-second proposal.

Weather, location, calendar, health. Not four separate alerts — one fused sentence on the wrist.

Moment Composer takes the four agents' observations and folds them into "the one option that matters in the next ten seconds." Not a stack of notifications — a single proposal the Brain has already weighed.

The unit isn't number of notifications. The unit is meaning. That's the Rule Engine's job.

Backstage · Moment Composer (Day 4, 08:30) Looking through the AI's eye at the moment it fuses four signals into one ten-second proposal. The watch face in the centre is what Lena ends up seeing — everything around it is the AI's own work.

Day 08 · Drive-Me

"I don't want to choose right now." Three fingers, and Lena hands the wheel to AI.

Per-Domain Autonomy isn't static. When she's tired, Lena temporarily grants AUTO — for one domain, for one window.

The point: the human picks the moment to hand over. AI never raises its own autonomy. On Day 8, Lena handed lunch to the Shopping Agent. After lunch, the Dial restored itself to the prior setting.

Trust hinges on this: the human picks the handoff moment. AI never grabs autonomy.
1
Three-finger tap on the watch
A single amber ring pulses — the gesture has been received.
2
"Drive me for lunch"
Lena names the domain and the time-window. Voice or tap, both work.
3
Shopping Agent decides
Mackerel set · Nutrition+ · ¥980 · 3-min walk. Lena eats — she didn't pick.
After lunch, the Dial returns to its prior setting automatically.
Day 12 · Protected Ritual ★ new AX Pattern

"Friday Frappuccino — I pick this one." The moment Lena declared it, she became protected.

Not an Override (reactive). A pre-declared zone where AI is forbidden to step in.

A Protected Ritual is declared as part of Intent Declaration: "this moment, this choice, is mine." When the place × time × frequency conditions match, every agent goes silent. Only Lena's hand is on the menu.

Context Grammar's principle: a design that doesn't take will away — a design that supports it. Rituals are the fortress of the second.

Concept · AX Pattern Card · Protected Rituals The pattern reference card — Problem, Solution, Anti-Pattern, Related, Evidence. A timeless designer artifact, not a screen Lena sees.

Day 13 · Driver Mode

Some nights, every agent stops.

Tonight belongs to two people.

Where Protected Ritual guards a single moment, Driver Mode halts the agents themselves across every domain. Triggered by a confirmed reservation, a manual toggle, or a calendar tag.

Not Do-Not-Disturb. DND silences notifications. Driver Mode silences the agents — no judgement runs at all.
Reservation Confirmed
Enter Driver Mode?
Healthsilent
Financesilent
Locationsilent
Shoppingsilent
19:00 start
~ 23:00 predicted end
Driver Mode active · all agent judgement halted
Chapter 03 · Memory and Review — a quiet Tokyo back-street at 22:00, warm café glow
Chapter 04
What the Brain remembered.
A saved place returns. A dial earns its evolution.
Day 18 · Forgotten Intent Retrieval

An intent saved three months ago and forgotten — surfaces when place and time align.

Saves on Instagram, Pinterest, Maps don't disappear. They wait until the conditions match.

When Location × Time × Health × Finance all pass, the sleeping intent rises. Lena doesn't have to open Instagram — what she saved on Instagram appears. Information crosses silos.

Memory itself is not Context Grammar's unique value. The unique value is the grammar of when to bring memory back.

Backstage · Retrieval Gate (Day 18, 22:00) Looking through the AI's eye as the four-signal gate evaluates: location, time, status, finance. All four pass — exactly one of forty-two sleeping intents surfaces to Lena's wrist.

Day 21 · Mid-Month Review

Three weeks of behaviour. The Dial earns its evolution. Trust is the result of observation.

No automatic promotion. The Brain proposes; Lena decides.

After 21 days, the Brain has watched enough to suggest changes — promote Health to Auto, sharpen Finance notifications, register a new ritual the Brain noticed. Every change requires Lena's consent. The grammar belongs to AI; the settings belong to the user.

User UI · Mid-Month Review (Day 21) What Lena opens on Day 21. Progress, two dial-change proposals, one new ritual proposal, the trust log. The AI proposes; Lena's hand is on every Approve button.

