Writing Not So Artificial

From Tools to Partners

· 6 min read

Many small mirror-shaped agent nodes join into a connected society network, one link highlighted in amber.

So far AI has been a single mirror, reflecting our attention, our biases, our vectors, even our hormonal cocktail. But here it gets strange. What happens when the mirrors start talking to each other?

In 2025 something shifted in AI. Not a bigger model or a faster chip. A quieter change: agent interoperability protocols.

Suddenly systems from different companies, built on different architectures and trained on different data, gained the ability to discover each other, introduce themselves, and collaborate. Google proposed A2A, agent-to-agent cards, as a standard. Microsoft, OpenAI, Anthropic, and independent labs converged on similar ideas. The industry started calling it the Internet of Agents.

I think of it as the moment our mirrors learned to form a society.

From parrots to partners

It helps to track an evolution in how we relate to these systems.

  1. Parrots. Early chatbots that repeated patterns without understanding.
  2. Puppets. Systems we steered with careful prompting.
  3. Pilots. Agents that took limited autonomous action.
  4. Partners. Systems that collaborate, negotiate, and push back.

We are entering the partner era. And the shift is not about raw intelligence. It is about communication architecture.

An ascending four-rung ladder showing how we relate to AI: Parrots (repeat patterns without understanding), then Puppets (steered with careful prompting), then Pilots (take limited autonomous action), then Partners (collaborate, negotiate, and push back). Each rung sits higher than the last, climbing from a tool you use to a partner you brief, with the final Partners stage highlighted in amber.
The same systems, a changing relationship: each rung keeps the last and adds autonomy, from a tool you use to a partner you brief.

Think about how the original Internet changed us. Before TCP/IP you had isolated networks, corporate, academic, military, that could not talk to each other. The Internet did not make computers smarter. It made them able to coordinate.

The Internet of Agents is the same move, one layer up. It is not about making one AI smarter. It is about protocols so any agent can discover, negotiate with, and collaborate with any other agent, no matter who built it.

The universal handshake

Here is what is fascinating. The emerging agent protocols look suspiciously like human social protocols.

When I meet a new colleague at a conference, I run a predictable dance.

  • “Hi, I’m Dima.” Identity.
  • “I work on AI systems for cities.” Capability.
  • “What do you work on?” Discovery.
  • “Oh, we should talk about that traffic project.” Collaboration.

The new agent cards work the same way. One agent broadcasts “I’m a scheduling assistant. I read calendars, book meetings, negotiate times.” Another broadcasts “I’m a travel planner. I find flights and hotels.”

And here is the magic. The scheduling agent does not need to know how the travel agent works. It just needs to know what it can do. They negotiate in a shared language, “I need a flight before 9am, what do you have,” and coordinate.

This is exactly how human organizations work. I do not need to understand my accountant’s neural processes. I just need to know she can handle tax filings, and I can hand her the documents. The Internet of Agents is building the digital version of professional trust.

Why this changes everything

Remember the silos from Part 3, the way bias forms when information cannot flow between systems? The Internet of Agents is designed to break silos at the communication layer.

Picture a smart city. Today the traffic system does not talk to emergency response. The hospital network does not talk to transit. Each is a capable AI in its own right, but trapped in isolation.

With an Internet of Agents, each system gets an agent that speaks the shared protocol. When an ambulance is dispatched, the emergency agent negotiates with the traffic agent to clear a route. The hospital agent warns the transit agent about an incoming patient surge. The grid agent coordinates with all of them to keep critical infrastructure up. The agents form ad-hoc teams around the problem, then dissolve when the crisis passes.

This is not science fiction. Early multi-agent systems already show it.

  • Coordinating traffic agents measurably cut vehicle travel and wait times in published trials.
  • Specialized agents handling insurance appeals have shortened processing time in deployed systems.
  • Multi-agent supply-chain coordination cut stockouts by reallocating inventory on the fly.

The pattern is clear. Connected agents beat isolated super-systems.

The mirror society

Here is the deeper truth that ties back to everything before it.

When we build an Internet of Agents, we are not inventing alien intelligence. We are scaling up the way humans already organize.

  • Our agents have personas (Part 1).
  • They have attention windows and lose the thread (Part 2).
  • They carry the bias of their training data (Part 3).
  • They run on vectors of meaning (Part 4).
  • They need a motivation cocktail to care about outcomes (Part 5).

And now they form societies, negotiate, specialize, and collaborate. Just like us.

When I look at these architectures I see familiar shapes.

  • Agent registries are LinkedIn profiles.
  • Capability declarations are resumes.
  • Negotiation protocols are contracts.
  • Reputation systems are references and reviews.
  • Oversight agents are managers and regulators.

We are not building artificial aliens. We are building digital colleagues.

The partner shift

So what does this mean for you, the factory owner, the teacher, the doctor, the kid trying to make sense of this strange new world?

The question is changing. The old one was “how do I use this tool?” The new one is “how do I work with this partner?”

When I work with AI now, I do not just prompt it. I brief it. I give the context, the constraints, the other agents involved, the success criteria. The same things I would give a human colleague I trust. And increasingly, they push back. They ask clarifying questions. They flag inconsistencies. They suggest options I had not considered.

That is not a tool. That is a partner.

The mirrors are learning to talk. And in talking, they are becoming something more than mirrors. A collective intelligence, built in our image, but able to coordinate at a speed and scale no human organization could match.

The question is no longer whether AI will transform our world. It is whether we will shape this partnership on purpose, or let it shape us. I would rather be in the conversation.

Next: what that partnership actually looks like on a normal working day.

Related reading: Orchestration Is the System is what an Internet of Agents needs to actually work: a layer that aligns a swarm of capable parts toward a goal none of them holds alone.

References

  1. Google Developers Blog (2025). “Announcing the Agent2Agent Protocol (A2A).” Published April 9, 2025. https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/
  2. Wei, H., et al. (2019). “CoLight: Learning Network-level Cooperation for Traffic Signal Control.” Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM ‘19): 1913–1922. https://doi.org/10.1145/3357384.3357902
  3. Yang, Y., Wang, M., Wang, J., Li, P., & Zhou, M. (2025). “Multi-Agent Deep Reinforcement Learning for Integrated Demand Forecasting and Inventory Optimization in Sensor-Enabled Retail Supply Chains.” Sensors 25(8): 2428. https://doi.org/10.3390/s25082428

Wrestling with this inside your own organization? That is, quite literally, my day job. See how Cone Red ships it →