The art of simplicity

If you've built anything with the Microsoft Agent Framework (MAF), you'll notice that your tool calls can fill up the context window quite fast. A function that returns a list of 50 orders as JSON easily costs you a few hundred tokens on braces, quotes and repeated field names alone. That cost hits you twice: once on the way into the model as tool output, and again on every subsequent turn where that history gets replayed. That's where TOON (Token-Oriented Object Notation) comes in. Let's explore this. What TOON actually is TOON is a line-oriented, indentation-based encoding of the same data model JSON uses. It borrows YAML's indentation for nested objects and CSV's tabular layout for arrays of uniform objects. The trick is in that last part: if you have a list of objects that all share the same fields, TOON declares the field list once and then just streams the values, row by row, instead of repeating every key for every item. Take a small object like t...

While creating a workflow system with the Microsoft Agents SDK, I encountered the following error message when testing my workflow: System.InvalidOperationException: Cannot use a Workflow that is already owned by another runner or parent workflow. at Microsoft.Agents.AI.Workflows.Workflow.TakeOwnership(...) at InProcessRunnerContext..ctor(...) at InProcessRunner.CreateTopLevelRunner(...) It's cryptic if you haven't seen it before. But once you understand the ownership model, the fix is straightforward. What's actually happening .NET workflow runtimes treat workflow instances as stateful, non-reentrant objects. When a runner picks up a workflow, it takes exclusive ownership of that instance. No other runner — and no parent workflow — is allowed to touch it while that ownership is held. This is by design. Workflows accumulate state as they execute, and allowing two runners to share that state simultaneously would corrupt it. The runtime enforces ow...

Yesterday, I created a minimal .NET project with DevUI and registered a couple of standalone agents. That gets you surprisingly far for interactive testing. But real business scenarios quickly outgrow a single agent: you need data flowing through multiple specialized steps, decisions being made along the way, and a clear picture of the whole pipeline. That's what workflows are for. In this post, we'll build a content review pipeline as a concrete example — a Writer agent drafts a response, a Reviewer agent critiques it, and a deterministic formatting step finalizes the output. All of it visualized in DevUI. Agents vs Workflows — the key distinction The Agent Framework docs put it cleanly: an agent is LLM-driven and dynamic — it decides which tools to call and in what order, based on the conversation. A workflow is a predefined graph of operations, some of which may be AI agents, but the topology is explicit and deterministic . You decide exactly what runs after what. ...

If you've been exploring the Microsoft Agent Framework , you've probably seen the Python DevUI example showcased prominently in the docs. DevUI is a fantastic inner-loop tool — it lets you visually inspect your agents: their messages, reasoning steps, tool calls, and conversation state, all in a browser dashboard while you develop locally. Think of it as Swagger UI, but for AI agents. The problem? When I went looking for a .NET / C# equivalent , I couldn't find one. The official Microsoft Learn page for DevUI samples simply said: "DevUI samples for C# are coming soon." — Not great when you're trying to ship. So I built one. This post walks through a complete, working .NET Core example using Microsoft Agent Framework 1.0, with DevUI wired up and ready to go. What is DevUI? DevUI is a lightweight developer dashboard shipped as part of the Microsoft Agent Framework. It is not intended for production — it's a local dev tool, similar in spirit to what...