Deployment
5 guides on Deployment.
Getting a .NET agent onto Container Apps, GKE, Azure Functions or a local Aspire stack, and the platform defaults that will cut your longest requests in half without telling you.
Run Your Whole AI Agent Stack Locally with Aspire (Ollama + Qdrant + Traces)
Wire an LLM, a vector database and your API into one F5 with Aspire — no docker-compose, no API keys during development, and OpenTelemetry traces of every model call for free.
Hosted Agents in Foundry Agent Service: A .NET Developer's Guide
Hosted agents in Foundry Agent Service are GA: per-session sandboxes, scale-to-zero, and a simple path to deploy Microsoft Agent Framework agents from .NET.
Serverless AI: Deploy an OpenAI Endpoint with Azure Functions
Host an AI endpoint that scales to zero and costs nothing when idle. Build and deploy a serverless OpenAI-powered API in .NET with Azure Functions.
Deploy a .NET AI Agent to Azure Container Apps
Take a .NET AI agent from your laptop to production on Azure Container Apps: containerize it, wire up secrets with managed identity, deploy, and scale to zero when idle.
Running a .NET AI Agent on Google Kubernetes Engine (GKE)
Deploy a .NET AI agent to GKE the production way: containerize, authenticate with Workload Identity instead of keys, expose it through an ingress, and autoscale on load.