·
AI DevTools
AI Apparatus: An Open Marketplace for AI Agent Skills and MCP Servers
Introducing ai-apparatus, a fork-friendly marketplace for sharing IDE skills and MCP servers across Cursor, Claude, VS Code, and other AI coding agents.
Blog
Technical articles on cloud architecture, DevOps, Kubernetes, and platform engineering.
·
AI LLM
Running Local LLMs Without Guardrails: Understanding AI Workloads Before Building Safety Patterns
Lessons from running Qwen, Gemma, and GLM models on local NVIDIA 3080 GPUs with opencode and aider — understanding costs, risks, and how to design guardrails for enterprise use cases.
·
AI Strategy
Building an AI Center of Excellence
Team structure, responsibilities, and success metrics for an organizational AI Center of Excellence.
·
AI Security
Building a Secure AI Agent Container for Production Workloads
A workflow-based container architecture for running AI agents in production clusters with strict sandboxing, no external tool access, and VPC-bounded outputs.
·
AI Platform Engineering
From POC to Production with AI: Avoiding Common Pitfalls
Common pitfalls when scaling AI experiments into production workflows and how to avoid them.
·
AI Strategy
AI Readiness Assessment Framework
How to evaluate if an organization is ready for AI adoption across infrastructure, skills, and culture dimensions.
·
AI Compliance
Compliance Considerations for AI Coding Assistants
SOC2, HIPAA, and PCI implications when code and data flow through AI coding assistants.
·
AI Governance
AI Governance Playbook for Organizations
Policies for acceptable use, data handling, model selection, and vendor management in enterprise AI adoption.
·
AI Security
AI Security Posture for Enterprises
RBAC for AI agents, data governance, audit trails, and prompt logging for enterprise AI adoption.
·
AI Cloud
When to Self-Host LLMs vs. Use APIs
Decision framework for choosing between self-hosted models and API-based services based on volume, latency, privacy, and cost.
·
AI Observability
AI Observability: What to Monitor in Production AI Systems
Key metrics for AI systems - latency, token usage, quality signals, cost per task, and drift detection.
·
FinOps AI
FinOps for AI/ML Workloads: Mastering Cost Management in the Age of Generative AI
Inference economics, token-based billing, and cost attribution by team and project for AI workloads.
·
AI MCP
MCP Server Patterns for Enterprise
How Model Context Protocol changes agent architectures and what platform teams need to provide.
·
Kubernetes AI
GPU-Aware Kubernetes for Inference Workloads
Scheduling, quotas, and capacity planning when teams run local inference models on Kubernetes.
·
Envoy Go
Dynamic Routing in Envoy with a Custom Go Filter: A Practical Guide
How to enable dynamic route selection in Envoy after modifying headers in a Go filter
·
AI Platform Engineering
AI Golden Paths for Engineering Teams
How to build standardized, secure workflows for AI tool adoption with scoped access, sandboxes, and approval gates.
·
Kubernetes Security
Securing Kubernetes Access: A VPN-Integrated Solution for Public Endpoints
A robust Azure-based network architecture to secure Kubernetes public endpoints by enforcing VPN traversal, centralizing security, and enhancing auditability.
·
Networking Azure
Point-to-Site Internet Breakout through Azure Virtual WAN
Learn how to implement secure internet breakout for remote workers using Azure Virtual WAN.
·
Finops Cloud
FinOps and Kubecost: Navigating Cloud Cost Optimization in Complex Kubernetes Environments
A practical guide to cloud cost optimization in Kubernetes using FinOps principles and Kubecost.
·
MLOps AWS
Building a Robust MLOps Pipeline with AWS SageMaker and Terraform
A comprehensive guide to building a scalable, automated MLOps pipeline using AWS SageMaker and Terraform, covering architecture, CI/CD, and infrastructure as code best practices.