Transparency · Policy

Capability advances only with safeguards

Our responsible scaling policy ties each level of agent autonomy to safeguards that must exist before it ships.

Capability tiers
T1

Advisory

The agent proposes and explains; a human executes. Required safeguards: full trace capture and honest-partial reporting.

T2

Reversible action

The agent acts inside sandboxed, undoable surfaces. Required safeguards: capability grants, budgets, and provable memory.

T3

Consequential action

Money, signatures, or irreversible state. Required safeguards: MCL compilation, signed receipts, replayability, and human-approved policy bounds.

T4

Sustained autonomy

Long-horizon operation without step-level review. Not shipped. Gated on interpretable intent traces and durable evaluation evidence we do not yet have.

Evidence gates

The conditions we will not cross