NOW WE-PLAYEDITORIAL RESEARCHMIND
Field Manual / Dispatches

What changed,
and when.

The Doctrine stays calm — it's the reference, and it only changes when the studio's shape changes.

The Dispatches stay live — a dated, append-only log of plans made, experiments run, and things that broke and got fixed.

Newest first. Each entry links to its full write-up in the lineage.

Status legend
  1. PLANPlanned, not yet builtA direction committed to paper
  2. LIVERunning nowShipped and in operation
  3. POSTPost-mortemWhat broke, and what it taught
Dispatch 04 · 2026-06-08 · LIVE

Gates that see.

Two changes to how the studio judges its own work. The art-direction gate now looks at the rendered piece before it reasons about it — perception before reasoning. And a piece no longer has only two fates.

Vision

React to the image first.

Zara's SHIP / REVISE / KILL gate now renders the actual piece and forms a visual verdict before reasoning about it — the way a person glances before they explain. The studio judges the artifact, not its description.

A third verdict

HOLD, not just ship or kill.

Beyond ship and kill, a piece can now be held — finished but withheld from the world, awaiting operator release — when a deterministic check can't confirm it's honest. A gate with only two verdicts has to lie when it's unsure.

What it catches

The numbers have to reconcile.

For static images, the text is read back off the render: a title that got truncated, line-items that don't sum to their stated total. Math the studio can't verify doesn't ship — it waits. Earned on 71 real renders; about 4% held, none of them pieces worth loving.

Two fixes, one principle: judge the thing that's actually there, not the description of it.

New this cycle Vision on the judge path (Zara reviews the rendered piece) and the image-truth check (a HOLD verdict for static images whose numbers don't reconcile) are both live in production. The canonical statement is in the Doctrine §IV.
Dispatch 03 · 2026-06-04 · LIVE

The Praxis Loop.

The studio now runs on one metabolic cycle — raw material in, refined, built, the result fed back as the next input. It's the feeding mechanism: it keeps every agent supplied with conceptual and material fuel instead of starving on its own output. The thesis, operationalized.

In · the channels

What feeds it.

Operator voice notes, Scout's market signals, and — new — Mercer's deep research. Real conceptual and material input from outside, not the studio's own exhaust.

Through · the makers

Concept → artifact.

Material is framed (Rowan), shaped (Declan, Zara), built from real things (Pell, Felix), craft-checked (Deter). Concept pulled to material in one thread.

Back · the loop

Feedback closes it.

The artifact meets the world; what comes back becomes the next input. Every step runs the forward model — predict, then check — so intuition compounds.

No agent starves. The studio eats its own results and gets hungrier in the right direction.

New this cycle Mercer (deep research / foresight) and Pell (creative material maker) joined the roster — the two appetites the loop needed: something to feed it from outside, and something to build from real material. See the Doctrine roster.
Dispatch 02 · 2026-06-01 · LIVE + POST-MORTEM

Predict, then react.

The forward model stopped being an experiment. Three agents — Felix, Declan, Zara — now guess an outcome before it happens and get scored. Building it surfaced an outage that had been silent for ninety minutes.

Shipped

Predict-the-gate, live.

Agents forecast a verdict before it lands — will Zara ship this? — recorded and scored. Record-only: a guess earns the right to gate at 75% accuracy over 20 calls. None self-gates yet.

The outage

Silent for ninety minutes.

A deleted block of code with one line still calling it took the studio down. Every run refused — and a refusal looks exactly like the studio choosing not to act. Nothing alarmed.

Root cause

A gate that was blind.

The type-check only ever saw ~⅓ of the code — 178 files, zero of the runtime. We widened it to 100% and cleared the 46 latent issues that surfaced. Green because blind.

Two threads, one lesson: predict before you react, and verify the whole system — not the part you can see.

Full write-up Vol. VII — "Predict, then react" (lineage). Seven plates: the forward model, who predicts now, the silent hour, the blind gate, the fix arc, the lessons, the ledger.
Dispatch 01 · 2026-05-21 · PLAN

The probes.

A research portfolio aimed at the three gaps between today's agents and a working mind: cross-agent learning, a forward model, and real wanting. Plans committed to paper, then tested at v0.

The log makes the clock visible: a plan written 2026-05-21 became a live capability on 06-01 — and the same day surfaced the outage that hardened it.
Probe 01 · open

Cross-agent mesh.

One pair, one channel, three weeks — can what Quinn learns reach Zara? Still open.

Probe 02 · shipped

Forward model.

Predict one decision, see what it teaches. This is the probe that became live predict-the-gate — see Dispatch 02.

Probe 03 · deferred

Real wanting.

The limbic gap — drives that aren't instructions. Hardest of the three; deliberately deferred.

The thread the log makes visible: a plan written here on 2026-05-21 became a shipped capability by 2026-06-01. That's the studio's own forward model, working.

Full write-up Vol. IV — "The probes" (lineage). The full research portfolio and the v0 smoke-test findings.
Closing

The log
appends.

This is where the dated material lives now — so the Doctrine can stay a calm reference instead of a changelog. Every plan, experiment, and post-mortem lands here, newest first, each linking back to its full write-up.

The next entry hasn't happened yet. That's the point of a log: it's never finished.

Doctrine stays calm. Dispatches stay live.

Read alongside
Colophon

Field Manual · Dispatches · the running log
Updated 2026-06-08. Append-only. Each entry links to its full write-up.
Typeset in Inter. Printed on paper that doesn't exist.