Tag

LLM

This tag covers practical aspects of integrating large language models into .NET and Azure workloads, from managing prompt size and cost to ensuring observability and deployment. Articles discuss how context length directly impacts billing for .NET developers, how ASP.NET Core can expose trace and metric data for LLM apps, and how to use evals as release gates in CI/CD pipelines. Understanding the…

4 articles since Sep 2026

Azure OpenAI .NET .NET CI/CD ASP.NET Core azure ai foundry

Azure AI Foundry Cost Optimization: Caching & KV-Cache Reuse

Learn how to cut LLM spend in Azure AI Foundry with caching, model shrinkage, KV‑Cache batching, and intelligent routing—practical patterns for .NET teams building production RAG apps.

Oct 9, 2026 8 min read

azure ai foundry Cost Optimization Performance Tuning LLM RAG Architecture

Context length cost for .NET developers: Why your prompts are draining the budget

Explore how attention mechanics inflate the context length cost for .NET developers, see real‑world Azure OpenAI pricing, and get production‑ready strategies to keep token spend under control.

Sep 9, 2026 8 min read

LLM .NET Azure OpenAI Prompt Engineering Cost Management

Observability for LLM Apps in ASP.NET Core: Trace First, Metrics

Learn how to instrument, trace, evaluate, and close the feedback loop for large‑language‑model applications built with ASP.NET Core. Real‑world patterns, code, and production tips for Azure OpenAI, Semantic Kernel, and OpenTelemetry.

Sep 8, 2026 8 min read

ASP.NET Core Observability LLM Azure OpenAI OpenTelemetry

Using evals as release gates for LLM changes in .NET CI/CD pipelines

Learn how to embed evaluator‑driven release gates into your .NET CI/CD flow, ensuring LLM updates meet accuracy, safety, and latency standards before they hit production.

Sep 5, 2026 8 min read

LLM .NET CI/CD Azure OpenAI Semantic Kernel Model Evaluation