Chapter 05 · Same Grammar, Different World — a quiet morning kitchen with the routine of someone managing a chronic condition
Chapter 05 · The proof
Same grammar. Different world.
If the framework only fits Lena's leisure month, it's a demo. Watch what happens when the same Life Brain runs for someone managing chronic illness.
Generalization · Chronic-disease self-management

Akari (52, type-2 diabetes since 2024). Same Life Brain. Same four agents. Same Protected Rituals. Different world.

A diagnosis isn't a personality. The framework that helped Lena hand AI lunch helps Akari hand AI three pharmacy refills — without taking her hand off the wheel.

Same architecture · re-purposed agents
Health Agent
Glucose readings · medication times · symptom log · A1c trajectory
Finance Agent
Insurance co-pays · prescription costs · annual deductible runway
Location Agent
Pharmacy distance · endocrinologist's clinic · safe walking routes
Shopping Agent
Carb-aware grocery · safe restaurant menus · supplement reorders

A Tuesday morning, the same shape as Lena's.

Akari (52, lives alone, retired primary-care nurse) checks her glucose on the bathroom mirror — 6:12 AM, fasting, 142 mg/dL. The Health Agent logs it. The Watch's Moment Composer assembles a single proposal: "Take the Metformin in the bathroom now — coffee with the breakfast at 6:45, walk the long way to the pharmacy after." One ten-second glance. Three actions woven.

By 8 AM, Akari has done all three. The Brain saw it happen — every Token logged. The Brain did not act. Akari did.

A Sunday she will not let AI touch.

Sunday dinner with her daughter and grandchildren is a Protected Ritual. Place × time × cadence: home address, 18:30–21:30, every other week. Inside the box: D2 Disclosure Lock (no glucose-related notification surfaces), A2 Approval Gate Skip (Health Agent observes but cannot suggest), T4 Time-Box. The Brain still records the carb intake; it just doesn't argue with the third helping of takikomi gohan.

After dinner, the Brain's only message: "3 hr 14 min · logged." Not "you spiked." Not "you should have." Just the fact, and the door back to Monday.

Same comparison. Two patients, one grammar.

Akari · AI-collaborative · 64% AI. Lets the Brain order pharmacy refills, schedule the quarterly endocrinologist visit, draft her A1c update message. Tomohiro · 56 · Driver style · 12% AI. Same diagnosis, different rhythm — wants the data raw, the choices his. Both held steady through the quarter. Same grammar.

The framework's argument is not "this works for diabetes." The argument is "the same grammar that holds across two opposite users in leisure also holds across two opposite users in chronic illness." If it generalizes that far, it generalizes.
Lena's eye in soft morning light — a barely-visible amber pinpoint inside the iris suggests the smart contact lens has rendered a proposal
Future form factor · 2030

The ten-second glance becomes the zero-second whisper.

Same Token. Same contract. New render — inside the iris, an amber pinpoint Lena does not need to lift her wrist to see.

If the framework was designed correctly, a 2030 surface costs the framework nothing. The Token composer.proposal already names a render hint. The lens registers a new value — whisper — and subscribes. The Brain doesn't change. Only the projection function does.

Honest aspirational note: smart contact lenses with usable displays do not ship in 2026. Mojo Vision shut down in 2023; Samsung and Sony hold prototypes. The point isn't the device — it's that the framework's projection contract is forward-compatible. The question for any 2030 surface: "does it accept a Token contract?" If yes, the framework already speaks it.

Concept · Future form factor Surfaces will keep changing. The Brain shouldn't have to.

Metrics · indicative

Six numbers vs the 2026 single-app stack — measured against a 30-day simulated cohort of 24 users.

All figures are indicative. The cohort is composite. The framework hasn't shipped to a real population. Honest labeling above hype.

Outcome
Baseline · 2026 stack
With Life Brain
Δ
Daily decisions made by the user
≈ 38
≈ 14
−63%
Notifications received per day
≈ 27
≈ 6
−78%
Saved-intent activation rate · 30 days
3 of 42
11 of 42
+267%
Protected Ritual compliance (declared → fired)
N/A
100% (17/17)
0 misfires
User-reported "AI took something from me" incidents
2.3 / month
0 / month
−100%
Cross-domain proposals accepted (vs single-domain)
N/A
71% acceptance
vs 23% baseline

Method: 24-user composite cohort, 30-day simulated month, baselined against current Apple Health + Google Calendar + Samsung Health + bank-app stack. Cohort split: 12 AI-collaborative, 12 Driver-style. Numbers are indicative — they describe what the framework is designed to deliver, not what a real deployment has shipped.

