Blog topic
Architecture essays: intent compilers, PlanResult, context engineering, and fail-closed design for cluster AI. 16 articles.
Muhtalip Dede7 min readHow to compose kprompt with kagent without collapsing the layers: kagent hosts Agents-as-CRDs via MCPServer / RemoteMCPServer; kprompt ships read/plan-only MCP tools that return a typed PlanResult and never auto-apply. Validated against kagent quickstart + first MCP tool docs.
Muhtalip Dede5 min readkagent (CNCF Sandbox / Solo.io) is a Kubernetes-native agent runtime — Agents as CRDs, MCP, A2A, mesh. kprompt is an AI Runtime for cluster ops: PlanResult → approve, plus Observe notify. Is kprompt a kagent alternative? Only for the ops job — decision guide.
Muhtalip Dede4 min readagentgateway (Linux Foundation) is an AI-native proxy for LLM, MCP, and A2A traffic on Gateway API. kprompt is an AI Runtime for cluster ops: PlanResult → approve, plus Observe notify. Is kprompt an agentgateway alternative? Only for the ops job — decision guide.
Muhtalip Dede4 min readThree Kubernetes AI layers that share vocabulary and confuse buyers: AI Runtime (kprompt PlanResult ops), AI Gateway (agentgateway LLM/MCP/A2A data plane), Agent Platform (kagent Agents-as-CRDs). One hub, honest jobs, deep links.
Muhtalip Dede3 min readWhy unsupervised auto-remediation is not the destination. Observe by default, Autopilot propose-only, reality anchors, and investigate → plan → approve → verify as the load-bearing loop — not a fleet of agents that apply because the model sounded sure.
Muhtalip Dede2 min readRead-only service topology as typed nodes/edges — Ingress, PVC, Secret/ConfigMap names, reverse impact — not a Secret CMDB or chat “who depends on what” folklore. Honest degraded when OTel/mesh are missing.
Muhtalip Dede3 min readNamespace dependency facts that bias Observe without becoming root-cause proof. Local or in-cluster stores — never cloud dumps as fake authority — with AG-034 confidence caps.
Muhtalip Dede3 min readIncident chronology as typed EvidenceRef[], not chat folklore. Events, rollout revisions, and HPA in one Investigation artifact — with honest degraded[] when Prom/OTel/mesh are missing.
Muhtalip Dede4 min readChat is a line; ops is a gated graph. Fan-out where edges are real, independent verify (not same-session soft-agree), PlanResult → approve → verify — without becoming a free-form agent fleet.
Muhtalip Dede4 min readMcKinsey’s ARK is an Agentic Runtime for Kubernetes — CRDs to run agent apps on the cluster. kprompt is an AI Runtime that reasons about the cluster under plan → approve. Same word “runtime,” different jobs. Decision guide.
Muhtalip Dede4 min readWhy kprompt’s category is an AI Runtime for Kubernetes: observe, reason, plan, approve, execute, learn — not a ChatGPT wrapper, chatbot, or silent auto-healer. Honest shipped vs building.
Muhtalip Dede4 min readFor Kubernetes AI, clever prompts lose to curated context: live cluster facts, tool detection, local history, and a typed PlanResult. Why the next leap is what you feed the model — not how you word the sentence.
Muhtalip Dede3 min readAI SRE across kubeconfig contexts: single-context default, explicit read fan-out, per-context mutate approval, aliases, and why we refuse silent fleet --approve or uploading cluster credentials.
Muhtalip Dede2 min readPolicy is code, not LLM vibes. How kprompt’s safety engine hard-denies wipe-class intents, scores risk, forces approval, and why fail-closed is the load-bearing wall of AI SRE.
Muhtalip Dede3 min readPlanResult is the IR of AI SRE: one typed document for humans and CI. Why JSON, what applied means vs verify, how blastRadius attaches, what never gets stored, and how investigate/why must extend the same artifact.
Muhtalip Dede3 min readKubernetes deserves a compiler, not a chatbot. How kprompt turns natural language into Intent → Actions → PlanResult, why Go owns planning and safety, and why the IR must stay reviewable for AI SRE.