Showing category results for Python

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 the new , available for both .NET and Python, your agents can discover and load Agent Skills at runtime, pulling in only the context they need...

We're thrilled to announce that Microsoft Agent Framework has reached Release Candidate status for both .NET and Python. Release Candidate is an important milestone on the road to General Availability — it means the API surface is stable, and all features that we intend to release with version 1.0 are complete. Now is the time to move your Semantic...

Introduction: A New Paradigm for AI Application Development In enterprise AI application development, we often face this dilemma: while cloud-based large language models are powerful, issues such as data privacy, network latency, and cost control make many scenarios difficult to implement. Traditional local small models, although lightweight, lack...

Microsoft Agent Framework now integrates with the Claude Agent SDK, enabling you to build AI agents powered by Claude's full agentic capabilities. This integration brings together the Agent Framework's consistent agent abstraction with Claude's powerful features, including file editing, code execution, function calling, streaming responses, multi-t...

Microsoft Agent Framework now integrates with the GitHub Copilot SDK, enabling you to build AI agents powered by GitHub Copilot. This integration brings together the Agent Framework's consistent agent abstraction with GitHub Copilot's capabilities, including function calling, streaming responses, multi-turn conversations, shell command execution, f...

In the explosive era of Agentic AI, we're not just seeking more powerful models—we're searching for a development experience that lets developers actually get some sleep. When building Agents locally, we've traditionally faced three major challenges: Today, I'll walk you through a classic case from Microsoft Agent Framework Sampl...

The Architectural Imperative: Why Multi-Agent Orchestration is Essential In modern enterprise AI systems, the scope and complexity of real-world business challenges quickly exceed the capabilities of a single, monolithic AI Agent. Facing tasks like end-to-end customer journey management, multi-source data governance, or deep human-in-the-loop revi...

In previous versions of the Semantic Kernel, the encoding of template arguments was performed automatically if the argument type was a . The encoding was not applied for custom types, anonymous types, or collections. With the latest changes, we've introduced stricter rules: if automatic encoding is enabled (the default behavior), an exception wi...

In previous versions of the Semantic Kernel Python, the default fallback authentication mechanism for Azure services like was from the Azure Identity library. This provided a convenient way to authenticate without explicitly passing credentials, especially during development. However, with the latest package version , this fallback is being remov...

Google's Agent-to-Agent (A2A) protocol is designed to enable seamless interoperability among diverse AI agents. Microsoft’s Semantic Kernel (SK), an open-source platform for orchestrating intelligent agent interactions, is now being integrated into the A2A ecosystem. In this blog, we demonstrate how Semantic Kernel agents can easily function as an ...