8 मिनेट
Long context got cheap. Your prompt didn't.
Million-token windows are table stakes now. The bill didn't disappear — it moved somewhere most pipelines aren't looking.
लेखहरू
लेखहरू
उत्पादनस्तरको एमएल बनाउने बारेमा — एलएलएमभन्दा अघिका चार तहहरू, मोडेलभन्दा माथिको राउटिङ निर्णयहरू, र तीन-एजेन्ट IDP पाइपलाइनबाटका प्रत्यक्ष अनुभवहरू।
2026
8 मिनेट
Four layers before the LLM: the gatekeeper pattern
How a stack of cheap classifiers cuts a document-IDP bill by an order of magnitude without ever waking the model.
6 मिनेट
The cheapest token is the one you don't send
Routing, retrieval, and a small set of decisions about which questions a model should never see.
7 मिनेट
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.