Designing a general-purpose LLM agent is easier than you think. From picking the perfect model to defining memory strategies, take your first step in creating a versatile agent that adapts to your needs. Check out Maya Murad's step-by-step guide now. #LLM #AIAgent

Build AI Agents Fast with Bee Agent Framework from IBM Research. A new Open Source framework for building scalable and typesafe agent flows. TS tutorial below 👇. IBM Research youtu.be/AsYQVlBC6Mo

How to Build a General-Purpose LLM Agent by Maya Murad in Towards Data Science towardsdatascience.com/build-a-genera… #HwWvW

Testing no-code AI agent builder iambee.ai from Maya Murad and IBM Research

🚀 Introducing BeeAI: an IBM Open Source platform designed to make working with AI Agents simpler, more flexible, and more powerful. Whether you're building your own agents or leveraging existing ones, BeeAI helps you discover, run, and compose AI agents across any framework

🚀 New AutoGen release python-v0.5.4 is live — and it's packed with new features and upgrades! ✨ AgentTool & TeamTool — build multi-agent patterns using tool calls. 🛡️ Azure AI Agent adapter — now available as an Extension. 🐳 DockerJupyterCodeExecutor — sandbox your Jupyter

Changing my model's tool calling interface from JSON to YAML had surprising side effects. Entropy collapse is one of the biggest issues with GRPO. I've learned that small changes to one's environment can have massive impacts on performance. Surprisingly, changing from JSON to

Magentic-UI, new from Microsoft Research, is an open-source research prototype of a human-centered AI agent, designed to work with people to complete complex, web-based tasks in real time over a web browser. msft.it/6013SjYgN

🚀 Introducing Magentic-UI — an experimental human-centered web agent from Microsoft Research . It automates your web tasks while keeping you in control 🧠🤝—through co-planning, co-tasking, action guards, and plan learning. 🔓 Fully open-source. We can't wait for you to try it. 🔗

Computer use + Human-in-the-loop + Open-source 🔥

1K on Magentic-UI ⭐️ Thank you! 🙏 star-history.com/#microsoft/mag… github.com/microsoft/mage… #starhistory #GitHub #OpenSource via Star History

✨ Human-in-the-loop, by design. Magentic-UI introduces four core HCI features to make human–agent collaboration more transparent, controllable, and adaptive: 🧑‍🤝‍🧑 Co-Planning 🤝 Co-Tasking 🛡️ Action Guards 🧠 Plan Learning Let’s dive into each 👇

👀New Magentic-UI tutorial by Maya Murad Learn how to make the most of MAGUI's features and automate complex tasks.

11/ 👀New Magentic-UI tutorial by Maya Murad  Learn how to make the most of MAGUI's features and automate complex tasks. AutoGen  x.com/pyautogen/stat…

My recent talk on challenges in developing human-centered agents is now available online! It provides an HCI perspective of our learning from developing AutoGen youtube.com/watch?v=O5jSX8…

🚀 Introducing MCP Agents in Magentic-UI! Spin up custom agents that wrap one (or many) MCP tools, and let the Orchestrator pick the best agent for every step of the plan. Check out the demo below to see them in action 👇 #MCP #MagenticUI #AIagents

How do we design and evaluate human-agent interaction? Our report on Magentic-UI details key interaction-patterns including co-planning and co-tasking that could enable effective interaction at low cost for users. Report link: aka.ms/magentic-ui-re…

Interested in the technical details behind Magentic-UI? Our report is now available on arXiv: arxiv.org/abs/2507.22358

MCP is an exciting start to future agentic ecosystems but is it enough? The current MCP ecosystem is vulnerable to tool interference. We opensource MCP reviewer as a tool to help. microsoft.com/en-us/research…

x.com/i/article/1974…