docs(marsh): nudge event found the thread had moved on — drafted the real reply instead

The GCal-scheduled "send a light nudge if no options landed" event fired at 12:00pm ET
assuming silence. The thread had already gone through four state changes since the prompt
was authored: Mary offered today, retracted it, asked us to take calendar control, and
Elias had already locked Thu 16 Jul 3pm UK on his own calendar off an earlier self-reviewed
draft. Sending the literal scripted nudge would have re-asked for something already
resolved.

Tightened the vetted reply's one weak paragraph (a double hedge that qwen-as-Mary read as
"ugh, another rescheduling"), re-graded clean, created a Gmail draft (cc Carls/Dias) rather
than auto-sending — draft-only tool, and a specific-day commitment cc'ing two more
executives right after Mary's own message recall warranted a one-click confirm, not a
silent fire. Still needs the agenda PDF attached by hand (tool has no attachment support).

Filed two off-center findings rather than dropping them: bf-1404 (architect) — GCal RUN
prompts need a freshness check against live thread state before firing scripted text;
bf-1405 (network) — the Gmail draft tool can't attach files, so any PDF-bearing GCal reply
needs a manual-attach flag or a route through the comms/Resend pipeline.

Originating-Terminal: 🎩 operator
Relevant-Rooms: ☕ network, 📐 architect, 🧭 navigator
Story: The GCal C2 runner fired on a stale premise; reading the live thread and calendar before acting caught it, and the correction plus the two systemic gaps it exposed are now recorded so the next fire on a live thread doesn't repeat it.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

commit 51383b235 — 144×144 lattice triptych (on-chip)

◎ the ingest chose A1,B3 — Strategy·Law × Tactics·Signal — acting on A1,B — Strategy·Law × Tactics (grip 0.781) · the walk starts at the ACTOR's row · 2 file(s)

⏱ ingest 225.3ms (corpus→lattice) · definer walk 438ms (row→transpose→row, ballistic XOR per hop) · total 1367ms
ingest here = commit-scoped SENSING only (this commit's message + changed files → lit anchors) — deep seed authoring lives in the reef-self-loop, off the commit path

rows = ACTOR (lens) · cols = PATIENT (object) · diagonal = self-reference; ◎ at actor-row × patient-col — every panel, same orientation. Heat above the diagonal = actors ranking ShortLex-earlier than their patients (the walk follows definers uphill in rank).
The 12 canonical lanes (rows top→bottom, cols left→right): A·Strategy · B·Tactics · C·Operations · A1·Law · A2·Goal · A3·Fund · B1·Speed · B2·Deal · B3·Signal · C1·Grid · C2·Loop · C3·Flow

PAIR LATTICE (the map we normally see)

PRE-WALK SENSE · INTENT grid — the snapshot, no point of view

the no-point-of-view snapshot — what the sensor lit before any walk; the leaf walk below is what bridges the two grids

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PRE-WALK SENSE · REALITY grid — the snapshot, no point of view

the no-point-of-view snapshot, reality side — same sensor law

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PRE-WALK Δ · straight comparison of the two ingested grids (green both · cyan intent-only · amber reality-only) · 8% overlap · ◎ = where the competence pixel sits in the raw overlap

good = green overlap without being a copy — near-100% is self-similarity, not alignment

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

◎ the pixel this commit belongs to

A1,B3 — Strategy·Law × Tactics·Signal (actor) acting on A1,B — Strategy·Law × Tactics (patient) · grip 0.781

actor seed A1,B3 — Articles of governance mandate the binding rule for signal bandwidth and message broadcast reach. EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at any moment. Compliance attaches to the artifact the artifact cannot escape — provenance is a regulatory primitive, not a feature. Constraints precede objectives. The cap-table, the license text, the consent envelope — each draws the inviolate line the action must respect, and the line is enforced before the optimization runs. A rule names what the system MAY NOT do. If the agent can do X, then 'forbid X' is not the constraint — it is wishful thinking dressed as policy. Constraints live in the gate, not in the prompt. Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipients tune out. The right channel is the one whose floor matches the message's importance. A broadcast that addresses everyone addresses no one. Precision over reach until the address is calibrated; only then does scale convert prospects into recipients rather than into unsubscribes. Repetition is the cost of being heard. Three sends to one recipient beats one send to three; the first send announces, the second send is heard, the third send is remembered. Every message carries provenance. The sender's history is half the message's weight; an unknown sender pays in attention what a known sender pays in seconds saved.

patient seed A1,B — Governance rules mandate a binding article that restricts which tactics and maneuver choices are legally permissible. EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at any moment. Compliance attaches to the artifact the artifact cannot escape — provenance is a regulatory primitive, not a feature. Constraints precede objectives. The cap-table, the license text, the consent envelope — each draws the inviolate line the action must respect, and the line is enforced before the optimization runs. A rule names what the system MAY NOT do. If the agent can do X, then 'forbid X' is not the constraint — it is wishful thinking dressed as policy. Constraints live in the gate, not in the prompt. Tactics is the choice of which leverage to pull at which beat. Not what we want, but how the want lands on Tuesday: the sequence of irreversible commitments, each made before the next one's information is available. Speed of feedback dominates speed of execution. Tactics that converge fast beat tactics that compute long, because the loop closes around the world's response before the world has moved. The tactical map is a ranked list of moves where each move carries a cost-of-delay. Pick the move whose cost of doing it tomorrow exceeds the cost of doing it imperfectly today.

