Content by Wes Steyn (6)

Wes Steyn announces the release of the Microsoft Agent Framework Harness, a batteries-included runtime that turns a chat model into a production-ready agent with planning, tool-calling, memory, approvals, web search, and OpenTelemetry built in for both .NET and Python.

Wes Steyn shows how to scale a Microsoft Agent Framework “claw” using the Agent Harness: on-demand skills (including centrally managed Foundry skills via MCP), approval-gated shell access, CodeAct for sandboxed code execution, and concurrent background agents, with runnable samples in both .NET and Python.

Wes Steyn shows how Microsoft Agent Framework’s Agent Harness can safely work with user data by adding file access, human approvals for risky tool calls, and durable memory. The post includes both C# and Python examples, plus runnable samples you can use as a starting point for your own agent.

Wes Steyn shows how to build an “agent harness” (a loop around a model with tools, planning, memory, and web search) using Microsoft Agent Framework. The post walks through creating a chat client with Microsoft AI Foundry, wrapping it into a harness agent, and running it in a console UI with plan/execute modes.

Wes Steyn introduces a hands-on series for building a CLI-style “claw” (a coding agent) using Microsoft Agent Framework, explaining the core harness loop—tools, planning, memory, approvals, and observability—and outlining how the sample evolves from a minimal agent to a production-ready service in .NET and Python.

Wes Steyn breaks down the main chat history storage patterns for AI agents—service-managed vs client-managed—and explains how Microsoft Agent Framework uses AgentSession and pluggable history providers to switch between providers (including Azure OpenAI and Foundry) without rewriting your agent code.