Break a kind cluster on purpose, then watch an Observe agent

Kprompt v0.5 ships an optional Observe agent that continuously watches Kubernetes clusters for failures, correlates incidents, and gates notifications via Slack or webhook, with Autopilot remaining propose-only. The kprompt-examples repository provides a fixture set with seven failure scenarios (CrashLoop, ImagePull, OOM, stalled rollout, unbound PVC, failing CronJob, missing Redis hostname) to demo the agent offline in heuristic mode without spending LLM tokens. The agent never applies, patches, or deletes by default, and Autopilot proposals require explicit approval.

One command from kprompt-examples: kind up, seven failure scenarios, verify they actually broke, then run the Observe agent offline in heuristic mode — $0, no silent auto-heal. Originally published at https://kprompt.ai/blog/observe-agent-kind-demo. v0.5 shipped the optional Observe agent https://kprompt.ai/docs/agent : always-on watch → correlated Incident → gated Slack/webhook, with Autopilot still propose-only. The missing piece for a live walkthrough was a payments namespace that actually misbehaves — not a slide claiming CrashLoopBackOff. kprompt-examples https://github.com/kprompt/kprompt-examples is that fixture set. Break the cluster on purpose, then watch the agent react without spending an LLM token. Needs Docker, kind, kubectl, and kprompt with the agent subcommand. Heuristic mode — no API key, no spend. DEMO SECONDS=60 stretches the agent window for recordings. git clone https://github.com/kprompt/kprompt-examples.git cd kprompt-examples make walkthrough up → break-all → verify → agent-full ~45s Or step by step when you want to film each failure: make up make break SCENARIO=01-crashloop make verify kprompt agent run -n payments \ --emit-initial --analyze --fetch-logs --health --heuristic \ --memory --patterns --autopilot-propose --emit-initial matters: a live watch stays quiet until new Pod/Event traffic. Already-broken workloads may not re-emit until the next BackOff . Emitting current state first makes demos and CI deterministic. Seven scenarios in one namespace, with a healthy baseline so the health score has something Ready to weigh against: | Scenario | Rough signal | |---|---| | CrashLoop | Restarting container / BackOff | | ImagePull | ImagePullBackOff / ErrImagePull | | OOM | OOMKilled / Exit 137 | | Stalled rollout | Progress deadline / unavailable replicas | | Unbound PVC | Pending Pod waiting on volume | | Failing CronJob | Job failures / backoff | | Missing Redis hostname | DNS / connection errors to a stub Service name | Expect: web stays Ready --autopilot-propose : a propose-only rollback suggestion on the stalled checkout rollout Applied stays That last point is the product claim: Observe never applies, patches, or deletes by default ADR-0013 https://github.com/kprompt/kprompt-architecture/blob/main/decisions/ADR-0013-in-cluster-agent.md . Autopilot emits PlanResult-shaped proposals ADR-0015 https://github.com/kprompt/kprompt-architecture/blob/main/decisions/ADR-0015-autopilot-mode.md ; apply stays gated. | Surface | Job | |---|---| | Laptop CLI | Reactive: NL → PlanResult → approve → apply | | Observe agent | Always-on: watch → Incident → severity/confidence gate → notify | | Autopilot | Opt-in propose-only; apply needs policy + explicit approve | K8sGPT-style tools are great at on-demand scan → explain. Observe is a different job: continuous watch with threaded alerts from live Events/Pods. Do not expect fleet-scanner or multi-agent-framework parity — we ship one kprompt-native pipeline. brew install kprompt/tap/kprompt or curl -fsSL https://kprompt.ai/install | bash Try: kprompt.ai https://kprompt.ai · GitHub https://github.com/kprompt/kprompt · kprompt-examples https://github.com/kprompt/kprompt-examples Muhtalip