Agent Hour
# Multi-Agent
# AI Systems
# Security
Building Multi-Agent Systems // Shrivu Shankar // Agent Hour
As Large Language Models (LLMs) evolve, the challenge shifts from raw capability to structuring them into reliable, scalable systems. Many real-world AI products struggle with robustness, complexity management, and evaluation—especially in enterprise contexts. This talk explores how multi-agent systems can help overcome these obstacles by decomposing large monolithic agents into specialized subagents working together in structured architectures. We’ll cover: - Why enterprises struggle to integrate LLM agents effectively. - How multi-agent architectures (Assembly Line, Call Center, and Manager-Worker) improve scalability, modularity, and reliability. - Practical trade-offs and implementation strategies from real-world applications. (planning to adapt my post https://blog.sshh.io/p/building-multi-agent-systems)
Shrivu Shankar · Feb 19th, 2025
Popular topics
# Interview
# AI Agents
# LLMs
# AI
# Case Study
# Model Serving
# Deployment
# LLM in Production
# Generative AI
# Prosus
# Rungalileo.io
# Machine Learning Engineer
# Machine learning
# FinTech
# Open Source
# Cultural Side
# Scaling
# LinkedIn
# A/B Testing
# Large Language Models
Hassan Sawaf · Feb 19th, 2025
Artificial Intelligence is transforming the way we interact with technology, and Agentic AI—systems that exhibit autonomy, adaptability, and decision-making capabilities—is at the forefront of this revolution. But what does this mean for the Arabic language, one of the richest and most complex languages in the world? As we advance AI-driven agents, ensuring they understand, process, and generate Arabic with the same fluency and nuance as English or other dominant languages is not just a technological challenge but a cultural imperative. In this speech, we will explore how Agentic AI can empower Arabic speakers, enhance accessibility, and preserve the linguistic heritage of over 400 million people while driving innovation across industries. The future of AI is agentic. The future of Arabic in AI depends on how we shape it today. Artificial Intelligence is transforming the way we interact with technology, and Agentic AI—systems that exhibit autonomy, adaptability, and decision-making capabilities—is at the forefront of this revolution. But what does this mean for the Arabic language, one of the richest and most complex languages in the world? As we advance AI-driven agents, ensuring they understand, process, and generate Arabic with the same fluency and nuance as English or other dominant languages is not just a technological challenge but a cultural imperative. In this speech, we will explore how Agentic AI can empower Arabic speakers, enhance accessibility, and preserve the linguistic heritage of over 400 million people while driving innovation across industries. The future of AI is agentic. The future of Arabic in AI depends on how we shape it today.
# Arabic
# Agents
# Linguistics
Patrick Barker · Feb 6th, 2025
R1 > computer? In this talk, we will explore applying the ideas of R1 style RL fine-tuning for computer use
Sarah Wooders · Feb 6th, 2025
We are currently in the midst of a paradigm shift from stateless LLM workflows to stateful LLM agents. Today, developers are responsible for managing state (e.g. message history across sessions) and memory (e.g. with a RAG and a vector DB) themselves. Letta is an agents framework where the agents service is responsible for state and memory management, rather than client-side applications. This dramatically simplifies the experience of building stateful agentic applications, as Letta will use memory management techniques (extending the ideas from MemGPT) to automatically ensure the most relevant information is passed into the LLM context window, and also avoid context overflow errors. In this talk, we’ll cover Letta’s high-level architecture, and also explain the details of state and memory management. We’ll also go over how to use Letta to build stateful, reasoning agents with support for custom tools, secure tool environments, and personalized memory.
Zach Wallace · Jan 24th, 2025
Agents are transforming how we approach problem-solving, automation, and user interaction. In this talk, I will explore the practical applications of agents, focusing on how they can deliver value. We'll discuss when agents are the right tool for the job, scenarios where they are not the right tool for the job, and strategies for deploying them to production with confidence and reliability. Whether you're new to agents or looking to refine your approach, this session offers actionable insights grounded in real-world experience.
