#testing

A negative result, its root cause, and the feature it produced. My last post introduced ctxfold —...

I already had a resume download gate — email required, signed link, 15-minute expiry, presigned S3...

Disclosure: I maintain Tura. A coding agent often spends a separate model turn on each part of a...

Release-over-release, a fixed regression battery caught one clean change: raw-JSON output now arrives fence-wrapped despite a 'no markdown' instruction. 99%→71% on JSON archetypes; GPT and Gemini flat the same window.

AI tools can take a product from an empty repository to a convincing demo quickly. That is useful,...

Happy paths should be automated, and that part isn't up for debate. A suite that runs the same core...

Table of Contents Introduction 1. Integrating Playwright with Allure for Rich Test...

Part 4 of Retrieval-Augmented Self-Recall. Code: RE-call. Part 3: the honesty guards. A standard...

I wrote a cleanup routine that matched processes by command line with a wildcard pattern. It reported...

OpenAI has released GPT-Red, a tool that automates prompt-injection testing against AI agents, per The New Stack. The framing is straightforward: once agents take real actions on real systems, manual red-teaming stops being enough.

Disclosure: I work with SEELE AI. This article discusses an internal AI-assisted Godot prototype and...

The moment we realized our staging environment was broken It was 3 PM on a Thursday, and our team...