Category
AI Engineering
Evaluation, workflows, and practical AI-assisted software engineering.
Latest
Evaluate AI Coding Agents at the Patch, Not the Promise
A practical system for evaluating AI coding-agent changes with task contracts, fail-to-pass tests, pass-to-pass regressions, and diff review.
Don't Code the First Mock — What Claude Code /design Actually Changes
Claude Code's /design research preview (≈2026-08-17) adds editable UI artboards before implementation. Treat it as a review gate — not 'design system solved.'
Small PRs for the Agent Era — GitHub Stacked PRs and Copilot Stacked Sessions
GitHub’s 2026-07-30 public preview of stacked PRs plus Copilot stacked sessions: make agent output reviewable layers with gh-stack, not one mega-diff.
Copilot Code Review GA: Skills + MCP Turn PR Review into an Agent Team
GitHub made agent skills and MCP generally available for Copilot code review on 29 Jul 2026. Learn what changed, why skills beat a monolithic prompt, and how this maps to specialized agent teams.