feat(ghost-read): per-prompt QC delegation — route the reader by placement

Operator: "the cc layer needs to be set per prompt by the pmu lens — delegate
the QC for each prompt to the most fitting one, not always the same."

The ghost-read persona IS the QC reader, but the book/blog routes hardcoded
Budget Writer (defaultKeys ['B']) for every chapter. So the About-the-Author
page (6c7b58fef) was graded by a procurement buyer, who read it CLEAN-but-
irrelevant ("no connection to AI risks… a personal anecdote") — a category
error: a bio is not a procurement item.

Fixes:
 - NEW persona K, The Discerning Backer — the right reader for a bio/credibility
   page: a status-aware peer/investor/journalist whose gate is "do I want this
   person at my table?", not "would I sign?" (unusual biography = an asset;
   reader-as-hero; recomputable hook over trust; [Pn] contract kept).
 - personaKeysForContent(filePath) routes the persona by PLACEMENT — path
   dominates (a /pricing page is a buyer page), content keywords as fallback
   (path-neutral book chapters route on prose). Tunable dial: QC_PERSONA_MAP.
 - Wired at the persona-resolution point; explicit --personas still wins;
   unmatched content falls back to route.defaultKeys (safe).

Guard (same commit): tests/blog/qc-persona-routing.test.mjs (8/8) — About-the-
Author→K, pricing→B, architecture→A, underwriting→U, compliance→E, unmatched→
null-fallback. LLM-free routing; the reader model still does the monologue.

Originating-Terminal: 📐 architect
Relevant-Rooms: 📐 architect, 🧭 navigator, 🧪 laboratory
Persona-Intent: The operator sees the About-the-Author page now graded by the
reader who actually decides whether to back the author — the QC delegated to
the most fitting one per prompt, as the lens already delegates the QC room.

Receipt-Verified: σ=2.00 · cell=A1 · witness-agreement=GZIP_ONLY · lens=gzip · receipt=84f0ad82

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0177tZrfK4nEfqRKTAgSKaoN

commit 34a7f698b — 144×144 lattice triptych (on-chip)

◎ the ingest chose A2,B — Strategy·Goal × Tactics — acting on A,C — Strategy × Operations (grip 0.766) · the walk starts at the ACTOR's row · 2 file(s)

⏱ ingest 534.9ms (corpus→lattice) · definer walk 1620ms (row→transpose→row, ballistic XOR per hop) · total 2529ms
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) · 4% 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

A2,B — Strategy·Goal × Tactics (actor) acting on A,C — Strategy × Operations (patient) · grip 0.766

actor seed A2,B — Target positions set quarterly goals that require specific tactics and leverage maneuvers to successfully occupy. The target is the cell coordinate the system MUST occupy by end-of-quarter. Anything that does not drive toward that coordinate is exhaust, and exhaust does not become substrate by being labelled progress. 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. Vision is the coordinate the lattice rotates around — the fixed bearing every iteration is measured against. Without the fixed point, motion is movement; with the fixed point, motion is convergence. 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. Define the goal as a verifiable predicate, not a feeling. The system terminates when the predicate evaluates true, and the predicate is what the next agent inherits when this one hands off. 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. A goal that cannot be tested is a wish. Wishes have no termination condition, so they consume budget forever; goals have a finish line and therefore a payable price. Execution is a sequence of bets made under uncertainty. Tactics is the discipline of betting the right size on the bet whose information value pays for the loss-if-wrong.

