Rojan Dahal — लेखहरूउत्पादनस्तरको एमएल बनाउने बारेमा — एलएलएमभन्दा अघिका तहहरू, राउटिङ निर्णयहरू, र वास्तविक प्रणालीहरूका फिल्ड नोटहरू।https://rojandahal.com/ne-NPFour layers before the LLM: the gatekeeper pattern (in English)https://rojandahal.com/writing/the-gatekeeper-pattern/https://rojandahal.com/writing/the-gatekeeper-pattern/How a stack of cheap classifiers cuts a document-IDP bill by an order of magnitude without ever waking the model.Tue, 12 May 2026 00:00:00 GMTThe cheapest token is the one you don't send (in English)https://rojandahal.com/writing/the-cheapest-token/https://rojandahal.com/writing/the-cheapest-token/Routing, retrieval, and a small set of decisions about which questions a model should never see.Tue, 21 Apr 2026 00:00:00 GMTProduction ML is mostly not ML (in English)https://rojandahal.com/writing/production-ml-is-mostly-not-ml/https://rojandahal.com/writing/production-ml-is-mostly-not-ml/A field report from a three-agent IDP pipeline: what breaks first, what's worth automating, and where humans still earn their seat.Mon, 30 Mar 2026 00:00:00 GMT