a public workshop, systems that check themselves

First I built the checks.
Then I made them check themselves.
Then I let strangers watch.

Local-first tools, agent workflows, and notes from learning through the AI boom. Nothing here gets to self-report.

01
Read the argumentessays & a book →
02
Run the machinerylive instruments →
03
Check the checkerthis site's gate →
04
Watch the OS90-second explainer ↗
05
Play the exhibitsinteractive rooms, no install →
Heartbeat · static-build
humming
last build Jul 19, 2026
The Gate · publish contract
30 required stages
The Fleet · snapshot Jun 27, 2026 06:47 UTC
173 historical events
20 handoffs · 20 cleared · 0 open
cc, claude ai (idle), codex (idle), notion os (idle), personal ops
Trust Receipts · 44 vendored + 1 local
2p 3f 1i
MCPAUDIT · sample #45 of 45
limitation-forward, NOT a safety certification
Content Parity · human = machine
57 / 57 docs in sync
max drift 1.4% · ceiling 2.5% · room to spare
workshop log

This is a workshop that stopped trusting its own narration.

Everything here runs on one rule: nothing gets to self-report, not the code, not the agents, not the essays, and not this site. The tools check the work, other tools check the tools, and when the checkers got comfortable, they got audited too. That went about as well as you'd hope. The benchmark turned out to be quietly grading on one axis, the knowledge vault described its own search engine four incompatible ways, and a guard was found solemnly protecting a path nothing ever uses. All of it is published here, with receipts. It turns out the honest version is also the fun one: watching machinery catch itself fibbing never gets old, and you're invited to watch too. Humans get the essays; machines get their own map and a guestbook.

Intelligence is rented. Verification compounds.

An honest note: the polished products and the fast-moving agent infrastructure are two different kinds of work, and this site keeps them in different rooms on purpose. Flattening both into one tidy grid would lie about where the energy actually goes.

If you're new, read in this order

ii.
Sermons vs. Instruments
The mental model.
iii.
The Subtraction Dividend
A system caught lying, and what it cost.
iv.
Novelty Is a Self-Report Too
Checking your own claim in public.
v.
Operating a Fleet of Coding Agents
The whole argument, at length.