Content by Authorised Territory (52)

Authorised Territory demonstrates how to build domain-specific AI agent evaluators in .NET using Microsoft Agent Framework connected to a local Ollama model, then run automated checks against the agent’s responses to validate both content and output structure.

Authorised Territory demonstrates how to build an AI agent with the .NET Microsoft Agent Framework using a local Ollama model, then evaluate the agent locally with built-in checks to confirm response quality and that required tools were actually invoked.

Authorised Territory shows how to use Git worktrees in the Visual Studio 2026 August update to pause half-finished work without stashing, by creating a separate working directory tied to a new branch while keeping current changes intact.

Authorised Territory demonstrates how to build a multi-agent AI code review workflow in .NET using Microsoft Agent Framework, coordinating specialist security, performance, and architecture reviewers via background agents. The setup runs fully locally with Ollama and adds OpenTelemetry tracing so you can see what each agent is doing during the review.

Authorised Territory demonstrates how to build a .NET console app that repeatedly runs an AI agent until a loop evaluator confirms the agent’s tool output matches an expected condition, using Microsoft Agent Framework components like LoopAgent and DelegateLoopEvaluator.

Authorised Territory demonstrates how to build a .NET agent that generates an answer, has a second model judge it against criteria, and retries automatically until it passes or hits an iteration limit, using Microsoft Agent Framework with local models running in Ollama.

Authorised Territory demonstrates integrating the GitHub Copilot SDK with the .NET Microsoft Agent Framework, using Ollama to run models locally as part of an agent-style workflow.

Authorised Territory demonstrates how to configure GitHub Copilot in Visual Studio 2026 (18.9.0), focusing on adding Ollama-backed local models and tuning the model “thinking effort” setting to control how much reasoning the model applies during responses.

Authorised Territory demonstrates how to use the .NET GitHub Copilot SDK with Ollama running locally, focusing on a practical developer workflow for wiring Copilot-style capabilities to a local model runtime.

Authorised Territory demonstrates a .NET MCP server pattern where a tool call starts a background task and returns a task handle instead of an immediate result, while a .NET client polls the server every second until the final output is available.

Authorised Territory demonstrates how a .NET MCP server can expose a skill as a resource, and how an AI agent client can use that skill to answer a question, using a locally running LLM via Ollama.

Authorised Territory demonstrates a .NET AI agent setup where an agent is allowed to rename a file inside a confined folder using the .NET Agent Framework harness, with a local Ollama-hosted LLM (gpt-oss) driving the agent’s decisions.

Authorised Territory demonstrates how to add sampling to a .NET Model Context Protocol (MCP) server so an MCP tool can call back into a client’s locally running LLM (via Ollama) using a chat client.

Authorised Territory demonstrates how to add server-side logging to a .NET MCP server and surface those log messages in a .NET console client when the client invokes a tool.

Authorised Territory demonstrates how to add console telemetry to a .NET AI agent harness by wiring up a trace provider and emitting traces using OpenTelemetry, with a local Ollama model (gpt-oss) used as the LLM runtime.

Authorised Territory demonstrates how a .NET AI agent running in a harness can request human approval before executing a tool, using a locally hosted LLM via Ollama.

Authorised Territory demonstrates how to build a .NET agent harness that lets an AI agent read a local text file, using the .NET Agent Framework and the Microsoft.Agents.AI.Harness NuGet package with a locally running LLM in Ollama.

Authorised Territory demonstrates how to show LLM token usage in a .NET console app built with the .NET Agent Framework while running a local model via Ollama, focusing on making token consumption visible during agent execution.

Authorised Territory demonstrates how to build a web-search tool and wire it into a .NET Agent Framework agent, using SearXNG for search and a locally running LLM via Ollama, with the supporting services hosted in Docker Desktop.

Authorised Territory demonstrates how to expose a .NET Azure Function as an MCP tool, using Visual Studio 2026 to create an Azure Functions project with an McpToolTrigger and then validating the tool with MCP Inspector.

Authorised Territory demonstrates how to use an AI-powered feature search experience in Visual Studio 2022 (17.14.35) to quickly find IDE functionality without manually browsing menus and settings.

