Claude Code for Maintainable Software: Lessons from 4 Production Projects
See Also
The Sub-Agent Revolution: How Claude Code's Specialized Workflows Dramatically Increase Software Engineering Quality
Been reviewing some data from complex API development projects lately. Honestly, the traditional approach to AI-assisted development is pretty broken. We're asking general-purpose models to context-switch between domains like API design, contract testing, and security validation. The cognitive overhead alone kills productivity.
The Line Anthropic Didn't Quite Draw
Anthropic's new $100 Agent SDK credit is a free upgrade for plugin-heavy Claude Code users and a real rate-limit cut for anyone living in Zed, Conductor, or claude -p pipelines. The cost math, the cache_control traps, and the principle gap between the line Anthropic drew and the line they said they drew.
The Human in the Loop: When AI Orchestrates and You Execute
A tempo run revelation about the profound inversion of human-AI collaboration: what happens when you're not overseeing the algorithm, but executing its instructions? A personal journey through virtual coaching that illuminates a broader shift in how we work with intelligent systems.
More Articles
