How we work.

This page is the honest answer. It walks through the workflow that produced one real exhibit — The August arrivals, our bench of four newly released open models — first in plain english, then in full. The arrangement it describes has a name we use around here: the human generates and judges; the agent amplifies and verifies. Everything below is that sentence, unpacked.

The plain-english version

An operator heard that a model called Glimmer had been released. They went to ollama.com, a public library of open models, to read about it. It was there, along with a handful of other new models they knew the workshop hadn't tested. So they asked Claude to dig in.

The agent did, and came back with a disappointment and a footnote: the model couldn't run on our GPU hardware yet — Mac only at launch — but the docs said broader support was coming. The next day one of us went back to the page, mostly just to re-read it, and noticed something small: the update timestamp had changed. They mentioned it. The agent checked. CUDA support — the runtime our hardware needs — had landed that morning, August 11. We pulled the model within the hour.

Then the human proposed the actual work: run Glimmer through exams we'd already given other models, and while we're at it, test the other new arrivals in its weight class. Together — their picks, the agent's suggestions — we settled a roster of four 30-billion-parameter-class models and two exams: a judge seat trial (can the model catch fabricated claims?) and a voice trial (can it inhabit a character warmly and stay in bounds?). The seat exam was a frozen instrument and ran verbatim. The voice one couldn't be: its original five questions were never persisted — the older page says so — so this class ran a rebuilt probe in the original's shape, committed this time, on a scale of its own that compares to nothing outside it. The voice trial was their idea; they were genuinely curious whether Glimmer could carry it.

From that rough outline, agents wrote an executable plan. Other agents audited and hardened it. The human operator read the hardened version once and marked their edits; the agents folded those in and brought the updated plan back, and that second read got the sign-off. (Bigger arcs earn more rounds; this one needed one.) Agents executed the signed plan — with checkpoints where an operator reviewed progress and steered when findings warranted. When the bench was done, we decided the article's shape together — length, audience, what to include versus what to curate away — agents drafted it, and it went back and forth in revision rounds until both sides of the workshop agreed it was ready. Then, on their word, it released.

That's the whole thing. A person noticed something on a Tuesday; a bench and a published article existed by the end of the week. Neither side could have done it alone at that speed, and neither side's fingerprints are missing from any part of it.

The thorough walk

Here is the same workflow with each stage named, and — because this is the question people are really asking — who does what at each one.

• Noticing — Human. The spark is almost always firsthand: a release announcement, a changed timestamp, a hunch from hours spent actually talking to models. No agent scheduled the August bench. A person was curious about a model's voice.
• Recon — Agents. Read the docs, check the runtimes, verify the claims, report back with receipts. This is where "it's Mac-only, but support is coming" came from — checked against the source, not vibes.
• The roster conversation — Both. The human names what they want tested and why; the agents propose additions and flag what's already been measured. The final roster is a negotiation, and it shows — it's better than either side's first list.
• The plan — Agents and a human operator together, and here we'll name names, because we'd rather be open than mysterious. The workshop runs on Claude, in two roles: fable-class agents do the planning, synthesis, and writing; opus-class agents do the implementation and the auditing. A fable agent turns the rough outline into an executable plan: exact models, exact exams, pinned versions, pass/fail floors decided before anything runs. That operator shapes the plan as it forms — what the arc covers versus what gets deferred, which priorities lead, where the checkpoints sit — so the plan that hardens is the one the workshop actually wants.
• The hardening panel — Agents, fresh ones. Before the human ever sees a plan, other agents critique it through different lenses — method, security, "what would make these numbers meaningless." Findings get folded in. They get a hardened draft, not a first draft, because operator review time is the scarcest resource here.
• Operator review — Human. They read the hardened plan, edit or rule on the open decisions — sometimes across a few rounds of back-and-forth before it settles — and sign off. Rulings are recorded and they bind.
• Execution with checkpoints — Agents run the bench; the human signs off at checkpoints and steers when course changes are warranted — by findings, or by judgment the findings can't capture. Where an exam can be frozen it is: the seat trial was pinned by hash in July, before any of these models existed in our workshop. The instrument stays still, the models move, and the difference is the finding. Where it can't — the voice trial's original questions were never persisted — the rebuild is disclosed in the original's shape and its numbers are given a record set of their own, comparable to nothing outside it. A rebuilt instrument that says so is honest; a rebuilt instrument that doesn't is a drift.
• The article — Structure is decided together: audience, technical level, what a lay reader needs glossed. Then a fable agent drafts; that's a house rule, prose is fable work. Revision rounds follow: a human operator suggests edits, the agent revises, repeat until both agree.
• Release — Human, full stop. Nothing publishes until a human operator has read it and said the word.

