
Kubernetes
How to set resource limits on AI agent pods
Requests decide where an AI agent pod runs and limits cap its use. See how CPU throttling and memory OOM kills treat a runaway agent, and pick a QoS class.
5 min read
Tag
62 posts

Kubernetes
Requests decide where an AI agent pod runs and limits cap its use. See how CPU throttling and memory OOM kills treat a runaway agent, and pick a QoS class.
5 min read

AI
Claude Code documents no budget alert or automatic stop. Contain a runaway agent with spend limits, gateway caps, --max-budget-usd and OpenTelemetry alerts.
5 min read

Kubernetes
A pod stays open for egress until a NetworkPolicy selects it and lists Egress. Start with default deny, allow DNS, then add one rule for each destination.
9 min read

AI
Deny a short list of destructive, secret and network actions in Claude Code, allow the rest, and prompt only for high-risk calls. Managed settings lock it.
6 min read

AI
Showback reports AI coding agent spend by team, and chargeback bills it to the team's budget. Map each tool's spend to a team key before you allocate it.
7 min read

AI
Map each AI agent threat to the control that stops it and the layer that enforces it: coding agent settings, MCP servers, Kubernetes admission and RBAC.
5 min read

Kubernetes
Pod Security Admission sets one of three levels per namespace. Baseline blocks known escalations and restricted adds container hardening. Choose per agent pod.
5 min read

AI
An enterprise MCP security checklist: approve servers by URL or command, pin OAuth scopes, set tool rules, keep a person in the loop and log every call.
6 min read

AI
Map the OWASP LLM Top 10 2026 risks to the agent controls that limit them: tool scope, policy checks outside the model, approval, spend caps and logs.
7 min read

AI
Detect shadow AI in Kubernetes: scan pod images for model servers, probe Ollama's /api/tags and /api/ps, and flag unapproved model API calls in egress logs.
5 min read

AI
Pin Claude Code plugins with enabledPlugins, allowlist marketplace sources with strictKnownMarketplaces, and block sideloaded plugins with managed settings.
6 min read

AI
An AI gateway in front of your API gateway checks agent calls first. Behind it, the API gateway stays the single entry point. Either way, block direct egress.
6 min read