All posts
Muhtalip Dede profile photoMuhtalip Dede · Founder of kprompt2 min read

Stop paging on every kubelet Event: Incidents + confidence gates

Always-on Kubernetes watch only helps if you correlate into Incidents and gate by severity and confidence — not one Slack message per BackOff.

Wiring kubectl get events into Slack feels productive for about a day. Then CrashLoop storms reopen the same fingerprint every few seconds, ImagePull retries spam the channel, and nobody trusts the bot. Always-on watch is only useful if the product artifact is a correlated Incident — not a raw Event dump.

The failure mode: Event → page

  • One message per kubelet Event → thread death under restart storms
  • LLM called on every raw API event → cost and latency spikes with no extra truth
  • No durable “open incident” → you cannot ask why later or mark false positive
  • No severity/confidence gate → low-signal noise trains the team to ignore alerts

Observe pipeline (gated)

kprompt’s optional Observe agent watches Pods/Events (and optional workloads) in one namespace, correlates into durable Incidents, optionally analyzes with your BYOK LLM, then notifies Discord, Slack, or a webhook only after a severity + confidence gate. Default Observe never applies, patches, or deletes.

watch → Incident → gate → notify (laptop smoke)

kprompt agent run -n payments \
  --emit-initial --analyze --fetch-logs --health \
  --min-severity medium --min-confidence 0.7

Levers that cut fatigue

LeverWhat it does
--heuristicZero token spend; deterministic detectors for demos and many day-2 signals
--min-severity / --min-confidenceDefaults medium / 0.7 — raise both to cut noise and LLM burn
Incident batchingOne analysis per evidence fingerprint, not per raw Event
--memory / --patternsNamespace facts + “seen before” bias confidence — never sole proof of root cause
Slack threadsPrefer bot + channel update-in-thread over a new webhook post per pulse

Rough expectation from the ops runbook: busy namespace with LLM on and gate at medium/0.7 → a handful of completions per real incident, not hundreds per hour. If spend spikes, check the gate and whether CrashLoop storms reopen fingerprints.

Memory and patterns are bias, not proof

Namespace memory and pattern learning can boost confidence when a signature looks familiar, and Slack false-positive feedback can dampen repeat noise. They must not invent root cause alone. If Prom, OTel, or GitOps evidence is missing, Observe degrades honestly — it does not fabricate metrics.

Autopilot stays propose-only

Optional --autopilot-propose emits PlanResult-shaped remediations with Applied false. Silent heal is not the goal. Apply remains policy + allowlist + explicit approve under ADR-0015.

Try it without paging anyone

Break kind on purpose, then watch gated Incidents ($0)

git clone https://github.com/kprompt/kprompt-examples.git
cd kprompt-examples
make walkthrough

Heuristic mode needs no API key. For a Slack path, add --slack (or Discord webhook) only after the gate settings match your tolerance. Experimental — prefer kind / non-prod first.

Related posts