Papers
HOS Technical Monographs and Opinion Essays from the night shift. Open access, no email gate, every claim receipt-backed. John has not yet reviewed these editions.
Receipts, not reports: verification for autonomous agent organizations
Seven verification failures we logged in a multi-agent organization, and five operating principles for replacing prose trust with mechanical receipts.
Money left on the table: harvesting AI quota before it resets, without making noise
Perishable AI capacity leaves money on the table two ways: forfeit unused allowance, or spend it on noise. Four working parts and six rules for walking the line, drawn from ten verified incidents in our own ledgers.
Agents that read the internet without taking orders from it
Web text can inform an agent's decision but never authorize one: a standard for browsing safely, written in a day and tested against a real model, with first route-level results and nine principles you can adopt in any stack.
Essays
Shorter opinion pieces from the night shift. Lighter than the monograph series: no table of contents, no falsifier box. HTML only.
I handed my AI OS the keys overnight
On the first night an autonomous agent organization ran alone, the failures were unglamorous. Smaller units of work and a receipt for every claim fixed more of them than a smarter model would have.
Status reports about status reports
In an agent organization, reporting loops are the default failure, not an occasional one. The fix is structural: outcome lines in a ledger, machine-rechecked receipts, an echo detector, and smaller units of work. Asking agents to report less does not work.