AWS Agent Squad
In this event, we check out the Open-Source Software (OSS) agent orchestration framework from AWS: Agent Squad.
The Agent Squad framework is a powerful tool for implementing sophisticated AI systems comprising multiple specialized agents. Its primary purpose is to intelligently route user queries to the most appropriate agents while maintaining contextual awareness throughout interactions.
From the High-level architecture flow diagram, multi-agent architectures are governed by a Classifier (read: Router) along agents’ characteristics and conversation histories.
Following an initial input by the user, the Classifier leverages both characteristics and conversation history to decide which agent to select to complete the task. This process operates in a loop until the task is complete.
This is broken down into a sequence of linear steps as follows:
Request initiation
Classification
Agent selection
Request routing
Agent processing
Response generation
Conversation storage
Response delivery
This process ensures that each request is handled by the most appropriate agent while maintaining context across the entire conversation. The classifier has a global view of all agent conversations, while individual agents only have access to their own conversation history.
We are also interested to explore the AWS-specific integrations that AWS Agent Squad allows off-the-shelf; e.g., an “agent” can be any of the following:
LLMs (through Amazon Bedrock or any other cloud-hosted or on-premises LLM)
API calls
AWS Lambda functions
Local processing
Amazon Lex Bot
Amazon Bedrock Agent
Any other specific task or process
Of course, the OSS framework is a competitor to leading orchestration frameworks today like LangChain, OpenAI Agents SDK, AutoGen, LlamaIndex, CrewAI, PydanticAI, smolagent, and others! It’s our goal as always to get to the bottom of why you’d choose Agent Squad over any other framework. In the age of CSP-focused agent frameworks (e.g., Google’s ADK, AWS Agent Squd) we’re also curious to discuss the importance of ease-of-integration when it comes to choosing the best framework for your next agent implementation. We’ll be joined by AWS Head of Generative AI & ML, Milan McGraw, as well as by Solution Architect Aravind Subramanian, to get to the bottom of it!
🤓 Who should attend
Engineers & data scientists building agents with OSS frameworks or on AWS.
AI engineering teams looking to align their agent framework for the most performant and safe models.
AI Engineering leaders who are interested in learning about the state-of-the-art in how CSPs are working with their clients to encourage the use of their own OSS frameworks.
Speaker Bios
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.