Hussein Mozannar

Senior Researcher at Microsoft Research AI Frontiers working on AI agents for computer-use applications. His research focuses on building AI systems that assist people in daily life and work, especially through human-AI interaction, post-training, interface design, and web-access agents such as Fara-7B.

MagenticLite Brings Full Agent Workflows to Small Language Models

Microsoft Research is presenting MagenticLite as a full-stack agentic system designed to make small language models usable for multi-step work across a browser and local files. Weili Shi, Harkirat Behl and Hussein Mozannar argue that the capability comes from specializing the stack rather than relying on frontier-scale models: MagenticBrain handles planning, coding and delegation, while Fara 1.5 controls the browser. The release also emphasizes user oversight, with the agent pausing for credentials, approvals or other points where the user needs to take control.

Microsoft ResearchMay 14, 20267 min read