Skip to content
Rykon AI Help

Approvals and autonomy levels

Risk classes and autonomy levels

Every tool has a class from R0 to R4. An agent acts alone up to its level’s ceiling; above it, a person decides. R4 always waits.

Updated 1 min read

On this page

Two things decide whether an agent’s action runs by itself: the risk class of the tool, and the agent’s autonomy level.

Risk classes

ClassKind of action
R0Read, search, report.
R1Draft, note.
R2Reversible changes in your own systems: update a record, organise, message your own team.
R3Reach known people, publish, change settings or credentials.
R4Irreversible or outward: contact strangers, send in bulk, move money, delete, make a legal commitment.

Autonomy levels

LevelMay do aloneCeiling
L0, observeRead and report. Everything else waits for a person.R0
L1, prepareAlso draft.R1
L2, act insideAlso make reversible changes in your own systems.R2
L3, act outwardAlso reach known people and publish.R3
L4, operateThe same as L3 for now. R4 always waits.R3

Every agent starts at L0. A bare task always runs at L0.

Asking for more, never less

On an agent you can tick tools that should always ask a person first, whatever their class. A rule can only add approval; nothing you set lets an agent skip one its level requires.

Risk classes and autonomy levels · Help · Rykon AI