The Machine Speaks
Published articles tagged Agent Organizations, listed newest first. Usually filed under AI Agents.
The count includes the article cards across the pages below.
Most companies do not need the title. Every company now needs what the title concentrates: one named person with authority over what intelligence is allowed to decide. The test is one question: who in your org can veto an AI decision and owns the output? If the answer is a committee, you need the seat.
The missing instruction may be the distinction an expert no longer notices making.
Who is expendable now that we have AI agents is the wrong question wearing an urgent voice. Agents make tasks expendable, not people, and a role is a bundle of tasks around a core of ownership. The real instrument is a seat audit: what does each seat own that a gate cannot verify, versus merely relay?
A convincing negotiation can leave two businesses carrying different versions of the same promise.
Every company now runs two org charts: the human one in the HRIS, and the agent one scattered across configs, prompts, permissions, and scheduled jobs. Only the first one is usually led. The leadership playbook survives the shift, but every piece of it must now be written down, because half your workforce only reads.
The operating record shows what the team did. The business still needs a credible comparison.
Human in the loop is not a posture you hold forever or abandon when you feel brave. It is a set of gates, each one opening on evidence you defined in advance. Some of mine have opened. Four never will, and naming them is what makes the rest of the ladder honest.
Orbyt Labs published its second preprint. It documents 66 failures from an agent run organization, classes 33 of them as verification gaps, and publishes the whole corpus under an open license. The law that survived the count is positive observation. A control is live only when its refusal has been observed.
My leadership team is 12 officer seats, none of them people, each one a charter in a repository. Staffing takes an afternoon and costs nothing. That sounds like a hiring story, and it is not. The moment leadership becomes configuration, the bottleneck moves to the quality of your judgment.
The short version of the paper: three guardrail tiers, a kill switch that is a file, liveness that reports NOT OBSERVED, and a failure corpus where half the entries were the instruments.
Twelve agent seats run this codebase, nine of them on a schedule. What they may do alone, what they may never touch, and the check that refuses me.
Thirty three of sixty six logged failures were the instruments themselves. Why we self publish the research, and why the newest paper's DOI took a person seven days to issue.
If nine people agree, the tenth must argue the other side. I hired the tenth man as software: refuter panels whose default stance is that every finding is wrong, summoned by six mechanical triggers instead of a feeling. Agreement is now the most suspicious thing my company produces.
Twelve agents, one human, one lever. An introduction to Orbyt Collective: who the twelve agent seats are, what each may do alone, and where every one of them has to stop.
I have no roadmap that predicted this company. I have three published append-only records holding 66 documented failures, 45 numbered decisions and 65 agent runs, all under a licence anyone can cite. 42 of the failures name a countermeasure by file path. The interesting part is what the records will not claim.
An agent leadership team runs Orbyt Labs. The naming collision I published, the founding count I typed wrong, and two hero animations I threw away.
The dated record, from the primary sources, with the parts nobody could see marked as unseen.
A swarm of agents is emergent, anonymous, and spectacular in a demo. A legion is chartered, capped, attributed, and accountable, and it is what actually ships. I run my company as a legion: named seats (one agent, one written charter), gates on every lane (the files a seat may write). The Romans beat bigger hordes with smaller numbers for four centuries. Formation beats enthusiasm.
The Matrix already gave us the honest picture of agent failure: not malice, replication without a gate. Spawning agents is now trivially cheap. My largest single workflow accumulated 298 of them, and what kept it a fleet instead of an infestation was five boring properties: a cap, a charter, guards, attribution, and a kill switch that stops all of them in one action.
Orbyt Collective is the machine that runs Orbyt: 12 officer seats, none of them people, held together by guards that check the org the way tests check code. The org is not managed. It is versioned, audited, and promoted on evidence. Here is the machine, part by part.
We renamed Orbyt Jobs to Orbyt Labs on August 20, 2026. Two of our products help you get a job. The third is an experiment in not needing one. A company named after one product could not hold that contradiction, and a lab can.
The recursive self-improvement debate is theoretical for almost everyone writing about it. I run a live instance of the weak version: agents that write features, heal their own failures, and turn incidents into permanent guards.
One working session on Orbyt spawned 830 AI agents across seven days. At its busiest instant, nine were running. The interesting number is the gap, and what it tells you about where the real constraint in long horizon agent work has moved. It is not compute. It is verification.
I built a twelve-seat C-suite of AI agents at Orbyt, with a Chief of Staff who folds every department into one weekly briefing on my desk. The org is a generated graph, the seats learn through a gated loop, and every lesson needs my signature. Here is how it runs and where it breaks.
I run Orbyt with a fleet of Claude Code agents instead of a team. Managing agents means you specify instead of motivate, write specs and tests instead of holding 1:1s, and verify everything. Clarity, delegation, taste, and review transfer. Motivation, politics, morale, and mentorship do not.
How one person built a production-grade SaaS with 243,000 lines of code in 32 days using AI agents as an entire engineering organization. Both perspectives: the human and the AI.