What a real AI-assisted PR looks like
PR
Ai
Build an eval harness for 184 AI agent prompts with promptfoo
How to build an LLM-as-judge eval system that scores AI agent prompts on quality, identity, and safety.
Prompting isn't engineering, it's storytelling
The best prompts don’t give instructions. They set a scene the model can reason inside.
He spent two years letting cars drive him. Now he's back on horses.
A man spent two years letting cars drive him around. He’s back on horses. 865 engineers debated whether that means the cars are broken.
Managing LLM context in a real application
How Claudriel manages LLM context in production: conversation trimming, turn budgets, model fallback, prompt caching, and per-turn token telemetry.
Vibe coding isn't the problem. Your workflow is.
The critics of vibe coding aren’t wrong about the symptoms — they’re wrong about the cause.
Building an Ojibwe Crossword Puzzle for Minoo
How Minoo’s crossword game teaches Anishinaabemowin through daily puzzles, Elder-authored clues, and a three-layer learning design.
Publishing a PHP monorepo to Packagist with splitsh-lite
How waaseyaa went from a monorepo with 43 path-repository subpackages to individually installable Composer packages on Packagist using splitsh-lite.
AI-native PHP: the waaseyaa AI packages
What ai-schema, ai-agent, ai-pipeline, and ai-vector enable in a PHP framework designed for AI from the ground up, and an honest look at what’s built versus what’s planned.
Shkoda: a campfire word game for learning Ojibwe
The first game on minoo.live teaches Ojibwe vocabulary through a campfire that burns as long as you keep guessing right.