Skip to main content

Agent Capabilities

k8s-autopilot operates as a multi-domain deep agent system — a Supervisor routes your requests to four specialized coordinators, each managing its own team of sub-agents. Every sub-agent connects to a dedicated MCP server via Just-In-Time (JIT) connections, keeping resource usage minimal while supporting dozens of complex workflows.


Architecture at a Glance


Domain Quick Reference

DomainCoordinatorSub-AgentsMCP ServersWhat it Does
📦 Helm Operatorhelm-operator-coordinator7 agentsHelm MCP, GitHub MCPChart generation pipeline, live Helm operations, GitHub persistence
🔄 App Operatorapp-operator-coordinator3 agentsArgoCD, Argo Rollouts, Traefik MCPGitOps, progressive delivery, edge routing
☸️ K8s Operatork8s-operator-coordinator1 agentKubernetes MCPCluster ops, pod debugging, scaling, RBAC inspection
🔭 Observabilityobservability-coordinator2 agentsPrometheus, Alertmanager MCPPromQL queries, exporter lifecycle, alert triage, silence management

Sub-Agent Reference

Every sub-agent follows a consistent pattern: Classify → Discover → Plan → Execute → Verify. State-modifying operations are always gated by Human-in-the-Loop approval.

DomainSub-AgentMCP ServerConnectionHITL Gated
Helmhelm-plannerCompiled SubgraphNo
Helmhelm-skill-builderStatic DictNo
Helmhelm-generatorStatic DictNo
Helmhelm-validatorStatic DictNo
Helmhelm-updaterStatic DictNo
Helmhelm-operationhelm_mcp_serverJIT MCP
Helmgithub-agentgithub_mcpJIT MCPNo
Appargocd-onboarderargocd_mcp_serverJIT MCP
Appargo-rollouts-onboarderargo_rollout_mcp_serverJIT MCP
Apptraefik-edge-routertraefik_mcp_serverJIT MCP
K8sk8s-cluster-opskubernetes_mcp_serverJIT MCP
Observabilityprometheus-operatorprometheus-mcp-serverJIT MCP
Observabilityalertmanager-operatoralertmanager-mcp-serverJIT MCP

Cross-Domain Handoff

When a coordinator determines that a request belongs to a different domain, it emits a structured handoff signal. The Supervisor detects this, extracts context, and re-routes to the correct coordinator with a [CROSS-DOMAIN] prefix — ensuring the receiving coordinator inherits all prior findings without the user repeating themselves.

Example flow:

  1. User asks the Observability operator about checkout service alerts → discovers 5 critical alerts
  2. Observability operator defers pod inspection to K8s operator
  3. Supervisor auto-routes: [CROSS-DOMAIN] Source: observability. Prior findings: 5 critical alerts for checkout. User Request: Check pod status
  4. K8s operator receives full context and executes immediately

What's Next?

Dive into each domain to see the full capabilities, sub-agent details, and workflow examples:

  • 📦 Helm Operator — Chart generation, validation, live operations, and GitHub commits
  • 🔄 App Operator — ArgoCD GitOps, Argo Rollouts progressive delivery, and Traefik edge routing
  • ☸️ K8s Operator — Cluster operations, pod debugging, scaling, and multi-cluster context switching
  • 🔭 Observability — Prometheus monitoring, PromQL queries, Alertmanager triage, and silence lifecycle