The average Fortune 1000 company has more than 30,000 employees and engineering, sales, and marketing teams consisting of hundreds of members. Large teams exist in government, science, and defense organizations alike. And yet, research shows that it’s the ideal size for productive real-time conversations. only about 4 to 7 people.
The reason is simple: as groups get larger, each person has less opportunity to speak And they have to wait longer to respond, increasing their frustration that their ideas are not adequately considered. This is true whether groups collaborate in person, by video or teleconference, or even by text chat (which buries users in a backlog of messages that reduces participation and undermines discussions).
Simply put, productive team conversations Don’t scale.
So, what do you do if you have a large team and you want to leverage their knowledge, intelligence, insight and expertise? For many organizations, their only choice is to resort to surveys, polls or interviews. It will capture data about individual viewpoints, but no one will feel “heard” when the process is finished, and it will rarely find the optimal solution.
This is because polls, surveys and interviews are not instruments of deliberation. There is no give-and-take as team members debate issues, provide reasons and arguments, present arguments and counter-arguments and ultimately agree on a solution based on their deliberative merits. Surveys find people oversimplified data pointWhereas interactive conversations treat people the same way thoughtful data processor. This difference is very deep.
I’ve been studying this issue for over a decade, and I believe the best way to unlock it is true collective intelligence Large teams scale through authentic real-time interactions. I’m talking about thoughtful discussions where multiple people can together brainstorm, set priorities, and forecast, ultimately converging on solutions that truly leverage their combined knowledge, intelligence, and insight.
But it’s impossible to measure interaction, isn’t it?
Wrong – In the last few years, a new communication technology, hyperchat aiHas emerged. It enables large, distributed teams to have productive discussions where they can debate issues, brainstorm ideas, prioritize options, provide arguments and counterarguments, and efficiently come up with solutions.
Inspired by large natural systems, HyperChat AI combines biological principles swarm intelligence With the emerging power of AI agents. It works by dividing any large, networked group into a set of smaller, interconnected subgroups, each sized for discreet real-time interaction by text, voice or video. The magic ingredient is a bunch of AI agents, called “Conversational Surrogates,” who participate in each local discussion and work to tie all the subgroups together into a coherent discussion.
Using HyperChat AI, groups of potentially any size can debate issues, brainstorm ideasPrioritize options, forecast results And solve problems in real time. And it works – research shows that when large teams interact this way, they converge on smarter, faster, and more accurate solutions. In a study I was personally involved in in groups involving HyperChat AI increased their collective IQ Up to the 97th percentile.
In another studyConducted in collaboration with Carnegie Mellon University, groups of 75 people who interacted using HyperChat AI technology said they felt more collaborative, productive and heard than through traditional communication structures like Microsoft Teams, Google Meet or Slack. they also felt more buying and selling The solutions that emerged.
To test the merits of HyperChat AI in a fun and topical format, I asked the research team at Unanimous AI (developer of Thinkscapes, a platform that uses HyperChat AI) to bring together 100 members of the public watching the Super Bowl this Sunday and debate. Which Super Bowl ad was the most influential and why?
I know this isn’t a question of grand social importance, but the Super Bowl is one of the most watched events in the world for both the athletic spectacle and the commercials. This year, the 30-second spot cost between $8 and $10 million, not including production costs. With that level of investment, every brand wants to stand out, yet only a few can achieve it.
So, we brought together 110 random members of the public – their only qualification was that they watched the Super Bowl – and asked them to discuss and debate the ads. Sixty-six unique commercials played during the game. Did any of them stand out above the rest, and if so, Why Was it that effective?
The 110 participants were divided into 24 subgroups, each consisting of 4 or 5 humans and one AI agent. Each agent was tasked with observing their subgroup, identifying key insights in real time Share those insights with AI agents In other subgroups. When agents received those external insights, they participated in their local conversations, expressing the insights as members of their group. This process threads all discussions together into a real-time conversation that flows and blends together seamlessly.
In total, 110 human participants suggested 54 different ads for consideration, and they reached a conclusive answer in just 10 minutes of hyper-connected discussion. And, because the AI agents were tracking dynamics within all 24 local debates, as the conversations ended, the system generated a ranked list of all 54 ads based on support for the conversation across the entire population.
Here are the top ten identified by discussion participants:
As you can see, the Pepsi ad that used Coke’s polar bear was the most effective ad of the night by a wide margin. In fact, the Thinkscape system reported that this was a statistically significant result for a population of randomly selected consumers (p<0.01).
In addition, the system automatically tracks the reasons that emerged in each subgroup and the reactions to those reasons (whether it influenced others’ opinions, prompted counterarguments, or both). This enables the system to quickly produce a thoughtful overview for each ad produced, assessing why the group viewed each ad the way it did.
Here’s a spur-of-the-moment argument for a polar bear ad: :
“Our collective view is that the most effective Super Bowl ad of 2026 was the Pepsi Polar Bear spot. We found it effective because of its humor, clever use of polar bears, a dig at Coca-Cola, memorability, nostalgic elements, broad appeal, product focus, and ability to spark conversation. While some of us criticized it for focusing on a feud, a large majority felt it successfully captured the essence of the classic Super Bowl ad.”
For the record, the team at Unanimous AI also asked this real-time group to consider a follow-up question, Which Super Bowl ad was the least effective and why? After 10 minutes of deliberation the system reported this:
“Our collective view is that the worst Super Bowl ad of 2026 was the Coinbase spot. We found that it lacked clarity, had confusing messaging and a failure to explain the product effectively. Additionally, many people found the ad annoying, cheesy and low-effort, with very little promotion of the product and no separation from Coinbase’s services. Overall, it failed to build trust and was disappointing for many viewers.” Note: There was a statistically significant result (p<0.01) among the selection population of this advertisement.
Again, this was just a fun example of involving the public, not a discussion of any grand significance. That said, I have seen large groups, from analysts at large financial institutions to scientists at the Department of Energy, discussing important issues using this technology – and in all cases the groups seem to be coming together with increased speed, accuracy, and buy-in.
For an overview of academic studies on HyperChat AI, see This recent paper.
Louis Rosenberg received his PhD from Stanford University, was a professor at California State University (Cal Poly) and has been awarded over 300 patents for his work in human-computer interaction, AI, and collective intelligence.
<a href