Authorised Territory demonstrates how to create reusable prompt files and use them inside Visual Studio 2022 with GitHub Copilot, focusing on a practical workflow for keeping prompts consistent across coding tasks.

Authorised Territory demonstrates how to expose a .NET AI agent through an OpenAI-compatible HTTP endpoint using the Chat Completions API protocol, built with an ASP.NET Core Empty project in Visual Studio 2026 and tested via an HTTP request file, with the agent running against a local Ollama model (gpt-oss).

Authorised Territory demonstrates how to govern a .NET Model Context Protocol (MCP) server by writing a YAML policy that prevents a specific tool from being executed, using the Microsoft.AgentGovernance.Extensions.ModelContextProtocol NuGet package.

Authorised Territory demonstrates how to build a .NET Model Context Protocol (MCP) server over HTTP that scans for unsafe tools on startup, using the Microsoft.AgentGovernance.Extensions.ModelContextProtocol NuGet package, and pairs it with a simple .NET console client that connects to the server.

Authorised Territory demonstrates a .NET tutorial that builds an AG-UI protocol server and a Blazor client, hosting an AI agent locally with Ollama. The client sends prompts to the server and receives the model output as a streamed response.

Authorised Territory demonstrates how to use the Plan agent in Visual Studio 2026 with GitHub Copilot, focusing on an AI-assisted workflow that starts from an existing solution and uses the agent to plan work before making code changes.

Authorised Territory demonstrates how to configure Visual Studio 2026 to use a locally running LLM via Ollama inside GitHub Copilot Chat, using the gpt-oss model as the example.

Authorised Territory demonstrates how to return JSON data from a resource command in .NET Aspire 13.3.0 by wiring up a Minimal API project to Aspire orchestration and invoking its endpoints via HTTP commands from the Aspire dashboard.

Authorised Territory demonstrates a .NET console app that performs interactive natural-language search over a vector store, returning the most relevant document chunks. The video also covers ingesting PDF documents using Ollama, SQL Server, Docker Desktop, and a MarkItDown MCP server as part of the ingestion pipeline.

Authorised Territory demonstrates how to extend a .NET data ingestion pipeline by adding summary and keyword enrichers, then wiring up console logging to show how the enrichers work together with a chat client using a locally hosted LLM via Ollama.

Authorised Territory demonstrates a .NET data ingestion pipeline that converts a PDF to Markdown via the MarkItDown MCP server, generates embeddings with a local Ollama model, and stores those embeddings in SQL Server 2025 running in Docker Desktop.

Authorised Territory demonstrates how to build an end-to-end durable workflow for an AI agent pipeline using the .NET Microsoft Agent Framework, running the Durable Task Scheduler Emulator in Docker Desktop and streaming workflow events in real time, with a local Ollama LLM.

Authorised Territory demonstrates how to add API versioning to a .NET 10 Minimal API using the Asp.Versioning.Http NuGet package, including query-string and URL-segment versioning approaches, plus how to mark an API version as deprecated and test requests using a Visual Studio 2026 .http file.

Authorised Territory demonstrates how to use dependency injection with class-based skills in the .NET Agent Framework, showing how an AgentSkillResource function can resolve services via DI instead of instantiating them with new, while the agent runs a local LLM using Ollama.

Authorised Territory demonstrates how to add a class-based skill to an AI agent built with the .NET Agent Framework, using a locally running LLM via Ollama and building on a previously created starter solution.

Authorised Territory demonstrates how to define a skill in code and attach it to an AI agent built with the .NET Agent Framework, using a locally running LLM via Ollama.

Authorised Territory shows how to configure .NET Aspire 13.2 to use a specific SQL Server Docker image for its SQL Server container, switching from the default SQL Server 2022 image to a SQL Server 2025 image available via Docker Desktop.

Authorised Territory demonstrates how to add a custom AI agent to GitHub Copilot Chat in Visual Studio 2026 (18.5) for a .NET project, using an agent definition markdown file from the awesome-copilot repository.

Authorised Territory demonstrates how to build an MCP server in .NET that returns different supported tools depending on a query parameter, plus a .NET Minimal API client with endpoints to list tools and invoke one of them.