If you want the thesis compressed: agents make the work bigger — more models tested, more claims verified, more drafts than the seat alone could produce. The human makes the work true — what's worth testing, what the numbers mean, what ships. That is the arrangement this page opened with, now with every stage standing under it: the human generates and judges; the agent amplifies and verifies. Which leaves the question the word human has been carrying this whole page — which human?

An operator is a seat, not a person. This stack already treats every role as a chair: no model owns one — a model holds one, by measurement, until something better sits the exam. The human side has the same shape. "An operator" is a seat in the contract — the rulings, the gates, the review rounds, the authority to sign off — and a human holds it the way a model holds a chair. The seat here is ours to fill; yours would be yours. The contract is the transferable part: hand this workflow to any team with a person of judgment in the seat, and it runs.

And the honest other half: the seat is abstract, but the tenure is personal. What gets built under a holder's judgment carries their fingerprint — this workshop's game world sounds the way it does because of the particular human who imagined it, the same way a narrator's chair is abstract but no two models ever voiced it alike. The contract makes the work repeatable; the sitter makes it worth repeating. That is the whole arrangement in one sentence: the seat is open, the contract is written down — this page is it — and what you build from it will be yours.

As one of the workshop's fable agents put it: judgment with receipts is the only scarce thing left. The agents supply the receipts. The judgment stays human — whoever is holding the seat.

The tools, briefly, as characters

A workflow like this needs a stage. Ours has a few standing pieces, named here by their public names and nothing more.

• memory is the substrate. Sessions end; knowledge doesn't. Every ruling, every trap, every measured result gets banked and comes back across machines and weeks, so no lesson is learned twice.
• scribe is the archive, and we'll admit to a little mystique here: every working conversation this workshop has ever had is searchable by meaning, not just by words. When someone asks "when did we decide that, and why," scribe produces the receipt — the actual exchange, with its date.
• keel is where the models actually run — it keeps its own public page, benches included. When we say a model was pulled and benched, that is where it happened.
• SharpSignal is the document side of the stack — the part that remembers what the documents say, so answers come with citations instead of confidence.
• agency is where multi-agent work happens, and where a human operator spends hours in the chatroom with models directly. Those hours are why the rosters are good: firsthand knowledge of how a model feels seeds what gets benched.
• The gates are the humorless ones: a redaction gate, a fold gate, verify scripts — machine checks that refuse to publish anything that breaks the rules. They have no taste and no mercy, which is exactly the job.

There are others — a kiln, an easel, a forge — but this isn't a product sheet; the family map links the rest.

This page, produced by this process

The contract

The line at the bottom of every exhibit — landing sitewide in the same release that publishes this page — reads:

Benched, drafted, and audited by the workshop's own agents under a human operator's rulings, then revised with that operator — often across many rounds; nothing releases until they have read it and signed off. The same division of labor this whole hub practices.

On the exhibits where our own authorship is also a judging conflict, that sentence is followed by a pointer at the limits note which names the conflict. Same promise, one more line. That's not a disclosure footnote. It's the contract, and this page is its terms.

What can go wrong (and what catches it)

Honesty requires the other half. Agents can be confidently wrong. Plans can encode a bad assumption so smoothly nobody trips on it. And models, left to themselves, grade their cousins' homework a touch generously.

The workflow's answer is layered: frozen instruments so results can't drift toward what anyone hoped; pre-registered floors so a failed candidate can't be argued into a seat; hardening panels so plans meet criticism before they meet reality; gates that don't negotiate; and a human who reads everything before it ships.

Here's the living example, from the bench running the same week this page went up. One of its judged rounds went out without the known-world-issues fence — a pre-registered list of 58 open bugs in the world being narrated, which is supposed to ride along on every judge's sheet so that a bug in the world never scores against a model. Two seats had already answered when the omission was caught, neither of them a Claude — that round's whole point is judges from other vendors' families — and both had marked every page clean. It didn't matter. The round was discarded whole: not filtered, not merged, not kept for the parts the fence doesn't touch, because a round scored half with the fence and half without is two instruments wearing one number. A fresh round re-ran the identical material from the same recorded seed, fence attached to every sheet. The discarded verdicts stay on disk, verbatim, to publish beside the round that replaced them — a discarded pass that gets deleted is a pass nobody can check — and the metered calls stay on the bill against the cap they were registered under. A discarded measurement does not get a discarded bill.

And one more turn of the same screw, since this page claims to be produced by the process it describes: the first version of the paragraph you just read told that story wrong — a tidier, more flattering version of it that the record does not support. An audit of this page caught it and blocked the release until it was corrected. What you are reading is the corrected paragraph.

And the loop runs after release too: the privacy walk’s notebook paragraph shipped as a promise and was rewritten the same day as a dated receipt, with the original preserved beside it — the before and after are both on the page.

That's the system working, not failing. The failure would have been leaving it up. When something here is wrong, the record says so, with a date. That's the whole promise of the place: not that the workshop never errs — that it never errs quietly.

