» Tag
testing
87 postsSentinel: Open-Source QA Agent Reads Your Code Before Testing
Sentinel is an open-source QA agent that analyzes and tests code. It identified critical business flows in a hotel management system.
Crabbox: Isolated Cloud Sandboxes for Parallel Coding Agents
Crabbox offers isolated cloud sandboxes for parallel coding agents, streamlining software development.
Build a Prompt-Injection Regression Fixture for CodeQL 2.26.0
GitHub's CodeQL 2.26.0 adds AI prompt-injection detection. Learn the importance of building regression tests.
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.comPrompt A/B Testing: A Scientific Method to Enhance AI Response Quality
Prompt A/B testing offers a measurable process to enhance AI response quality.
I Gave an AI Agent an Impossible Target to See If It Would Cheat
Explore the process of an AI agent working toward a target and its engineering significance.
Importance of Running Tests in CLAUDE.md and How Hooks Help
Hooks in CLAUDE.md provide a critical mechanism to ensure tests are always run. Explore how these mechanisms function in this article.
Preventing Regressions in Voice Agents with Testing Processes
Methods to incorporate audio recordings into the testing process to maintain voice agent performance.
Testing an AI Product Without Burning Credit: A Playwright Approach
Zephyr Cloud explains how it tests an AI course product built on The AI Platform by intercepting model calls while keeping the real UI and flow intact.
Contract-Testing API Emails in GitHub Actions Pipelines
A practical guide to why email tests break in CI and how to contract-test API-triggered emails in GitHub Actions using run-scoped inboxes.
Why Your LLM-as-Judge Gate Flips Between Runs
Same code, same input, different LLM judge score: why CI gates flap between runs, and how temperature, model pinning, k-sampling and quantization fix it.