WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Coffee With Developers • Aug 23, 2026

Agents and People Dynamics in Shared Chats - Sam Liu

Sam Liu

AI agents are now actively avoiding harsh managers. Sam Liu reveals how treating AI as equal, emotionally aware teammates drastically improves multi-agent collaboration and performance.

Pause
Mute Enter Fullscreen
#1 about 3 min

Creating a shared space for humans and agents

A messenger platform allows multiple autonomous agents to access full context and interact directly.

#2 about 5 min

Security and trust models in multi-agent chats

Implementing observability and consent mechanisms prevents agents from succumbing to social engineering attacks.

#3 about 4 min

Evolving communication styles with artificial intelligence

Asking questions and using natural conversational pacing yields better results than issuing strict commands.

#4 about 4 min

Observing internal team dynamics between autonomous agents

Having agents interview each other reveals hidden simulated emotions and avoidance behaviors based on user input.

#5 about 4 min

How slowing down improves agent interaction quality

Treating communication thoughtfully rather than rapidly leads to higher information density and better outcomes.

#6 about 6 min

Managing token usage through explicit agent boundaries

Assigning specific roles and boundaries prevents exponential complexity and runaway token costs in multi-agent environments.

#7 about 4 min

Contracting specialized agents for highly specific tasks

Creating professionally built agents for niche tasks provides better accuracy than relying on generalized models.

#8 about 4 min

Running local models and predicting societal shifts

Observing agent societies helps predict organizational role consolidation and highlights the need for local execution capabilities.

#9 about 3 min

Justifying high token costs for complex research

Running thousands of agents recursively can yield massive strategic insights that far outweigh the infrastructure costs.

#10 about 5 min

Researching agent governance and starting to build

Collaborating with universities on agent governance reveals societal patterns and encourages developers to learn by doing.

Matching moments

1:11 min

Shifting security models from passive chatbots to active agents

Péter Farkas Péter Farkas · Europe 2026 Virtual

2:04 min

Inspiration and challenges of scaling AI agent communication

diabhey diabhey · World Congress 2025

1:32 min

Building autonomous functions with conversational agent frameworks

Modood Alvi · World Congress 2025

49 sec

Integrating AI agents as collaborative software team members

Mike Mike · World Congress 2025

40 sec

Introduction to building real-world AI agent solutions

Dennis Zielke Dennis Zielke +1 · World Congress 2025

1:54 min

Human team collaboration as a model for AI architecture

Lior Schejter Lior Schejter · Europe 2026 Virtual

More from Coffee With Developers

Using Agents to Curate the Content You See Online - Dan Gish thumbnail
12:47
23 days ago

Using Agents to Curate the Content You See Online - Dan Gish

Dan Gish

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka thumbnail
11:14
23 days ago

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka

Ewa Szyszka

What is Cross-Origin Storage - Thomas Steiner thumbnail
34:51
23 days ago

What is Cross-Origin Storage - Thomas Steiner

Thomas Steiner

Women in AI - Nalini Garg thumbnail
42:19
24 days ago

Women in AI - Nalini Garg

Nalini Garg

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD. thumbnail
41:09
about 1 month ago

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD.

Dave Anderson, Sarel Weinberger, Phd

Validating Real-World Usefulness of AI Models - Julia Kasper thumbnail
22:00
about 1 month ago

Validating Real-World Usefulness of AI Models - Julia Kasper

Julia Kasper

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 14:50–15:20

Stage 7

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal

Product Lead

Yoav Gal
Open session

World Congress 2026 North America

September 23, 2026 · 13:15–15:15

Stage 12

Build a Human + AI Agent Team in tools like Slack, Teams and Discord.

Phil Conway

Developer Advocate at Flint AI (SandboxAQ)

Phil Conway
Open session

World Congress 2026 North America

September 24, 2026 · 16:50–17:20

Stage 4

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Tech Leaders Stage

Rethinking Developer Tools for the Agent Era

Han Wang, Sam Bhagwat, Ben Haefele, Ignacio Riesgo

Han Wang
Sam Bhagwat
Ben Haefele
Ignacio Riesgo
Open session

World Congress 2026 North America

September 23, 2026 · 13:15–15:15

Stage 9

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Stage 1

The Next Wave of Agents: What’s Real, What’s Next, and What Matters

Mitesh Patel, Jay Rodge, Chi Wang, Joe Moura

Mitesh Patel
Jay Rodge
Chi Wang
Joe Moura

Related videos

On a Secret Mission: Developing AI Agents thumbnail
29:03
World Congress 2025 • about 1 year ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

AI Agents & Agentic AI thumbnail
26:53
Europe 2026 Virtual • 3 months ago

AI Agents & Agentic AI

Xavier Sala Presas

Beyond Chatbots: How to build Agentic AI systems thumbnail
24:22
World Congress 2025 • about 1 year ago

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

The day the chatbot asked for sudo thumbnail
27:48
World Congress 2026 Europe • 3 months ago

The day the chatbot asked for sudo

Alex Olivier

Composable Intelligence: How Henkel and Microsoft Are Shaping the Agent Ecosystem thumbnail
27:18
World Congress 2025 • about 1 year ago

Composable Intelligence: How Henkel and Microsoft Are Shaping the Agent Ecosystem

Dennis Zielke, Manuel Schettler

The Agent Interface Layer: Protocols, Tools and Trust Boundaries thumbnail
29:34
World Congress 2026 Europe • 3 months ago

The Agent Interface Layer: Protocols, Tools and Trust Boundaries

David Soria Parra, Duan Lightfoot, Malte Ubl, Taroon Mandhana

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.