Build a private local AI chat in C# with Semantic Kernel and Ollama. Add Plugins for time and DB lookups, plus context tips.
Stop Paying for Tokens: Run Semantic Kernel + Ollama Locally in C#
Tag: prompt engineering
Cut LLM API Costs by 40% with TOON in .NET
Trim tokens by 30-60% using TOON in .NET. Get encoder/decoder code, a quick migration plan, and real token benchmarks with OpenAI/Azure.
Semantic Kernel on .NET: Deploy, Observe, Optimize
Deploy Semantic Kernel apps on .NET the right way. Add OpenTelemetry, cut latency and token costs, and ship compliant, resilient LLM services.
Prompt Engineering in C#: Templates and Chains
Learn how to create structured, reusable, and testable prompt templates and chains in C# for smarter AI integration.