2025-09-12 –, Room 2
Agents in Action is a 3-hour hands-on workshop that explores the world of AI agents in a practical way. Participants will learn what agents are, how they make decisions, and how they can work together to solve problems. Starting from the basics of single agents and moving toward multi-agent systems, the session will highlight real examples, design patterns, and frameworks that make agentic AI systems reliable and scalable. Through live demos and interactive discussions, this workshop will help participants see how intelligent agents can move from simple tasks to complex, useful workflows.
This workshop is designed to introduce AI agents in a clear, approachable way. We’ll begin by understanding the basic ideas: what agents are, the different types of agents, and how they differ from general AI systems. Step by step, we’ll build on this foundation:
Single-agent design: how one agent can use tools, keep memory, and take actions.
Multi-agent design: how several agents can coordinate, collaborate, and divide work.
Frameworks and protocols: an overview of popular tools (like CrewAI, LangGraph, etc.) and why standards like the Model Context Protocol (MCP) are important for safe, interoperable systems.
We’ll see live demos including a real time applications of different domains. The session will close with practical tips for evaluating, tracing, and making agent systems trustworthy.
The workshop is open to anyone curious about intelligent agents, no prior technical experience is required. By the end, participants will have a clear picture of how agents work, how to design them, and how to apply them in real-world scenarios.
Workshop Outline (3 Hours)
0:00 – 0:10 | Welcome & Setup
Introductions, technical checks, quick icebreaker.
0:10 – 0:30 | Agents 101
What are agents?
Types of agents.
Agents vs. agentic AI.
0:30 – 0:50 | Patterns & Prompts for Agents
How prompts shape agent behavior.
Simple examples.
0:50 – 1:15 | Single-Agent Design
State, memory, tools.
Designing an agent step by step.
1:15 – 1:45 | Multi-Agent Design
Orchestration & coordination.
Collaboration and specialization.
1:45 – 2:15 | Live Demo
Domain Specific Applications
2:15 – 2:40 | Frameworks Tour
Overview of frameworks
When and why to use each.
2:40 – 2:55 | MCP in Practice + AgentOps
Why MCP matters (interoperability, security).
Evaluations, tracing, and safety with AgentOps.
2:55 – 3:00 | Wrap-Up
Q&A and resource sharing.
- No prior experience with agents is required.
- Familiarity with Python is required.
- Basic curiosity about AI and automation is enough.
- You come, we talk, we share, we learn together.
Intermediate
Kalyan is a Lead Data scientist with a background as a former data science and analytics manager, effectively balancing both academia and industry. He has presented talks at various PyCon's, Data Science and AI conferences, showcasing his expertise. As a community leader, Kalyan currently serves as the one of the Chair for PyConf Hyderabad 2025 and has held the role of Co-chair for PyCon India 2023 and PyConf Hyderabad from 2022 to 2024. In addition to these leadership positions, he is an active contributor to numerous Python, data science, and scientific communities worldwide.
Serial AI Entrepreneur creating contents on YouTube and Building Ventures