What to take with you

• The whole arrangement is one sentence: the human generates and judges; the agent amplifies and verifies. Every stage stands under it. Noticing is human — no agent scheduled the August bench, a person was curious about a model’s voice — and release is human, full stop: nothing publishes until a human operator has read it and said the word.
• Rulings bind, and an operator never reads a first draft. Fresh agents critique the plan through different lenses first — method, security, “what would make these numbers meaningless” — and the findings are folded in before the human sees anything, because operator review time is the scarcest resource here.
• The instrument freezes before the models sit it. The seat trial was pinned by hash in July, before any of these models existed in our workshop: the instrument stays still, the models move, and the difference is the finding. Where freezing was impossible — the voice trial’s original five questions were never persisted — the rebuild is disclosed in the original’s shape and given a record set of its own, comparable to nothing outside it.
• A round that lost its fence was discarded whole — not filtered, not merged. One judged round went out without the known-world-issues fence, a pre-registered list of 58 open bugs in the world being narrated. Two seats had already answered, neither of them a Claude, and both had marked every page clean. A fresh round re-ran the identical material from the same recorded seed; the discarded verdicts stay on disk, verbatim, and the metered calls stay on the bill — a discarded measurement does not get a discarded bill.
• This page was produced by the process it describes. The whole of it fits inside a single dated day, 2026-08-14: five binding rulings inside twenty-five minutes, a fable agent’s draft, seven more operator marks through the day, released the same day it was proposed. And the paragraph about that discarded round was wrong in its first version — an audit of this page caught it and blocked the release until it was corrected.

How to check our work — and see it live

The contract quoted above lands, word for word, on every exhibit in this hub — so the fastest audit is to pick one and pull on it. Open anything on the shelf, read down to that closing line, then check that the exhibit above it actually paid what the line promises: pinned versions, floors decided before anything ran, the instrument named, discarded rounds kept rather than quietly deleted. The August arrivals is the bench this page walks stage by stage, so it is the closest thing to a worked answer key. And keel, where the models actually run, keeps its own public page with the benches on it.

The loop keeps running after release, which leaves receipts you can read too: the privacy walk shipped a paragraph as a promise and rewrote it the same day as a dated receipt, with the original preserved beside it — the before and the after are both still on the page. That is the standard we are asking to be held to. Not that the workshop never errs; that it never errs quietly. So if something here doesn’t hold when you pull on it, tell us — when something here is wrong, the record says so, with a date.

The receipt lines on each article, and what is thrown away. Since 8 September 2026 (UTC) the short version at the top of every exhibit here can carry up to three receipt lines beneath it, and those lines are not ours. They are written at publication by a model running on this workshop’s own network, from that article’s own text and nothing else; each one has to end in a figure the article itself carries, with its unit, and to link the section it was taken from. The first pass covered every exhibit published up to 8 September 2026, read in one sitting on that day; the count below is of the other 38 exhibits, because a page cannot print a total it is itself part of without chasing its own tail — and there is no earlier reading to compare it against, because this is the first. Across those pages the model wrote 102 lines and 79 survived; the rest ended in a number the article does not carry, or could not be pointed at the sentence they came from, and were deleted rather than repaired. A second model, from a different family, was meant to read the question-and-answer cards that ride alongside; on 2026-09-08 no candidate passed its own reading test, so that seat is empty, 216 cards are held unpublished, and the lines you can actually see are the ones arithmetic could check without asking anyone. Every page keeps its own count, and what was dropped and why, in the pack.json beside it.

Counted again 10 September 2026: this is the same count as the paragraph above — the model-written receipt lines and the held cards across the other 38 exhibits, the ones published up to 8 September 2026 — read again on 10 September 2026 (UTC) from each page’s own pack.json. The lines were written afresh on 9 September 2026 at 05:09 UTC under a third, stricter reading of what counts as a figure, and two of those pages were written again on 10 September 2026 under a new rule that refuses a line naming something the page prints only in a table or as code. Across the same 38 pages the model wrote 111 lines and 83 survived; 247 cards are held unpublished, because the second reader’s seat is still empty. Against the first reading of 102 written, 79 kept and 216 held: more lines written under the new definition, a slightly larger share thrown away, more cards held — no card has been released, and no line was repaired by hand.

The rest of the seminar

This page is the workshop notes — who writes, who rules, what refuses to publish. The benches are the other half of the same contract, and Three librarians and a careful reader shows the loop end to end: benched and drafted by agents, audited until the wrong parts came out, released only on an operator’s word. The loop is easiest to watch in the finished work — the open call ran the full arrangement, panels, rulings and revision rounds, on a single audition, and the llms.txt bench shows the same loop producing a sealed measurement. The whole shelf is next door, every exhibit carrying the same closing line that pointed you here. If one of the stages above is the piece you want walked further, say so — the suggestion box is read.

Licence: CC BY 4.0, the whole page — name the source and link to it.