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
| Domain | Coordinator | Sub-Agents | MCP Servers | What it Does |
|---|---|---|---|---|
| 📦 Helm Operator | helm-operator-coordinator | 7 agents | Helm MCP, GitHub MCP | Chart generation pipeline, live Helm operations, GitHub persistence |
| 🔄 App Operator | app-operator-coordinator | 3 agents | ArgoCD, Argo Rollouts, Traefik MCP | GitOps, progressive delivery, edge routing |
| ☸️ K8s Operator | k8s-operator-coordinator | 1 agent | Kubernetes MCP | Cluster ops, pod debugging, scaling, RBAC inspection |
| 🔭 Observability | observability-coordinator | 2 agents | Prometheus, Alertmanager MCP | PromQL 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.
| Domain | Sub-Agent | MCP Server | Connection | HITL Gated |
|---|---|---|---|---|
| Helm | helm-planner | — | Compiled Subgraph | No |
| Helm | helm-skill-builder | — | Static Dict | No |
| Helm | helm-generator | — | Static Dict | No |
| Helm | helm-validator | — | Static Dict | No |
| Helm | helm-updater | — | Static Dict | No |
| Helm | helm-operation | helm_mcp_server | JIT MCP | ✅ |
| Helm | github-agent | github_mcp | JIT MCP | No |
| App | argocd-onboarder | argocd_mcp_server | JIT MCP | ✅ |
| App | argo-rollouts-onboarder | argo_rollout_mcp_server | JIT MCP | ✅ |
| App | traefik-edge-router | traefik_mcp_server | JIT MCP | ✅ |
| K8s | k8s-cluster-ops | kubernetes_mcp_server | JIT MCP | ✅ |
| Observability | prometheus-operator | prometheus-mcp-server | JIT MCP | ✅ |
| Observability | alertmanager-operator | alertmanager-mcp-server | JIT 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:
- User asks the Observability operator about checkout service alerts → discovers 5 critical alerts
- Observability operator defers pod inspection to K8s operator
- Supervisor auto-routes:
[CROSS-DOMAIN] Source: observability. Prior findings: 5 critical alerts for checkout. User Request: Check pod status - 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