At Sun Microsystems we spent about an hour a week on code review, and shipped Solaris. The industry has spent twenty years staring at diffs instead of designs, and AI just made the diffs nearly free.
Blog
An open letter on LinkedIn wants older programmers to pair with younger ones to learn AI. I started college in 1982 with COBOL on punchcards. Ten platform shifts later, adapting is the one skill that never needed replacing.
The AI in WPLoadTester 7 writes what it learns into a deterministic expert system, so the more you use the AI, the less it runs. Why prompt-file memory is a design flaw, and what I built instead.
A three-pillar workflow for agentic coding: spec-driven planning, jurisdiction-scoped multi-model review, and hand-curated tests with golden datasets. Updated with the 2025-2026 research on staffing review panels and keeping writes in one agent's hands.
How I modernized a 25-year old software suite with 550,000+ lines of hand-written Java code as a sole developer using Claude Code and multi-LLM spec-driven development. Java 6 to 11, Eclipse RCP 3.6 to 4.19, Ant to Maven, and a new interactive React reporting module that runs in the cloud and embedded in the desktop app. 1,294 commits, 791 automated tests.
How I built two agentic AI systems for a 25-year-old load testing application: one that configures test cases through natural language conversation, and another that agentically investigates load test data and generates professional performance analysis reports.
How I built a natural-language reporting system for personal finance using AI, reverse-engineering the Copilot Money API, and creating a Chrome plugin with MCP server capabilities.