KubeBolt docs
ENES GitHub

Kobi

Meet Kobi: one AI, two modes

Kobi is KubeBolt's AI SRE. Kobi Copilot answers when you ask and ships in every edition; Kobi Autopilot acts on its own under your rules on KubeBolt Cloud.

On this page
  1. How Autopilot handles an incident
  2. When does a human sign off in Autopilot?
  3. The rest of the guardrails
  4. Where to go next

Kobi is KubeBolt’s AI SRE — the same character everywhere in the product, working in two modes:

Copilot never changes anything by itself: every fix is a proposal that runs only when you click Execute, under your role, and lands in the audit trail. The difference between the modes is who drives.

Kobi Copilot investigating an incident and proposing a fix you approve.
Kobi Copilot investigating an incident and proposing a fix you approve. KubeBolt 2.1.1

How Autopilot handles an incident

  1. Detect. KubeBolt’s rule-based insights surface problems; they never fix anything. Autopilot opens an incident only for a closed catalog of eight incident classes: OOM kills, crash loops, image pull failures, rollouts past their progress deadline, a missing ConfigMap or Secret, failing readiness probes, failing liveness probes, and an HPA pinned at its maximum. Any other insight stays an insight.
  2. Triage and investigate. Every incident goes through an LLM triage, then an investigation that reads the cluster with Kobi’s read-only tools — and, through a cloud connector, the cloud resources the workload depends on.
  3. Plan. The plan can only use a closed set of typed actions: restart, scale or roll back a Deployment, patch a workload’s resources or probes, patch an HPA — plus a readiness check and an inform-only step that changes nothing. When the investigation’s confidence is below the floor for that incident class, nothing executes: the plan is kept as advice for a person to review.
  4. Execute and verify. The executor runs the plan’s actions and nothing else, then checks that the pods are Ready (180 seconds by default). Only when that check fails does it revert what it changed — in Approve & execute, after asking.
  5. Write the postmortem.

When the cause is outside the cluster — a stopped database, a cloud quota, a firewall rule — no restart or rollback fixes it. The plan names the resource and what its owner has to do, and the incident ends as Needs a human, never as resolved.

When does a human sign off in Autopilot?

That depends on Autopilot’s operating mode — configurable per organization on KubeBolt Cloud. New organizations start in Suggest only.

Operating modeWhat executesHuman sign-off
Suggest onlyNothing — Kobi investigates and proposes; you apply the commands yourselfNot applicable (never executes)
Approve & executeEvery action, after your approvalEvery action waits for it
AutonomousRestarts, HPA and probe patches, low-risk resource patches and a scale of one replica up or down, automaticallyRollbacks, scale-to-zero, larger scale changes and riskier resource patches always wait for it

An approval nobody answers within the approval timeout (5 minutes by default) counts as rejected. Approving or rejecting takes the Editor role.

A resolved incident is “auto-resolved” either way — the incident view marks whether an action paused for a human sign-off, as an attribute, not a different status.

The rest of the guardrails

Beyond the operating mode, Autopilot’s autonomy is bounded by:

The settings, credit pacing and who gets notified are in KubeBolt Cloud; what Autopilot may execute, next to what Copilot and the UI may, is in Actions & Governance.

Where to go next