The organisation's only active project
Agents today are applications. This is the argument that they should be an operating system — and that the difference is not branding, but three abstractions nobody has built yet.
An OS earns the name when it owns how work survives interruption, how state is addressed, and how a person perceives and steers the whole machine. QM already solves the hard part underneath: a real multi-tenant harness with scoped identity, permissions, sandboxes and audit. ai-os is the layer above it.
Four questions today's agents cannot answer
Four pillars
What if the unit of work outlived the conversation?
Runs. A flow is a declared, persisted, resumable object with a goal, a shape, a state and a lineage. Agents and their sub-agents are markdown files; a declared tree executes as real work. A flow started by one process is finished by another, after a restart and after context compaction.
What if the interface were the state, not the transcript?
Runs. A desk: flows are documents, agents are cubes that stack on them. Drag a cube onto a document and that agent gets a step in that flow. The system composes the arrangement from the flow's state and never re-arranges what you moved.
What if memory had an address space?
Four levels — system, user, project, flow — with different lifetimes. Flow memory is expected to die. Promotion between levels is explicit, recorded and reversible.
What if we did not rebuild the part that works?
QM, vendored as a subtree and pulled weekly. Identity, scopes, sandboxes, policy, audit and six model harnesses. We did not write it and we are not rewriting it.
Where this actually is
Three pillars run. ai-base is vendored and runs.
ai-flows runs — the flow engine, a signed HTTP API,
multi-agent composition from markdown-declared trees, and the measurement
harness below. ai-ui runs — the desk pictured here.
333 tests of our own, on top of the 3,768 ai-base carries from
upstream. ai-storage is still specified and not
implemented. Nothing on this page describes running software unless it
says so.
ReviewAgent on the ledger flow:
it answers "Looks fine to me", the flow reports 3/3 done and green — and the
trace flags that the step carried nothing forward. That is the finding
the whole system exists to make visible.
AnomalyScanner is struck
through because it is declared in an agent's markdown and has no file — a
declared name is a claim, a file is a fact.Each pillar ships with the measurement that would show it is not worth building, written before the code. Two have now come back and neither flattered us. A flow does survive what a plain session loses — proven by starting one in one process and finishing it in another, on two harnesses. And the question of whether adding a reviewer to an agent tree helps came back unmeasurable: across four attempts the producer was already correct, so a review stage had nothing to add.
That second result is the one worth reading. It is the shape of Google's g-AMIE study, where physician oversight of an agent improved 6.7% of cases and reduced quality in 21.7% — oversight adding least where the output was already strong. Our first run appeared to reproduce it, reporting a reviewer that damaged a correct answer. It was an artefact of a check that scored “The answer is 24.” as wrong, and retracting it invalidated four other numbers. All of it is written up rather than deleted, because a finding that was wrong and the reason it looked right is the most useful record we can keep.
The predecessor of this project shipped eighteen thousand lines describing five subsystems and three test functions — an architecture written down and never pinned to anything that could contradict it. This is the correction.
Twenty-six frozen experiments, 2025 – 2026.
Agent memory, self-modification, interpretability and constrained decoding — each labelled by how much evidence stood behind it, including the ones where the evidence went against us. Kept because they are still true, not because they are maintained.