The Fifth Elephant
The Fifth Elephant

The Fifth Elephant 2025 Winter Edition Call for Proposals

On AI disrupting analytics - make a submission

All submissions

Mayur Madnani

@mayurmadnani

Building Multi-Agent AI Systems: A Philosophical Debate

Submitted Nov 10, 2025

Type of submission: Hands-on workshop (1.5 hrs to 3 hrs)

Abstract

This hands-on workshop introduces participants to multi-agent AI systems through a unique philosophical lens. Attendees will learn to build a debate system where three AI agents—embodying Socrates, Plato, and Aristotle—engage in dynamic conversations on user-provided topics. The workshop demonstrates core agentic AI concepts including agent orchestration, persona design, memory management, tool usage, and multi-turn dialogue systems.

Participants will work with local LLMs to create specialized agents with distinct reasoning styles: Socratic questioning, Platonic idealism, and Aristotelian pragmatism. Through live coding and experimentation, attendees will understand how to design agent personalities, manage conversational context, implement turn-taking logic, and integrate tool-calling capabilities.

By the end of the session, participants will have a working multi-agent debate system and understand the architectural patterns for building collaborative AI systems applicable to various domains—from creative writing to problem-solving to policy analysis.

Target Audience

  • Level: Intermediate developers and AI practitioners
  • Prerequisites: Basic Python knowledge, familiarity with LLMs/prompting concepts
  • Ideal for: Software engineers, AI/ML developers, technical leads exploring agentic AI architectures

Learning Objectives

By the end of this workshop, participants will be able to:

  1. Design Multi-Agent Systems: Understand architectural patterns for coordinating multiple AI agents with distinct roles and personalities
  2. Implement Agent Personas: Create specialized agents with unique reasoning styles using prompt engineering and system instructions
  3. Manage Conversational Context: Build memory systems that maintain dialogue history and enable coherent multi-turn conversations
  4. Orchestrate Agent Interactions: Implement coordination logic for turn-taking, randomized ordering, and multi-round debates
  5. Integrate Tool Usage: Enable agents to call external tools and incorporate results into their reasoning
  6. Run Local LLMs: Set up and use Ollama for running open-source models locally without API dependencies

Mayur is a seasoned engineer specializing in 𝐀𝐈, 𝐝𝐚𝐭𝐚, 𝐚𝐧𝐝 𝐛𝐚𝐜𝐤𝐞𝐧𝐝 𝐬𝐲𝐬𝐭𝐞𝐦𝐬, with a proven track record of building scalable, high-performance platforms for leading organizations including 𝐉𝐢𝐨𝐇𝐨𝐭𝐬𝐭𝐚𝐫, 𝐈𝐧𝐭𝐮𝐢𝐭, 𝐖𝐚𝐥𝐦𝐚𝐫𝐭 𝐚𝐧𝐝 𝐒𝐀𝐏.

He has taken several webinars and undertaken speaking sessions. He is active on https://www.linkedin.com/in/mayurmadnani/

All submissions

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

The Fifth Elephant
The Fifth Elephant
Jumpstart better data engineering and AI futures