Everyday AI Podcast – An AI and ChatGPT Podcast

Ep 708: Inside the Society of Agents: Why AI Teamwork Beats Bigger Models

65 snips

Feb 6, 2026

Ece (AJ) Kamar, Microsoft Research leader with two decades in multi-agent systems, explains why small, coordinated agents outperform single huge models. She discusses agents acting as teams, practical interfaces and workflows, multi-agent oversight for safety, privacy boundaries, and emerging agent-based business ecosystems.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Agents Over Bigger Models

Large models were the early focus, but agentic systems—many smaller models working together—offer a different path to capability.
Ece (AJ) Kamar argues new reasoning models enable building agentic systems we only dreamed of for decades.

ANECDOTE

Two-Decade Agent Journey

Ece describes her 20-year journey from PhD work on agents to building practical systems today at Microsoft Research.
She notes GPT-4 marked the moment prototypes could become real, deployable products.

INSIGHT

Agents Work In Teams

Agents won't operate in isolation but will communicate with people and other agents to complete tasks.
Ece envisions agents representing skills and forming teams with humans across workflows and companies.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

For better AI agents, we just need bigger models, right? 🤔

Nah.

They just need to all work together in a society.

That's Ece Kamar's take. And she should know. She's been working in the AI agent field for two decades, long before the birth of the modern large language model.

So what's the next step for your company to embrace agents? Focus on smaller agents working and sharing, not one jumbo model working in a silo.

Tune in and find out how to make it work.

Inside the Society of Agents: Why AI Teamwork Beats Bigger Models -- An Everyday AI Chat with Jordan Wilson and Microsoft Research's Ece Kamar

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Join the discussion on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

Society of Agents vs Bigger AI Models
Agentic Teamwork Advantages Explained
Evolution of Agents at Microsoft Research
Real-World Multi-Agent Collaboration Use Cases
Emergence of Action-Oriented Reasoning Models
Designing Business Workflows for Agentic AI
Multi-Agent Oversight and Risk Management
Future Ecosystems and Agentic Business Models

Timestamps:

00:00 "AI Agents: Decades to Breakthroughs"

05:44 Collaborative AI Agents Transform Work

08:13 "AI Models Learning to Act"

12:49 "Transforming Workflows with Generative AI"

16:49 "Human Value in Tech Change"

20:30 "Autonomous Agents: Resilient Actions"

21:37 "Multi-Agent Strategy for Oversight"

26:04 "Integrating Memory into Models"

29:28 "Future Ecosystems and Business Models"

Keywords:

society of agents, multi-agent systems, agentic society, AI teamwork, agentic workflows, AI agents, team of agents, multi-agent approach, agent-based models, agentic models, reasoning models, large language models, reinforcement learning, collaboration between agents, autonomous agents, agentic behavior, orchestration, agent communication, a

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.