llm-as-judge | Amir Teymoori

Fine-tuning Gemma 4 E4B pipeline diagram for English to Swedish novel translation with Claude Opus 4.7 as evaluator.

Fine-Tune Gemma 4 E4B for Swedish Translation

Fine-tuning works best when the task is narrow. You do not need a small open-weight model to beat Claude Opus 4.7 at...

LLM MODELS, PROVIDERS AND TRAINING

LLM-as-judge eval pipeline diagram for customer support AI agents showing user message, agent tools, trace, judge scores, and release gate.

LLM-as-Judge Evals for Support AI Agents

Customer support is one of the best use cases for AI agents. It's also one of the easiest places to ship a...

MLOPS, EVALUATION AND OBSERVABILITY