Kobi
- Kobi Copilot — assisted incident resolution
- kubectl operations, Helm and MCP via agent
Kobi Copilot is Kobi's assisted mode, already working in your cluster: it investigates the incident with real context (events, logs, metrics), proposes the diagnosis and executes actions under your supervision. Every action is audited — who, what and why. It doesn't replace your judgment; it saves you the slow part of the investigation. The agent adds kubectl operations, visibility into your Helm releases and a read-only MCP server.
Autopilot
Autonomous remediation debuts as an open beta on every Cloud plan: you enable it per organization, define the time window it can act in and the mode (suggest-only or execute). Destructive actions require human approval by platform policy, and its usage is metered separately against the same plan credit pool Kobi draws from. Anything awaiting your approval goes to a queue, and every intervention leaves an automatic postmortem.
Security
- Insights Engine — 24 rules with memory
24 rules that evaluate reliability and configuration from minute one, without writing a single one: missing probes, resource limits, single replicas, unpinned images. Findings feed Kobi, so the copilot already knows the weak spots when an incident hits. Each finding is an episode with its evidence and history: if it comes back it counts as recurring, and bursts group what broke together from one cause. With Slack, Discord or email configured, it alerts you when one fires.
Lifecycle
- Cloud costs on OpenCost, rightsizing in money
Pulled forward from stage 02: the Cost tab appears on every cluster once OpenCost data flows, without building your own FinOps stack. Monthly run-rate, idle cost, breakdown by namespace, workload and node, and money-priced rightsizing recommendations from your real consumption — with three connection modes in the wizard.
Fleet
- Per-cluster dashboards with metric history
- Topology and traffic map
Every cluster has its dashboard: on top, a summary that answers whether anything is on fire; below, the detail, with live metrics and their history from the agent, Metrics Server or your own Prometheus. The topology draws how your resources relate, and the traffic map, which pods talk to each other and to which external destinations.