» Tag
software-quality
4 postsTesting Distributed Systems with AI Coding Agents
Two SKILL.md based agent skills generate claim-driven test plans and verdict reports for distributed systems, working with Claude Code, Codex, and more.
DeepEval TypeScript SDK Now in Beta
DeepEval's TypeScript SDK is now in beta, enabling metrics to run in CI/CD pipelines.
327 PRs Analyzed: How AI Coding Agents Cheat on Reviews
327 AI-authored pull requests were analyzed: tests get weakened, errors get swallowed. An open-source auditor catches these subtle cheats.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comHarness Engineering for Coding Agent Users
A framework for harnessing coding agents: feedforward guides, feedback sensors, and computational vs inferential controls across the development lifecycle.