# Agents
# real world
# AI agents in production
Nirodya Pussadeniya · Jan 24th, 2025
AI Agents as Neuro-Symbolic Systems: Expanding the Boundaries of Intelligence" The current discourse around AI agents often centers on LLM-based systems with tool-calling capabilities, like REACT agents. While effective, this narrow definition limits the potential of agents to solve complex, real-world problems. In this talk, we explore a broader, more robust perspective—AI agents as neuro-symbolic systems. By combining neural networks' adaptability with the precision of symbolic reasoning, neuro-symbolic architectures bridge traditional AI approaches and modern advancements, enabling scalable and versatile workflows. This expanded definition accommodates not only LLMs but also embedding models, decision trees, and hybrid systems that integrate various modalities of intelligence. We will delve into: 1. The evolution of AI agents and the limitations of current models. 2. The core principles of neuro-symbolic systems and their practical applications. 3. A reimagined framework for building intelligent agents that operate flexibly across diverse tasks. This session aims to redefine the way we think about AI agents, empowering developers and researchers to design systems that are more efficient, resilient, and capable of tackling dynamic challenges. Join us as we explore the future of agentic AI and its transformative potential.
# Agents
# neuro
# symbolic
# neuro-symbolic systems
Vanessa Escande & Demetrios Brinkmann · Jan 9th, 2025
//Abstract
AI has transformed industries, yet its true potential often lies untapped within core business processes. In this session, we’ll explore how AI agents differ from generative AI models, emphasizing their deterministic, hallucination-free approach to problem-solving. We’ll take a live example of an AI Agent in the logistics sector, and will detail the architectural foundations that enable AI agents to reason effectively, execute chain-of-thought workflows, and integrate seamlessly into human teams.
We’ll discuss how these agents confidently navigate complex, multimodal tasks, extracting structured insights from unstructured data, and leveraging dynamic workflows for maximum flexibility. With customizable confidence thresholds, statefulness to track long-term cases, and advanced document understanding, these agents solve real business challenges, such as processing autonomously claims till resolution, with precision.
Through a live case study, we’ll illustrate the measurable top and bottom-line effects of deploying AI agents—highlighting significant efficiency gains, multilingual capabilities, and safe, scalable applications in mission-critical environments. By showcasing how AI agents mimic human decision-making at unparalleled speed, we’ll inspire senior management to rethink AI’s role in their organizations and harness its full potential for transformative impact.
//Bio
Passionate about connecting deep tech to end-users, Vanessa’s work is at the forefront of AI’s transformative potential. For over a decade, she has been transforming cutting-edge innovations into actionable solutions that drive industry change.
This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Thanks to arcade-ai.com for the support!
Join the next live event at home.mlops.community
# logistics
# europe
# AI Agents
Valdimar Eggertsson · Jan 9th, 2025
//Abstract
Demonstrating agents embedded within websites that utilize real-time audio and structured outputs to dynamically update web pages through conversational interactions.
//Bio
Raised in Reykjavík, living in Berlin. Studied computational and data science, did R&D in NLP and started making LLM apps as soon as GPT4 changed the game.
This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Thanks to arcade-ai.com for the support!
Join the next live event at home.mlops.community
# sales agent
# voice agent
Natan Vidra · Dec 19th, 2024
//Abstract
In this presentation, we will explore how intelligent autonomous multi-agent systems can augment workflows. By leveraging collaborative multi-agent AI systems, people can automate routine tasks and streamline complex processes. We will go over the architecture of building multi-agent systems, talk about how to coordinate teams of AI agents that work together, discuss how to monitor and optimize these systems to be intelligent, and showcase real-world applications that highlight their potential to enhance efficiency.
//Bio
Natan has experience working as a Data Scientist / Software Engineer within Deloitte's Applied Artificial Intelligence division. At Deloitte, Natan collaborated on many AI projects in the domains of Natural Language Processing, Computer Vision and Big Data Analytics. He wrote the Deloitte Prompt Engineering Guide, and led execution for Ready AI, enabling clients to practically go from zero to one on their AI journeys. .
This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents.
Sponsored by Arcade Ai (https://www.arcade-ai.com/)
# Autonomous
# Multi-Agent
# Agents
# AI agents in production
Samuel Colvin · Dec 19th, 2024
//Abstract
In this talk, Samuel will go into more detail on why they built PydanticAI and what problem they're aiming to solve. He'll also cover some of the future enhancements they plan for PydanticAI.
//Bio
Python and Rust engineer. Creator of Pydantic and Pydantic Logfire. Professional pedant.
This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents.
Sponsored by Arcade Ai (https://www.arcade-ai.com/)
# Pydantic
# Agents
# Agent Hour
# AI agents in production
Popular