Practice

6 designs that reimagine how we interact with software

Introducing Brand Studio: The creative production platform powered by your brand

We’re excited to introduce Brand Studio by Stability AI, the end-to-end creative production platform powered by your brand.…

How to make remarkable videos with Seedance 2.0

If you have never tried a video model before, now is the time.…

The TL;DR on MCP: Why context matters and how to put it to work

How AI leaders are borrowing from the design playbook

How to design agentic tools for work

Workflow lab: Expanding the canvas with Figma MCP

How to prompt Grok Imagine Video 1.5

Grok Imagine Video 1.5 is the most exciting video model release from xAI. You can generate realistic video with synchronized audio in a single pass, capable of …

Enterprise-managed plugins in VS Code in public preview

Last month we launched a public preview with Copilot CLI that allows enterprise administrators the ability to configure and distribute plugins to GitHub Copilot…

MCP Prompts: Building Workflow Automation

A practical guide to building workflow automation with MCP prompts and resource templates, demonstrated through a meal planning example.…

Exploring the Future of MCP Transports

The Transport Working Group's plan to evolve MCP beyond Streamable HTTP for enterprise-scale remote deployments.…

The 2026 MCP Roadmap

The updated Model Context Protocol roadmap for 2026: transport scalability, agent communication, governance maturation, and enterprise readiness, plus guidance …

A2A v1 Is Here: Cross-Platform Agent Communication in Microsoft Agent Framework for .NET

As organizations move from single-agent prototypes to multi-agent production systems, the ability for agents to communicate reliably across platforms and organi…

From Local to Production: Deploy Your Microsoft Agent Framework Agent with Foundry Hosted Agents

Once you have your Microsoft Agent Framework (MAF) agent or workflow happily running locally on your dev machine, it’s time to decide how to deploy your a…

Governance at the Speed of Agents: Microsoft Agent Framework and Agent Governance Toolkit, Better Together

Building powerful AI agents is only half the story, running them safely in production is the real challenge. As customers adopt Microsoft Agent Framework for ag…

Stop prompt injection from hijacking your agent, new security capabilities now released within Agent Framework

Prompt injection is the #1 risk on the OWASP LLM Top 10, and most agents in production today defend against it with one of two heuristics: a defensive system pr…

ICYMI: Inside the Microsoft Agent Framework: How we designed a layered SDK

In case you missed it, the Command Line blog was launched last week and has a great article (by yours truly) about our SDK design philosophy with Microsoft Agen…

Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment

Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth conge…

Identifying Interactions at Scale for LLMs

--> Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial inte…

Notes from inside China's AI labs

Lessons from my trip to talk to most of the leading AI labs in China.…

Building realistic electric transmission grid dataset at scale: a pipeline from open dataset

Microsoft Research is excited to release an open dataset of approximate transmission topology of the U.S. power grid derived from publicly available data. The a…

MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models

MagenticLite is an agentic system for small models that works across the browser and local file system in a single workflow. It combines specialized models and …

Data Formulator 0.7: AI-powered data analytics for enterprise data

Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily bring enterprise data into an AI-ready workspace where user…

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization h…

Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models

Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual con…

MiniPIC: Flexible Position-Independent Caching in <100LOC

Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files. Y…

OR-Action: Multi-Role Video Understanding with Fine-Grained Actions

Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited…

From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews s…

Uncertainty Estimation for Molecular Diffusion Models

Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low qu…

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational o…