| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.
You must be logged in to block users.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseI am a Principal Research Software Engineer at Microsoft working on Generative AI and Agents. I am the author of Designing Multi-Agent Systems. I have worked on a number of projects including Microsoft Agent Framework (core contributor to Microsoft's agent platform merging AutoGen and Semantic Kernel), AutoGen (toolkits for building multi-agent applications, 52K+ GitHub stars), AutoGen Studio (a no-code interface for building multi-agent workflows, 634K+ downloads), LIDA (a library for automated data visualization using AI agents), and HandTrack.js (a library for real-time hand tracking in the browser using TensorFlow.js).
I wrote Designing Multi-Agent Systems (DMAS), drawing on my experience as a core developer of AutoGen. DMAS is a first-principles guide across 15 chapters: it starts with foundations (what makes a task suitable for agents, a taxonomy of orchestration patterns from deterministic workflows to autonomous coordination, and UX principles for delegation design), then walks you through building a complete agent framework from scratch in Python (picoagents) — implementing the agent loop, tool systems, computer use agents, workflow graphs with checkpointing, autonomous orchestration, and integrating agents into web applications. The final sections cover what it takes to make these systems production-ready: evaluation using trajectories, optimization against common failure modes, distributed agent protocols (MCP, A2A), responsible AI considerations, and end-to-end applications including a software engineering agent.
Digital PDF | Amazon | Code
Building LLM-Enabled Multi Agent Applications from Scratch
Automatic Generation of Visualizations and Infographics using Large Language Models
A library for prototyping realtime hand detection (bounding box), directly in the browser.
Building a Real-time Hand-Detector using Neural Networks (SSD) on Tensorflow
| Back | FazBrowse Home | New Git URL |