patient seed A,C — Long-horizon strategy substrates provide the frame for daily operations, run cycles, and execution cadence. The lattice we build today is what next year's underwriter inherits. We set the substrate that downstream pricing rides on, and that choice is paid back across every quarter we keep operating. Direction is what you keep when you forget the calendar. Multi-year posture, irreversibly chosen, defines the boundary every quarter renegotiates inside. Strategy is the bearing the rotation is measured against. Capital lives where strategy is durable. Frame the ten-year shape of the business before optimizing the ten-week sprint; the substrate decisions compound while the surface decisions decay. The strategic question is which doors close on purpose. Anything that keeps every option open until next year has already chosen the option of inaction, paid in optionality cost. Operations is the loop that runs whether anyone watches. The daily commit, the hourly hook, the per-request fingerprint — the substrate of the substrate, ambient and unwatched. Process is what you forget to do; ops is what does itself. Convert manual moves into ambient state, because the tax of remembering compounds faster than the tax of automating. The daily friction is the diff between your intent and your harness. Close the diff or pay the tax twice — once in the slip, once in the apology to the next agent. Operations earns its keep by being boring. The day the routine is interesting is the day it has already failed and is being narrated rather than executed.

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) · 2% 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 · 7% 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 · 10 in the 9×9 A1..C3 square · 1723 in the 132×132 children square · 400 cross-zone
REALITY: 1 in the 3×3 ABC corner · 2 in the 9×9 A1..C3 square · 1814 in the 132×132 children square · 237 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 12 claims @ θ 0.5938 · reality 53 claims @ θ 0.625 · projection 617ms

SHAPE-MATCH σ = 2.04 — the real intent↔reality definer walk vs random-reality (actual 0.1214 vs random 0.065). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · weak · panel story is not yet evidence

Most out-of-lane row: C1 · Grid — 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 45% vs tolerance 25%.
292 green · 210 amber · 419 red · 125 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 67% (no distinctive match)

reality 70% for (const rule of QC_PERSONA_MAP) { if (rule.test('', text)) return rule.keys; }

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

intent 69% (no distinctive match)

reality 77% (no distinctive match)

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

intent 72% (no distinctive match)

reality 73% (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 73% Operator: "the cc layer needs to be set per prompt by the pmu lens — delegate the QC for each p

reality 75% (no distinctive match)

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

intent 78% (no distinctive match)

reality 78% (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 80% tests/blog/qc-persona-routing.test.mjs. PER-PROMPT QC DELEGATION (2026-07-13). The ghost-read p

reality 77% // K = The Discerning Backer — the RIGHT reader for an author bio / credibility

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

intent 73% (no distinctive match)

reality 77% (no distinctive match)

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

intent 77% (no distinctive match)

reality 77% (no distinctive match)

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

intent 69% Receipt-Verified: σ=2.00 · cell=A1 · witness-agreement=GZIP_ONLY · lens=gzip · receipt=84f0ad82

reality 70% 'A status-aware peer — investor, reinsurance exec, journalist, high-status operator — deciding

C1,C1 Power flows where the grid lets it.

intent 70% (no distinctive match)

reality 75% (no distinctive match)

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

intent 72% (no distinctive match)

reality 75% (no distinctive match)

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

intent 77% (no distinctive match)

reality 72% (no distinctive match)

commit context — 2 file(s)

feat(ghost-read): per-prompt QC delegation — route the reader by placement

Operator: "the cc layer needs to be set per prompt by the pmu lens — delegate
the QC for each prompt to the most fitting one, not always the same."

The ghost-read persona IS the QC reader, but the book/blog routes hardcoded
Budget Writer (defaultKeys ['B']) for every chapter. So the About-the-Author
page (6c7b58fef) was graded by a procurement buyer, who read it CLEAN-but-
irrelevant ("no connection to AI risks… a personal anecdote") — a category
error: a bio is not a procurement item.

Fixes:
 - NEW persona K, The Discerning Backer — the right reader for a bio/credibility
   page: a status-aware peer/investor/journalist whose gate is "do I want this
   person at my table?", not "would I sign?" (unusual biography = an asset;
   reader-as-hero; recomputable hook over trust; [Pn] contract kept).
 - personaKeysForContent(filePath) routes the persona by PLACEMENT — path
   dominates (a /pricing page is a buyer page), content keywords as fallback
   (path-neutral book chapters route on prose). Tunable dial: QC_PERSONA_MAP.
 - Wired at the persona-resolution point; explicit --personas still wins;
   unmatched co

scripts/ghost-read-async.mjs
tests/blog/qc-persona-routing.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 585.52ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 34a7f698b

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.