Skip to content
// Core idea

How it works

The loop, end to end: a job is routed by what's worked before, run by a worker, re-rewarded by its real outcome, and distilled into a lesson the next run on that project starts with.

↻ reward folds back into Route
View raw trace
> loop.trace
prompt ─map─▶ task region ─learned choice of (agent, model)─▶ route
                                                                  │
                                        a worker runs the agent   │
                                                                  ▼
   reward fold ◀── run verdict ◀── durable outcome (the job's pass / fail)
        │
        ▼
   the routing map drifts toward what works
        +
   distiller agent writes a lesson ──▶ recalled into the next run
// Guardrails

Invariants

Promotion never regresses

A candidate policy goes live only if it beats or ties the incumbent — on a held-out eval set or under a live canary — then flips with one signed pointer.

The worker floor is a hard limit

No learned routing or policy overlay can widen a job's power past the worker's fail-closed opt-ins. Learning tunes choices; it never escalates privileges.

> Agent memory is versioned

Each named agent's working state is snapshotted to its own versioned history at job end and restored at job start — continuity and a full audit trail for free, with secrets scrubbed before every snapshot. Project source is versioned the same way; that history *is* the durable record. No transcript database, no client-side capture.

> Let's talk

Stop guessing which agent gets the job. Start grading it.