All blog posts
Set up an EKS cluster with Auto Mode enabled using a single eksctl command. Covers how Auto Mode eliminates node group management and when to choose it over traditional managed node groups.
Hands-on verification of AgentCore Runtime's new shell command API. Covers HTTP/2 streaming, in-session file persistence, cross-session microVM isolation, and concurrent execution behavior.
A canonical duplication error triggered a full SEO audit. Missing sitemaps, absent structured data, no OG images for TILs — a record of pitfalls found and fixed on a Next.js App Router site with locale routing.
Unified all skill names to gerund form, added pushy trigger clauses to descriptions, and merged overlapping skills. Centralized quality standards cut maintenance overhead.
Deploy an AG-UI protocol server to Bedrock AgentCore Runtime and stream real-time agent responses via SSE events. Hands-on walkthrough with agentcore CLI Direct Code Deploy.
Applied Anthropic's two official best practice guides to a real skill set, uncovering reserved word violations, naming issues, and missing progressive disclosure. Includes a self-check workflow using a custom analysis skill.
Hands-on verification of Bedrock AgentCore Policy: Cedar-based tool access control via Gateway, natural language policy generation, and default deny behavior validated with real API calls.
Build macOS/Linux dotfiles with XDG compliance, 1Password SSH integration, and a test script. Covers the design decision to use copy-based deployment over symlinks, and how CLAUDE.md enables AI-assisted maintenance.
Turning the AI coding maturity model into practice. A 30-day action plan, review guideline creation, cross-team metrics bootstrapping, and quarterly review cadence.
A 5-level maturity model for coding agent adoption, built on Anthropic and OpenAI frameworks but tailored to software development teams. Assess your current level and identify the highest-impact next step.