Yoke Agent — Blog https://yoke-agent.digital/blog/ Essays on RAG and agent evaluation, grid-search methodology, and self-hosted AI quality workflows. en-US Tue, 28 Apr 2026 12:00:00 +0000 Grid-search for RAG: an old technique, retrofitted for a new problem https://yoke-agent.digital/blog/grid-search-for-rag/ https://yoke-agent.digital/blog/grid-search-for-rag/ Tue, 28 Apr 2026 12:00:00 +0000 Grid search is a 60-year-old hyperparameter-tuning technique. Applying it to RAG required rethinking what a hyperparameter even is — here is how Yoke Agent rebuilt it for chunking, embeddings, retrievers and advanced strategies. How to evaluate a RAG pipeline end-to-end in 2026 https://yoke-agent.digital/blog/evaluate-rag-pipeline-2026/ https://yoke-agent.digital/blog/evaluate-rag-pipeline-2026/ Tue, 21 Apr 2026 12:00:00 +0000 A pillar guide to evaluating retrieval-augmented generation pipelines: datasets, RAGAS metrics, grid-search axes, improvement reports and production monitoring. DeepEval vs Yoke Agent: honest comparison https://yoke-agent.digital/blog/deepeval-vs-yoke-agent/ https://yoke-agent.digital/blog/deepeval-vs-yoke-agent/ Tue, 14 Apr 2026 12:00:00 +0000 Where DeepEval wins, where Yoke Agent wins, and why most serious teams end up using both. The 14 agent evaluation metrics Yoke ships (and why) https://yoke-agent.digital/blog/14-agent-evaluation-metrics/ https://yoke-agent.digital/blog/14-agent-evaluation-metrics/ Tue, 07 Apr 2026 12:00:00 +0000 Every G-Eval rubric metric Yoke Agent implements, with definitions, formulas and when to use each one. Benchmarking chunking strategies on a real corpus https://yoke-agent.digital/blog/benchmarking-chunking-strategies/ https://yoke-agent.digital/blog/benchmarking-chunking-strategies/ Tue, 31 Mar 2026 12:00:00 +0000 Grid-searching four chunking strategies against a 500-document technical corpus — the numbers you actually need to pick one. Self-hosted LLM evaluation: a 2026 guide https://yoke-agent.digital/blog/self-hosted-llm-evaluation-2026/ https://yoke-agent.digital/blog/self-hosted-llm-evaluation-2026/ Tue, 24 Mar 2026 12:00:00 +0000 Why self-hosted evaluation matters in 2026, what to demand from the tool, and how to migrate off a SaaS platform. Why notebooks fail for RAG evaluation (and what to do instead) https://yoke-agent.digital/blog/why-notebooks-fail-rag-evaluation/ https://yoke-agent.digital/blog/why-notebooks-fail-rag-evaluation/ Tue, 17 Mar 2026 12:00:00 +0000 Five failure modes of notebook-driven RAG evaluation, and a practical migration path to reproducible grid-search.