AI agent autonomy levels for security work

Autonomy is set per action. Feng, McDonald and Zhang define five levels by the user's role, from operator to observer (arXiv 2506.12469, 28 July 2025). The worked example rates eight triage and fix actions on the NCSC's five 0 to 4 dimensions and finds two that can reach observer, four held at approver and two kept with a person.

Five levels named for the person's role

The paper's abstract argues that an agent's level of autonomy "can be treated as a deliberate design decision, separate from its capability and operational environment", and names five levels by the role the user takes: operator, collaborator, consultant, approver and observer. Descriptions below follow the paper's sections; the security examples are this site's.

Levels from Feng, McDonald and Zhang, Levels of Autonomy for AI Agents, arXiv 2506.12469 v2 (28 July 2025), read 19 Nov 2026.
LevelThe paper's description of the user's roleSecurity example
L1 OperatorIn charge at all times; the agent supports on demandAnalyst writes the triage query; the model drafts the ticket text
L2 CollaboratorClose and frequent collaboration; both plan, delegate and executeAnalyst and agent edit a threat model together
L3 ConsultantAgent takes initiative over long horizons; user gives feedback and direction, with no direct controlAgent works a backlog and asks the owner when a finding is ambiguous
L4 ApproverInteracts only at blockers, including signing off on consequential actionsThe agent prepares the merge of its own pull request and a named person merges
L5 ObserverNo involvement; logs to monitor and an emergency off-switch onlyAgent upgrades a finding's severity or opens a pull request; a person samples the log and holds the off-switch

Note what L5 means in the paper: the user "cannot provide input nor change the trajectory" of the agent and has only an off-switch. A security team that wants to keep editing or redirecting runs wants L4 for that action, however low its risk.

Rating an action on five dimensions

Dave Chismon of the UK NCSC proposes a way to estimate how risky a defensive action is, with five dimensions each rated 0 to 4 (21 September 2026). The end points of each scale:

UK NCSC, One does not simply defend agentically, dimensions and levels as published, read 19 Nov 2026.
Dimension0 means4 means
PotencyAI provides explainable advice to a humanExecutes code or makes direct system or runtime changes
ScopeSingle systemEnterprise-wide, fleet or shared platform
CriticalityKnown not critical; not business relevantKnown critical system or service
Rollout confidenceAudit mode, a proper twin, or strong evidence from historical logsNo failover and no or limited tests; weak or anecdotal validation
RecoverabilityNone needed because there is no state changeManual reversal, irreversible, or recovery depends on many teams or systems

The NCSC gives the scales and no rule for turning five numbers into a level. This page adds one, stated before any rating: add the five ratings. A total of 0 to 8 makes the action eligible for L5 after evidence; 9 to 14 keeps it at L4; 15 to 20 means the agent drafts and a person performs the action (L1 or L2). Day one depends on the band. An action totaling 0 to 14 starts at L4, because the NCSC's advice is to begin with low-potency tasks that "advise a human" and to prefer systems that are easy to recover. An action totaling 15 to 20 starts at L1 or L2 and stays there. The summing rule and its bands are this site's own: neither the NCSC nor the paper validates them, and they have not been tested against incident data. Use them to make ratings comparable, and adjust the bands against your own incident history.

Eight actions, rated

The estate assumed here: a known set of 60 repositories and their containers, some supporting critical services, with CI and tests in place. The first four actions are the ones Aikido's CVE Exploitability Analysis lets an admin set to "Fully Automated" or "Human Approval": downgrade, upgrade, snooze and ignore (Aikido help center). The last four are fix and response actions. The ratings are this site's judgments for that estate; a different estate gives different numbers.

Ratings use the NCSC scales; the total and bands are this site's rule. The proxy action is the stopgap described in the AI agent guardrails guide, read 19 Nov 2026.
ActionPotencyScopeCriticalityRolloutRecoverTotalLevel it can reach
Upgrade a finding's severity312118L5 after evidence
Snooze a finding to a date312219L4
Downgrade a finding's severity312219L4
Ignore a finding as not exploitable312219L4
Open a pull request on one non-critical service301217L5 after evidence
Merge that pull request to the main branch401229L4 (the agent prepares the merge and a named person merges)
Reject Brotli requests at the shared reverse proxy4343216L1 or L2
Deploy a fix across the production fleet4343317L1 or L2

The result matches the intuition behind the numbers. Upgrading can be wrong without hiding a threat, since an upgrade only adds work. Snooze, downgrade and ignore can each leave an exploitable finding out of sight (a snoozed finding stays hidden until its date, which this rating does not bound), so rollout confidence is rated 2 for all three: before the action, correctness can be tested only against replayed history. Potency is 3 for these four finding-state changes, one step under the NCSC's 4 for direct system or runtime changes, because they alter a record in the scanner or ticket system and not code or a running system; that reading of the scale is this site's. Merge is the point where code starts to run, so potency is 4. L4 for merge means the agent prepares the merge and a named person merges, as set in AI agent guardrails, where merge_pull_request is withheld from the agent's tools. No evidence moves merge to L5: the rating says only that the action suits a one-step sign-off. The proxy rule and the fleet deploy touch shared systems that nobody can fully test, and they stay with a person.

What moves a level up or down

Evidence for moving an observer-eligible action to L5, as example values for this team: 50 consecutive proposals approved without edits across at least 14 days, and a reviewed sample of 10 more with no wrong calls. The counts come from the measurement log.

Pull the level back to L4 on any of four events: a model, prompt or tool change until the rerun passes the gate in AI agent evals; one false clear found in the sample; a new data source; or a rise in the revert rate. One catch from Aikido's page: changing an action from Fully Automated to Human Approval "does not undo actions the agent already took", so a demotion needs a review of everything done since the last sample.

Each change of level leaves one record, kept with the agent's run logs (what to keep). A promotion without a record is a level nobody can defend later.

LEVEL CHANGE RECORD Action: ____ (one of the rated actions; merge is never promoted to L5) Change: L4 to L5 / L5 to L4 / L4 to L1 or L2 Date: ____ Decided by (name) and stand-in: ____ For a promotion: Window: ____ to ____ (at least 14 days) Proposals approved without edits in a row: ____ (example value: 50) Sample reviewed: ____ (example value: 10) Wrong calls: ____ (must be 0) NCSC ratings now: potency __ scope __ criticality __ rollout __ recoverability __ total __ (0 to 8) Model, prompt and tool versions the evidence was gathered on: ____ Sample cadence after promotion: ____ Who can set it back to L4: ____ For a demotion: Trigger (model/prompt/tool change, false clear, new data source, revert-rate rise): ____ Actions taken since the last clean sample: ____ Reviewed by: ____ Wrong items: ____ Rerun passed on: ____ Level restored on: ____

Download the template: .docx PDF CC BY 4.0

Levels can also depend on the case. Wiz triggers remediation automatically when its Green Agent reaches a high-confidence decision and routes lower-confidence decisions to a developer in Slack for approval (Wiz). The limits that go with each level are in AI agent guardrails.

Sources

  1. Feng, McDonald, Zhang, Levels of Autonomy for AI Agents, arXiv 2506.12469 v2, read 19 Nov 2026
  2. UK NCSC, One does not simply defend agentically (Dave Chismon, 21 September 2026), read 19 Nov 2026
  3. Aikido, CVE Exploitability Analysis (help center), read 19 Nov 2026
  4. Wiz, Introducing Wiz agents, read 19 Nov 2026

Last reviewed 19 Nov 2026