Stop Building Agent Teams. Start Writing Loops.
Three things I bookmarked weeks apart turned out to be one argument: the unit of AI work is the loop, not the prompt, and not the org chart.
Three things I bookmarked weeks apart turned out to be one argument: the unit of AI work is the loop, not the prompt, and not the org chart.
Anthropic splits Claude into two credit pools on June 15. If you run automated pipelines, here's what to do before your workflows break.
Where vibe coding is going. Predictions on always-on agents, Mythos-class models, design tools, enterprise adoption. Grounded in what we've seen, not hype.
Build a real React Native + Expo mobile app with claude code. Setup, navigation, API integration, deployment to TestFlight and Play Store. Real workflow.
Build claude code custom agents in .claude/agents/. Define personality, tools, constraints. Real examples for security review, docs, and test writing.
Honest analysis of vibe coding careers. Job posting data, salary trends, the rise of AI-native developer roles, and what skills survive the shift.
Run claude code in GitHub Actions for PR review, test generation, doc updates, and dependency audits. Complete YAML examples and honest limits.
How product managers use vibe coding to prototype features, validate ideas, and build internal tools. Real PM workflows, real examples, real limits.
What agentic engineering means. The L0-L5 spectrum from vibe coding to full agentic. Skills, hooks, sub-agents, and the new toolkit.