Peter's Articles

A real debugging story where Claude Code found a race condition in minutes that would have taken a developer half a day. The exact prompts and process.

Build analytics that respect user privacy while still giving you the data you need. No cookies, no PII, no dark patterns.

Use large context windows to grok unfamiliar repositories in hours, not weeks. Practical patterns for AI-assisted codebase exploration.

A first-person account of building a full-stack application with AI in 3 days instead of 60. What worked, what failed, and the real multiplier.

Terminal tricks for running parallel Claude Code sessions across worktrees, projects, and tasks without losing context or sanity.

Why CLI-first beats MCP-only for AI tool design. Build tools that work everywhere, not just inside a specific AI framework.

What actually changes after 30 days of AI-first development. The surprises, the struggles, and the permanent shifts in how you write code.

Protect user data in AI-powered applications with privacy-first logging patterns. PII redaction, consent-aware logs, and audit trails.

What to do when Claude Pro limits cap out. A practical guide to running local models as fallback without losing your workflow.

When does AI-written content cross the line from helpful to harmful? A honest look at quality, authenticity, and the slop problem.

Create universal build watchers that feed real-time context to AI agents. Faster feedback loops, fewer broken builds, happier AI.

The psychology behind 'one more prompt' and how to set healthy boundaries with AI coding tools. Recognize the signs before burnout hits.