Research · Founder's notes

The thinking behind the swarm.

Ten notes on why high-stakes work should be run by thousands of narrow agents behind one deterministic boundary — from the mathematics of compounding error to what ten sessions on real capital taught us. Point at a note and the figure becomes its idea.

02The seriesEight posts · the system, gate by gate

From the unit of work to the open platform.

Read in order, the eight posts walk the architecture from the lifecycle test to the master-and-copy model — each one describing the research idea behind a layer of the stack.

  1. 03
    Series · 01

    Not Tasks. Lifecycles. Why We Stopped Building Assistants

    Why we stopped building assistants and changed the unit of work to the lifecycle.

  2. 04
    Series · 02

    Why Five Thousand Small Agents Beat One Large One

    Failure analysis, not a taste for scale: why thousands of narrow agents beat one large one.

  3. 05
    Series · 03

    Agents Decide. Code Executes. The One Boundary That Matters

    Eight layers, one boundary. The top four estimate; the bottom four are deterministic code.

  4. 06
    Series · 04

    Post-Training a Model on a Rulebook, Not on the Internet

    Closing the gap between a model that knows finance and one that knows this lifecycle.

  5. 07
    Series · 05

    The Execution Council. Governance in Milliseconds

    Governance in milliseconds: what the council checks, three operating modes, and the kill switch.

  6. 08
    Series · 06

    A Ledger Nobody Can Edit. Hash Chains as Audit Infrastructure

    Append-only, hash-chained, replayable. Why a record an administrator can edit is only a claim.

  7. 09
    Series · 07

    Lifecycle 01. What Ten Sessions on Real Markets Taught Us

    What ten live sessions on real capital showed, precisely what they did not, and where the cost goes.

  8. 10
    Series · 08

    Master and Copy. How a Proven Agent Becomes a Platform

    How a proven agent becomes a platform: prove one, master and copy, then open the rails.

Four things that never change

The research contribution is four constants.

  1. Agents decide. Code executes.

    The top four layers estimate and reason; the bottom four are deterministic. The boundary between them is a typed schema.

  2. No single agent sees the whole job.

    Each agent is scoped to one gate and does one thing. Its failure is local and its output is a proposal until something downstream permits it.

  3. Nothing an agent believes can move what it is not permitted to.

    Capabilities are held per agent and per tool, enforced by the runtime rather than by the model's good behaviour.

  4. Anything that settles is written to a ledger nobody can edit.

    Append-only, hash-chained, replayable — and written only after an independent counterparty confirms.

See it run

The ideas, as working objects.

Tighten the council on the live swarm. Edit a record and watch the chain break. Run one simulated session of Lifecycle 01.