Engineering notes from real projects — production LLM systems, coding agents and computer vision.https://tianliangzhang.com/https://tianliangzhang.com/blog/easyielts-eval-harness/https://tianliangzhang.com/blog/easyielts-eval-harness/My last post claimed a rubric-as-contract makes LLM grading reproducible. This one tests that claim on real production data — and finds the grader is a distribution, the fallback model is +0.34 band more lenient, and top scores drifted almost a full band in three weeks.Thu, 11 Jun 2026 00:00:00 GMTLLMEvalsAI EngineeringEdTechProductionhttps://tianliangzhang.com/blog/act-learner-seed-first/https://tianliangzhang.com/blog/act-learner-seed-first/How ACT Learner serves grounded AI explanations to real users while calling the live model on only a fraction of requests — and why the prompt is the cache key.Tue, 09 Jun 2026 00:00:00 GMTLLMAI EngineeringCachingRAGProductionhttps://tianliangzhang.com/blog/skills-manager-one-library/https://tianliangzhang.com/blog/skills-manager-one-library/Coding agents each store skills in their own folder, their own way. Skills Manager normalises all of them behind one central library — the architecture, and why it's a Rust filesystem program wearing a GUI.Sun, 07 Jun 2026 00:00:00 GMTAI AgentsDeveloper ToolsRustArchitectureOpen Sourcehttps://tianliangzhang.com/blog/easyielts-speech-to-band/https://tianliangzhang.com/blog/easyielts-speech-to-band/IELTS speaking is a subjective exam graded by a human on four criteria. EasyIELTS does it with an LLM — here's everything you have to pin down to make a fuzzy human judgement reproducible, and honest.Fri, 05 Jun 2026 00:00:00 GMTLLMSpeechEdTechPrompt EngineeringProduction