A working log on building AI systems that survive production — RAG, tool-using agents, and honest evals. By Chirag Singhal.https://ai-blog.oriz.in/enwhyiswhen@gmail.com (Chirag Singhal)whyiswhen@gmail.com (Chirag Singhal)https://ai-blog.oriz.in/blog/evaluating-llm-outputs/https://ai-blog.oriz.in/blog/evaluating-llm-outputs/Vibes are not a metric. A practical framework for measuring whether your LLM feature is good — grounded in test sets, rubrics, and the honest limits of LLM-as-judge.Tue, 11 Aug 2026 00:00:00 GMTEvalsLLM-as-JudgeMetricsTestingBenchmarkswhyiswhen@gmail.com (Chirag Singhal)https://ai-blog.oriz.in/blog/mcp-real-tools-for-llms/https://ai-blog.oriz.in/blog/mcp-real-tools-for-llms/The Model Context Protocol turns an LLM from a text generator into something that can read your files, call your APIs, and act. Here is what it is and how to build a server that does not misbehave.Sat, 08 Aug 2026 00:00:00 GMTSystemsMCPAgentsToolsLLMProtocolwhyiswhen@gmail.com (Chirag Singhal)https://ai-blog.oriz.in/blog/rag-pipelines-that-work/https://ai-blog.oriz.in/blog/rag-pipelines-that-work/Most RAG demos fall apart on real corpora. Here is the retrieval stack that survives messy documents, ambiguous queries, and users who paste in nonsense.Wed, 05 Aug 2026 00:00:00 GMTTue, 11 Aug 2026 00:00:00 GMTRetrievalRAGEmbeddingsVector SearchRerankingwhyiswhen@gmail.com (Chirag Singhal)