CDCoding Dropletsincodingdroplets.com·10h ago · 12 min readSecuring LLM Tool Calling in ASP.NET Core: Least Privilege for AI AgentsTool calling is the moment an LLM stops being a text generator and starts touching your systems. Securing LLM tool calling in ASP.NET Core is therefore not really an AI problem - it is an authorizatio00
CDCoding Dropletsincodingdroplets.com·3d ago · 10 min readHow to Chunk Documents for RAG in .NET: A Real-World WalkthroughRetrieval-Augmented Generation lives or dies on one unglamorous step, and it is not the model or the vector database. It is chunking. When you get chunking documents for RAG in .NET wrong, the model r10
CDCoding Dropletsincodingdroplets.com·4d ago · 11 min readETags and Conditional Requests in ASP.NET Core: When to Use Them and HowMost teams reach for caching the moment an API gets slow, wire up Redis or output caching, and move on. But there is an older, lighter mechanism built into HTTP itself that solves two problems at once20
CDCoding Dropletsincodingdroplets.com·6d ago · 11 min readMigrating from Semantic Kernel to Microsoft Agent Framework in .NET: A Step-by-Step GuideIf you shipped an AI agent in .NET over the last two years, there is a good chance it runs on Semantic Kernel. That was the right call at the time. But with Microsoft Agent Framework reaching GA in Ap00
CDCoding Dropletsincodingdroplets.com·Jul 22 · 13 min readResilient LLM Calls in .NET: Retries, Timeouts, and Fallbacks Done RightThe first time an AI feature I shipped went down in production, nothing in my code had changed. The model provider had a bad afternoon: a wave of 429 Too Many Requests, then a stretch of 503s, and eve00