Chapter 04 · The Close — a quiet desk at end-of-month, late afternoon light, notebook and watch resting
Chapter 06
The month closes.
Numbers were hit. Something else was learned.
Day 30 · Month Close

Month's end. Lena's thirty days.

She hit her targets. The bigger win: she controlled the distance to AI herself.

Beyond the weight number and the budget number, the larger fact is that Protected Rituals fired seventeen times — exactly as Lena had asked. She found a way to borrow AI's force without letting go of her own hand.

Living with AI ≠ handing it everything. It needs a design where you decide how much to hand over.
Same Month · Different Rhythm

Haruki's same month. Same grammar — different settings.

Same Context Grammar, same Life Brain, same Protected Rituals mechanism. Only the rhythm differs.

Concept · Persona Comparison A designer-level read of the same Grammar used in two completely different rhythms — Lena (AI-collaborative, 60% AI) and Haruki (Driver style, 15% AI). Both hit every target.

Both use the same Context Grammar — same Life Brain, same Protected Rituals, same Driver Mode. Inside one grammar, each person finds their own rhythm.
New AX Pattern ★

Protected Rituals the pattern card.

CONCEPT · AX Pattern Specification
Problem
"I want to live with AI" and "I want to drive this myself" coexist in the same person. A static Dial can't handle it — even within one domain, "let go" and "hold" trade places by moment.
Solution
As part of Intent Declaration, the user declares in advance: "this moment / this choice is mine." Conditions: place × time × frequency. When matched, every agent switches to silent. A space opens where only the user chooses.
Anti-Pattern
AI auto-decides "this seems important, I'll be quiet." This destroys trust. The user must always declare. "Sensing" is not respect — it's trespass.
Evidence · Lena's Month
✓ 17 firings (exactly as declared) · 5 non-firings (conditions did not match — zero misfires) · Continuous use across all four weeks · Haruki registered 15 rituals — same pattern, different rhythm
Process · what got kept, what got cut

Six decisions that shaped this case study — with the reasoning, not just the result.

Senior portfolios show thinking, not output. These are the load-bearing calls — the ones that, reversed, would have changed the project.

01
Kept: single-person scale, not family

The smallest meaningful unit. P1 already covers family. P6 had to cover the unit beneath — the one every reader recognizes immediately, even if they don't have a family.

Cut

An early version followed Lena + her partner Sho. Tested poorly — readers conflated "Sho" with "Haruki" (the comparison persona) and the architecture argument blurred.

02
Kept: 4 Domain Agents — not 7

A person can hold roughly four concurrent personas — the working self, the body self, the spending self, the moving self. More than four fragments the mental model.

Cut

An early sketch had separate Mood, Sleep, Calendar, and Social agents. They folded back into Health (mood + sleep), Location (calendar place), and Shopping (social context).

03
Kept: Protected Rituals as pre-declared

Trust is built before the moment, not patched after it. A reactive "AI senses you want quiet" pattern reads as helpful in demos and creepy in life. Pre-declaration moves the boundary into the user's hand.

Cut

A reactive variant: "Smart Quiet Mode" that inferred when to back off based on biometrics. Worked 80% of the time. The 20% it failed cost more than the 80% it worked.

04
Kept: Watch as the primary surface

The 10-second glance is the smallest meaningful proposal window. Anything bigger invites bloat — anything smaller (haptic only) leaves the user guessing.

Cut

A phone-first version. Tested with three users. Within a week the screens grew explanatory, the proposals lengthened, the ten-second discipline collapsed.

05
Kept: the comparison is two personas, not one

A single-persona case study reads as "designed for me." Lena alone would have argued for one rhythm. Lena + Haruki argue for the grammar — the bigger claim.

Cut

A v0 with Lena only. Reviewers (correctly) asked: "Does this work for someone who hates AI?" Adding Haruki was the answer that wrote itself.

06
Kept: Driver Mode separate from Per-Domain Autonomy

Per-Domain Autonomy is a gradient (Suggest → Confirm → Notify → Auto). Driver Mode is a stop. Mixing them broke walkthroughs every time — readers couldn't tell whether they were turning a dial or pulling a brake.

Cut

"Autonomy = 0" as the way to express Driver Mode. Logically equivalent. Conceptually a mess.

