Microsoft Agent Framework
The latest news from the Microsoft Agent Framework team for developers
Latest posts
Chat History Storage Patterns in Microsoft Agent Framework
When people talk about building AI agents, they usually focus on models, tools, and prompts. In practice, one of the most important architectural decisions is much simpler: where does the conversation history live? Imagine a user asks your agent a complex question, clicks “try again,” explores two different answers in parallel, and then comes back tomorrow expecting the agent to remember everything. Whether that experience is possible depends on the answer to this question. Your choice affects cost, privacy, portability, and the kinds of user experiences you can build. It also determines whether your applic...
CodeAct in Agent Framework: Faster Agents with Fewer Model Turns
Modern AI agents often aren't bottlenecked by model quality, they are bottlenecked by orchestration overhead. When an agent chains together many small tool calls, each step typically requires a new model turn, driving up latency and token usage. With CodeAct support in Agent Framework, agents can collapse those multi-step plans into a single executable code block, cutting end-to-end latency by ~50% and token usage by over 60% in representative workloads, without compromising on safety or isolation. CodeAct ships in the new (alpha) package, which runs the model-generated code in a fresh, locally isolated...
Agent Skills in .NET: Three Ways to Author, One Provider to Run Them
Your agents can now draw on skills authored in three different ways – as files on disk, as inline C# code, or as encapsulated classes – and combine them freely in a single provider. Add built-in script execution support and a human-approval mechanism for script calls, and you have a practical authoring model that fits real-world scenarios: skills that evolve over time, skills owned by different teams, and scripts that need human oversight before they act on your systems. The scenario You're building an HR self-service agent for your company. It starts life with a single file-based skill that walks new hires thr...
Building a Real-Time Multi-Agent UI with AG-UI and Microsoft Agent Framework Workflows
Multi-agent systems demo beautifully. Putting them in front of real users is another story. In early prototypes, a terminal or a basic chat window is enough. But once agents start handing off to each other, pausing for approvals, or asking follow-up questions, those interfaces fall apart. Which agent is active? Why is the system waiting? What's it about to do on the user's behalf? Without answers to those questions, a multi-agent workflow stops feeling like a product and starts feeling opaque. This post shows what a better answer looks like. We'll build a customer support workflow that pairs M...
Microsoft Agent Framework Version 1.0
Today, we're thrilled to announce that Microsoft Agent Framework has reached version 1.0 for both .NET and Python. This is the production-ready release: stable APIs, and a commitment to long-term support. Whether you're building a single assistant or orchestrating a fleet of specialized agents, Agent Framework 1.0 gives you enterprise-grade multi-agent orchestration, multi-provider model support, and cross-runtime interoperability via A2A and MCP. When we introduced Microsoft Agent Framework last October, we set out to unify the enterprise-ready foundations of Semantic Kernel with the innovative orchestrations...
Handling Long-Running Operations with Background Responses
Handling Long-Running Operations with Background Responses AI agents powered by reasoning models can take minutes to work through complex problems — deep research, multi-step analysis, lengthy content generation. In a traditional request-response pattern, that means your client sits idle waiting for a connection that may time out, or worse, fails silently and loses all progress. Background responses in Microsoft Agent Framework let you offload these long-running operations so your application stays responsive and resilient, regardless of how long the agent takes to think. With background responses, you start ...
What’s New in Agent Skills: Code Skills, Script Execution, and Approval for Python
Code-Defined Skills, Script Execution, and Approval for Agent Skills in Python When we introduced Agent Skills for Microsoft Agent Framework, you could package domain expertise as file-based skill directories and have agents discover and load them on demand. Now, the Python SDK takes skills further — you can define skills entirely in code, let agents execute scripts bundled with skills, and gate script execution behind human approval. These additions give you more flexibility in how you author skills, more power in what agents can do with them, and more control over when agents are allowed to act. Code-Defined ...
Agent Harness in Agent Framework
Agent harness is the layer where model reasoning connects to real execution: shell and filesystem access, approval flows, and context management across long-running sessions. With Agent Framework, these patterns can now be built consistently in both Python and .NET. In this post, we’ll look at three practical building blocks for production agents: Shell and Filesystem Harness Many agent experiences need to do more than generate text. They need to inspect files, run commands, and work with the surrounding environment in a controlled way. Agent Framework makes it possible to model those capabil...
Give Your Agents Domain Expertise with Agent Skills in Microsoft Agent Framework
You can now equip your Microsoft Agent Framework agents with portable, reusable skill packages that provide domain expertise on demand — without changing a single line of your agent's core instructions. With built-in skills providers for both .NET and Python, your agents can discover and load Agent Skills at runtime, pulling in only the context they need, when they need it. What Are Agent Skills? Agent Skills is a simple, open format for giving agents new capabilities and expertise. At the core of every skill is a file — a markdown document that describes what the skill does and provides step-by-step instr...
