10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It

QCon San Francisco 2024

Session AI/ML

10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It

Tuesday Nov 19 / 03:55PM PST, Seacliff ABC

Abstract

Multi-agent systems – a setup where multiple agents (generative AI models with access to tools) collaborate to solve complex tasks – are an emerging paradigm for building applications. Tools and frameworks like AutoGen make the development of multi-agent workflows more readily accessible to developers.

However, transitioning from experimentation to the development of reliable, production-ready systems remains challenging and somewhat unclear. As teams embrace and experiment with multi-agent systems, an increasingly important first step is to understand when and why this paradigm might fail. This talk highlights 10 common reasons these systems often fail based on early user feedback and the author’s work as a core maintainer of the AutoGen open-source Python framework (>1 million downloads, > 300 active contributors, > 18k users on Discord).

Topics

AI/ML Autonomous Agents AutoGen
76% senior dev or higher
1:11 speaker ratio
60+ practitioners

QCon San Francisco 2024 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.

Share

From the same track

Tuesday 19 November

10:35 Ballroom BC Session Scaling Large Language Model Serving Infrastructure at Meta Ye (Charlotte) Qi Senior Staff Engineer @Meta 11:45 Ballroom BC Session Generative AI GenAI for Productivity Mandy Gu Senior Software Development Manager @Wealthsimple 13:35 Pacific DEKJ Session LLMOps Navigating LLM Deployment: Tips, Tricks, and Techniques Meryem Arik Co-Founder and CEO @Doubleword (Previously TitanML), Recognized as a Technology Leader in Forbes 30 Under 30, Recovering Physicist 14:45 Seacliff ABC Session AI/ML Search: from Linear to Multiverse Faye Zhang Staff Software Engineer @Pinterest, Tech Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Large Distributed System 15:55 Seacliff ABC Session AI/ML 10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It Victor Dibia Principal Research Software Engineer @Microsoft Research, Core Contributor to AutoGen, Author of "Multi-Agent Systems with AutoGen" book. Previously @Cloudera, @IBMResearch 17:05 Ballroom BC Session Machine Learning A Framework for Building Micro Metrics for LLM System Evaluation Denys Linkov Head of ML @Voiceflow, LinkedIn Learning Instructor, ML Advisor and Instructor, Previously @LinkedIn