Blog
Articles about development, AI and open source.
Claude Platform on AWS is GA: same-day parity, AWS IAM, AWS billing
Anthropic announced GA of Claude Platform on AWS. Full Claude API through IAM, invoice in the AWS console, identical pricing. Skills, Managed Agents, Advisor pattern and MCP connector – all the same day, no weeks of waiting like with Bedrock. What it actually unlocks for a dev and the team.
Meta released the Meta Ads MCP server: campaigns can now be run by Claude and ChatGPT
Meta Ads AI Connectors in open beta. Official MCP server and CLI, 29 tools with read+write access to your ad account. Claude and ChatGPT can pause campaigns, adjust budgets, and write ad copy. What it does, what it doesn't, and why it's the biggest Meta ecosystem story this year.
Expo × STRV Hackathon: how we shipped a loyalty app for PFERDA in 7 hours
One day in Karlín, three people, Expo + Supabase + NativeWind. What you can ship in 7 hours for a non-profit that employs people with disabilities — and what I'd do differently next time.
Anthropic Admitted a Month of Claude Code Degradation — Here's What Actually Happened
From March 4 to April 20, 2026, three concurrent degradation modes ran in Claude Code. Anthropic frames them as bugs — but two of the three were deliberate decisions.
Per-task agent context will be the next karpathy-kind trend
My bet: by spring 2027, isolated context per sub-task gets a folk name and jumps from engineering blogs into pitch decks. Why the Lütke–Karpathy–Anthropic pattern keeps repeating.
Claude Code and .env files — the certification answer that isn't enough
The certification question has one correct answer out of four — a PreToolUse hook on Read and Grep. In production, your `.env` still leaks through Bash. A working hook that closes it.
Spec-driven development: writing specs that AI agents actually ship
Agents deliver sloppy code because they get sloppy briefs. A practical recipe for turning a Jira ticket into binary acceptance criteria, three-tier boundaries and self-verification.
Brain dump over writing — how I dictate feature specs into Claude Code
Whisprflow replaced my spec writing. I dictate a messy brain dump into Claude Code, the agent turns it into a structured spec and asks whether it understood me. Ten minutes instead of an hour — and a better output.
CSS Grid Lanes — masonry in CSS without a single line of JS
Pinterest layout used to mean Masonry.js or CSS columns with broken reading order. display: grid-lanes changes that — native masonry with a two-line @supports fallback.
Claude Code hooks — the complete guide to guardrails that actually work
PreToolUse, PostToolUse, Notification. What Claude Code hooks are, how to configure them in settings.json, and the three patterns I use in every production repo.
Cursor vs Claude Code — an honest comparison after shipping both to production
Not a spec sheet. A direct comparison of Cursor and Claude Code based on daily production use — editor integration, agentic workflow, hooks, skills, cost and when to pick each.
git push --force the future — how I presented at Yolk Studio
A talk on AI agents in software development. CLAUDE.md, hooks, skills, Skillsmith, git worktrees and real-world case studies — everything I showed at Yolk Studio.
Claude Agent SDK — building production agents without reinventing the loop
The Claude Agent SDK gives you the same primitives Claude Code uses — tools, hooks, subagents, permissions. A practical walkthrough of shipping one to production.
Claude Profile Manager: Multiple Accounts, One Machine
Personal subscription, company team, Vertex AI setup — and Claude Code stores everything in one directory. I built a CLI tool that gives each account its own isolated environment.
Skillsmith: Write AI Skills Once, Export Everywhere
Your team uses Claude, Cursor, and Copilot — and you're maintaining the same coding standards in five places. I built an open-source tool that fixes this with one command.
Why Your Website Should Serve Markdown to AI Agents
AI agents waste tokens parsing your navbars and cookie banners. I built an open-source library called next-markdown-mirror that fixes this — and it costs $0.