Part 3 of Build your own claw and harness with Microsoft Agent Framework. In Part 2 our personal finance assistant learned to work with your data safely: it reads your portfolio, asks before it trades, and remembers what matters across sessions. It's useful - but everything it knows is baked into one prompt, it does its work one step at a time, ...

Part 2 of Build your own claw and agent harness with Microsoft Agent Framework. In Part 1 we stood up a harness and gave our personal finance assistant its first abilities: a custom tool, web search, and planning. It can talk about the markets - but it can't yet touch your data, and nothing stops it from taking a sensitive action on a whim. T...

Part 1 of Build your own claw and agent harness with Microsoft Agent Framework. In the overview we said a "claw" is really just an agent harness: a loop around a model, wired up with tools, planning, memory, and more. In this first post we stand up that loop and give our personal finance assistant its first three abilities: plan...

What does it take to build your own "claw" - a capable, CLI-style agent that can plan, use tools, remember things, and safely act on your behalf? Coding agents and assistants like these can feel like magic, but underneath they are an agent harness: a loop around a language model wired up with tools, planning, memory, approvals, and observability. ...

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 ba...

We’re excited to announce the release of Microsoft.Extensions.VectorData.Abstractions, a foundational library providing exchange types and abstractions for vector stores when working with vector data in AI-powered applications. This release is the result of a close collaboration between the Semantic Kernel and .NET teams, combining expertise in AI ...

Today we’re thrilled to announce support for Hybrid search with Semantic Kernel Vector Stores for .NET. What is Hybrid Search? Hybrid search performs two parallel searches on a vector database.  The union of the results of these two searches are then returned to callers with a combined rank, based on the rankings from each of the constituent sear...

We are thrilled to announce the General Availability (GA) of our Memory packages for .NET, Java, and Python! The Semantic Kernel team and our partners have been working hard to allow you to quickly connect to vector stores and make it easy for you to do embeddings and data retrieval between stores. Transforming Data Management with Vector Stores...