From Connected Agents to Collective Intelligence with Guillaume De Saint Marc of Outshift by Cisco

**Daniel Faggella** (0:12)
Welcome everyone to the Emerge AI in Business Podcast. Today's guest is Guillaume de Saint Marc, VP of Engineering at Outshift. Outshift operates as Cisco's internal incubator for emerging technologies focused on reducing risk and delivering innovative results. Guillaume examines why enterprises building multi-agent AI systems encounter coordination failures that connectivity protocols alone cannot resolve. The conversation covers the infrastructure layers required to enable genuine agent collaboration, including shared semantic grounding, persistent memory architecture, and fine-grained task authorization. Along with the security and observability decisions, enterprise leaders must build into their agentic systems from day one. Today's episode is sponsored by Outshift by Cisco. In this episode, we cover why enterprises scaling multi-agent AI need more than connected agents. To go deeper on this topic and learn how consultants are winning business with evidence-based AI ROI and building long-term capabilities instead of chasing short-term gains, download our free PDF report 3 Keys to Thriving in the Coming Era of Automation at emerge.com/cok1.
That's emerj.com/cok1 to download your copy. Now the conversation with Guillaume.
Guillaume, welcome to the Emerge AI in Business Podcast.

**Guillaume de Saint Marc** (1:53)
Hey, Yolande, many thanks for having me. It's great to be here.

**Daniel Faggella** (1:56)
It is, and it's great to have someone like you, because you are the person that actually has to build the infrastructure that makes all these agentic systems work at scale. And I think we're gonna get into very interesting things today. I wanna start with something that I think a lot of leaders in our audience are quietly sitting with right now. They're not, we're not speaking about it out loud because we're not sure exactly where the problem is at the moment. I think your organization's own work on the Internet of Agents was premised on solving a connectivity problem.
That means getting agents to find each other, communicate and coordinate. But you've watched this play out from the inside and you've been saying publicly that connectivity is actually the first layer. And there's something more in the foundation. There's a fundamental problem underneath that first layer. What is that and what does it look like in practice when organizations hit that wall?

**Guillaume de Saint Marc** (2:46)
Yeah, that's exactly as you've said. And let me start with a little story to try to help everyone understand what we are going after and what is the second layer that you talked about. So picture a hospital, not a futuristic one from today. The diagnostic team is excellent. The pharmacy team is excellent. They avoid bad drug cocktails. The billing team knows every insurance code. The patient coordination team keeps the schedule running. Now put them all in a room for the first time with no shared language and no institutional memory of what success looks like. No way to resolve this agreement. And the patient is waiting on the other side at the door. That's not a staffing problem. That's a coordination infrastructure problem that you have with this human. And if we move to the agentic world, this little story is exactly what enterprise are running into as they try to move from a single agent to systems of agents working together. And so if you want the first wave of agentic AI, it works, but the second wave is where things start to break. So single agents performing well scoped tasks, for instance, creating a marketing campaign or generating a financial report or coding a new module. All these works pretty well and are obviously very useful these days.
But enterprise have real wins here, but challenges to go beyond. And the failure starts when you ask multiple agents to collaborate on something, none of them can achieve alone. And that's where the wheels come off. And not because the agents are bad at their job, on the contrary, but because there is no infrastructure for them to actually work together. So the way to think about it is so far, we've been focusing on solving the wiring, so making sure these agents can find each other, pass message, exchange data, all this is happening. But what hasn't been solved so far is what happened once they're in the same room. Put the best IT security team, the best cost management team, or the best customer experience team in a crisis together. If they've never shared a frame for what a good outcome looks like, they will be caught in a deadlock, like the security agent will compromise on nothing because that's his job. The cost agent will say, the fix is too expensive, whatever. The operation agent says, we need to roll back now, and the customer experience agent will say, well, customer can't wait, what are you guys doing? All four are right in a way, but none of them can resolve it without something in the room, which can hold all of them accountable for taking a reasonable decision. And that's the gap. And agents actually are hitting this type of problem faster than humans do, because keep in mind that contrary to humans, they run and they operate at machine speed and scale. So they have no patience for ambiguity in a way. And so just to wrap on this, there is really like a few well-known by now patterns into which these agents will fall again and again in production when you try to build a multi-agent solution or system. And the first one is, agent can very easily drift semantically and end up not sharing the same reality. They were asked to do one thing and they end up working on the wrong outcome. In a way, they're a bit lost in semantic translation, if you want. Second is they do not converge. So they try hard, but they do not converge. A competing agent with no shared frame for negotiation can end up in a deadlock, because they all camp on their position and they don't know how to find a good consensus. And the third classic that we see often as well, which can very rapidly happen with a multi-agent system or solution, is they have problematic blind spots or they keep resetting. And this has to do with memory. So every session starts from scratch, no memory of what was done before, no compounding of knowledge, past experience, no ability for one agent to access maybe the crucial information that another agent has but is not able to share.