INTENT · leaf-walk clouds · BLUE→VIOLET by ply (◎ = the competence pixel: actor∩patient)

good = the clouds concentrate where the commit SAYS it works

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

REALITY · leaf-walk clouds · ORANGE→RED by ply (◎ = the same pixel — the shared perspective)

good = the same clouds as intent — shipped where declared

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

DELTA · graded cloud divergence (green agree · magenta declared-not-done · amber done-not-declared) · 8% agree

good = mostly green; magenta = said-not-done (chase it in the code), amber = done-not-said (chase it in the docs)

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

TOLERANCE · cloud topology (dim green in-shape · hot amber bleed · red orthogonal concentration) · ⚠ TOO MANY

red only matters above the flip — a few amber is normal bleed

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

SHORTLEX-3 PROJECTION (ABC · A1..C3 · the 132 children — candidate, pre-ratchet)

PROJECTED INTENT · the commit’s claims, head→axis_i tail→axis_j (cyan)

the three-length view — good = claims land inside their own zone

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PROJECTED REALITY · same projection law (amber)

same projection law — good = reality occupies the zones intent does

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

STRAIGHT COMPARISON · green both · cyan intent-only · amber reality-only · 3% overlap

good = the zones agree; cross-zone scatter is the drift to read

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

shortlex-3 zone occupancy (lit cells per diagonal square)
INTENT: 2 in the 3×3 ABC corner · 9 in the 9×9 A1..C3 square · 1535 in the 132×132 children square · 362 cross-zone
REALITY: 0 in the 3×3 ABC corner · 0 in the 9×9 A1..C3 square · 836 in the 132×132 children square · 111 cross-zone
axes: identical 144 ShortLex names both sides (symmetric); weights asymmetric
zone 3 = candidate children, pre-ratchet (repo-derived dumps not yet past the perturbation-probe gate) · intent 34 claims @ θ 0.625 · reality 9 claims @ θ 0.6094 · projection 447ms

SHAPE-MATCH σ = 5.65 — the real intent↔reality definer walk vs random-reality (actual 0.1846 vs random 0.074). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · forming · separation is forming — the direction is real, the trust is not yet

Most out-of-lane row: A · Strategy — that lane is drifting most (read the red band in that row).

Three-colour tolerance (out-of-lane = reality fires where intent is weak, in orthogonal blocks): green=in-lane agreement · amber=a few out-of-lane (tolerated) · red=FIRED — orthogonal out-of-lane 26% vs tolerance 25%.
502 green · 303 amber · 283 red · 176 XOR-friction cells.

Both axes = the 144 ShortLex anchors, cell=row⊕col, on the chip. INTENT=docs+rules · REALITY=code · DELTA=friction.

tile dump — what the SimHash matched on the diagonal (inspect the sensor; tap to expand)

A,A The lattice we build today is what next year's underwriter inherits.

intent 78% **Take the time Paul already named.** Mary's 09:02 email said *"Paul can do 3pm UK or 3:30pm UK

reality 64% (no distinctive match)

B,B Tactics is the choice of which leverage to pull at which beat.

intent 70% (no distinctive match)

reality 69% (no distinctive match)

C,C Operations is the loop that runs whether anyone watches.

intent 77% (no distinctive match)

reality 72% (no distinctive match)

A1,A1 EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at

intent 80% **1. Paul wanted this TODAY.** Mary offered 3pm / 3:30pm UK at 09:02, then retracted at 07:10 t

reality 69% (no distinctive match)

A2,A2 The target is the cell coordinate the system MUST occupy by end-of-quarter.

intent 77% (no distinctive match)

reality 69% (no distinctive match)

A3,A3 Every dollar builds either the floor (substrate that lifts future bets) or the ceiling (cap on the next round)

intent 75% (no distinctive match)

reality 69% (no distinctive match)

B1,B1 Latency is the price of a missed beat.

intent 77% ## What the thread actually told us

reality 63% (no distinctive match)

B2,B2 The deal sets the exchange rate between two value substrates.

intent 75% Filed two off-center findings rather than dropping them: bf-1404 (architect) — GCal RUN prompts

reality 67% (no distinctive match)

B3,B3 Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipi

intent 78% The scheduled "send a light nudge" event found the thread had already moved past that: Mary ask

reality 73% attachments — bf-1405), then send.

C1,C1 Power flows where the grid lets it.

intent 75% (no distinctive match)

reality 67% (no distinctive match)

C2,C2 Each iteration is a hypothesis tested against the ground truth of the world.

intent 70% (no distinctive match)

reality 67% (no distinctive match)

C3,C3 Flow is the rate at which committed work crosses the finish line.

intent 72% Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

reality 73% (no distinctive match)

commit context — 2 file(s)

docs(marsh): nudge event found the thread had moved on — drafted the real reply instead

The GCal-scheduled "send a light nudge if no options landed" event fired at 12:00pm ET
assuming silence. The thread had already gone through four state changes since the prompt
was authored: Mary offered today, retracted it, asked us to take calendar control, and
Elias had already locked Thu 16 Jul 3pm UK on his own calendar off an earlier self-reviewed
draft. Sending the literal scripted nudge would have re-asked for something already
resolved.

Tightened the vetted reply's one weak paragraph (a double hedge that qwen-as-Mary read as
"ugh, another rescheduling"), re-graded clean, created a Gmail draft (cc Carls/Dias) rather
than auto-sending — draft-only tool, and a specific-day commitment cc'ing two more
executives right after Mary's own message recall warranted a one-click confirm, not a
silent fire. Still needs the agenda PDF attached by hand (tool has no attachment support).

Filed two off-center findings rather than dropping them: bf-1404 (architect) — GCal RUN
prompts need a freshness check against live thread state before firing scripted text;
bf-1405 (network) — the Gmail draft tool ca

data/self-prompts.json
docs/outreach/accounts/marsh-pack/2-mary-email.md

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 808.88ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 51383b235

Commit artifacts (open on a computer — Gmail mobile won't follow file:// links; the inline images above are the phone-viewable form): reef grid · this triptych · the HDL — all three are also attached to this email.