Writing
Notes from building software, and AI, for real.
Case studies, architecture and field notes by Anuj Gupta: the problem, the design, the math and what breaks in production. No theory without numbers.
Architecture$419$162Call the big model last: a RAG design, layer by layerYour AI assistant just answered "Where is Hall B?" for the 1,500th time. On your most expensive model. A cost-aware design for an event platform: the problem, the fix, the math, and what breaks in production.3 min readField notes80%+4 fixesWhy most AI projects fail, and it is rarely the modelMore than 80% of AI projects fail, twice the rate of normal IT projects. The reason is rarely the model. It is retrieval, latency, cost and trust, and we already know how to engineer all four.3 min readGuideRewrite6 waysIntegrating AI and machine learning into existing .NET applicationsLegacy .NET applications are the quiet engines still powering countless enterprises. You can make them intelligent without rewriting them. Six patterns, a real case and the code.3 min read