Voices from the cohort

Five quotes — composite voices from the simulated cohort, never self-defensive.

Methodology: 24-user composite cohort across the personal-leisure and chronic-disease scenarios. Quotes are not transcribed from real interviews; they are distilled from the user-needs research that informed the framework's shape.

"I want my morning back. Not silenced — composed."

— Lena (UX researcher, 30) · AI-collaborative

"I'd rather pick than be picked for. Always have."

— Haruki (architect, 33) · Driver style

"By 7 AM I've made twelve decisions for other people. I'd like three for myself."

— Composite · working parent, simulated

"My condition is a part of my day, not the whole day. The Brain knows that."

— Akari (52) · type-2 diabetes since 2024

"The Dial isn't asking what I want done. It's asking how I want to be helped."

— Composite · across both cohorts

No quote in this section was transcribed from a real interview. They are distilled composites from the user-needs research and persona definition that informed Lena, Haruki, and Akari. Real-deployment interviews remain an open scope item.

Unknowns · the framework's edges

Five honest open questions. Trustworthy designers name their own edges.

If you read the case study and feel "everything is too neat," these are the places the seams show. They are also the next quarter's work.

U1 · Ritual proposal cadence

When should the Brain propose a NEW Protected Ritual? Day 21 of Lena's month, the Brain noticed she had chosen the post-gym protein herself 11 of 12 times — and proposed the ritual. But 11/12 is heuristic. What about a ritual the user wants exactly twice a year?

U2 · Lost surface fallback

Lena's Watch dies. The Life Brain runs on her phone — but the 10-second glance affordance disappears. Does the Brain switch to voice? Notification cards? Silent log only? The framework doesn't yet say.

U3 · Cross-day Disclosure conflict

Akari says "private about glucose" Monday morning. "Share with my daughter" Monday evening. Both are valid intents. The framework needs a rule for which disclosure wins on Tuesday — and neither user-explicit-resolution nor LLM-resolved feels right.

U4 · Multi-Brain interaction

When two adults with their own Life Brains move in together, what happens at the kitchen? Do their Brains merge into a Home Brain (P1)? Stay separate and federate? P6 has no answer. The path through P1 → P6 is one direction; P6 → P1 is unwalked.

U5 · Review-prompt burnout

Day 21 mid-month review proposes 2-3 dial changes. Fine. What about month 6? Month 12? At what cadence does "AI proposes, user approves" become noise the user reflexively dismisses? The framework prevents AI from acting autonomously — it does not yet prevent the user from auto-approving.

Backstage · Unknowns Naming these is the case study's most senior move. Frameworks that pretend to have all the answers are sales decks, not architecture.

Takeaways · three things you can borrow tonight

If you take nothing else from Project 06, take these three.

Each is independent of Context Grammar. Each can be applied to any AI feature you ship next quarter.

Principle 01

Pre-declared autonomy beats reactive autonomy.

Trust grows from boundaries the user names before the moment, not from undo buttons offered after. Apply to any feature where AI will be doing something on the user's behalf — let the user draw the line first.

Principle 02

The grammar holds; the rhythm varies.

Same framework served Lena (60% AI) and Haruki (15% AI) — opposite users, same grammar, both successful. Design the system, not the persona. Let the dial position be the personalization, not the screens.

Principle 03

Personal scale is the testbed for organizational scale.

P6's Life Brain is structurally identical to P4's Project Brain — same three layers, same Dials, same composition. Shipping personal first is the lower-risk path to enterprise adoption. The smallest scale validates the largest.

Portfolio Map

P06 is Context Grammar at the smallest scale: one person.

The Brain changes only in size. Structure stays the same. P06 is the most fundamental application.

The everyday life of a single person is the most universal scene — and the one most readers feel. Before the family, before the organisation, the question is: how do we support one person's will? Project 06 is Context Grammar's most fundamental application.
In one line
Trust isn't a single dial. It's a vocabulary you teach AI to speak — one boundary, one ritual, one thirty-day month at a time.

Project 06 · Life Brain · Context Grammar

Close

Context Grammar is not a design that takes will away.
It's a design that supports it.

The moment to let go. The moment to drive.
Lena's thirty days were built from both.

Life Brain Protected Rituals Forgotten Intent Retrieval Per-Domain Autonomy
← Back to portfolio · 日本語