# Agents as collaborators, not chatbots > The story of rooting your AI strategy back in your product's DNA, and exiting the vicious cycle of copying the big AI players. Monika Pawlak · 2026-11-16 · https://monika.fyi/writing/agents-as-collaborators-not-chatbots --- Most AI products today look the same: a prompt box, often in a panel on the side, and a conversation that scrolls upwards. You trigger your agent only by sending a prompt. When we brought AI into Miro, we brought that pattern with us, because it's how the industry defined interaction with AI - through chat. This article is about the year we spent questioning it. The question I kept coming back to was simple. Miro is an infinite, multiplayer canvas. What would AI look like if it were built from Miro's DNA, rather than borrowed from a chat app? My answer, after a lot of experiments across product, design and engineering, is that in a product like Miro the canvas itself should be the prompt and the response. The canvas should be the chat. And the triggers shouldn't be limited to the user having to prompt an agent (that already feels like a boring job anyway, doesn't it?). There's one more tension running through this story. Miro is multiplayer first, but most AI patterns we saw in the wild are single-player. And you need to enable both. ## The problem When we talk to our users, there are clearly two reasons people choose Miro: to visualise something or to collaborate. They come for the infinite canvas. Nobody comes to Miro for a chat. That has had a big consequence for Miro's AI. A chat panel is a single-player, text-first surface that sits next to the canvas rather than on it. Whatever the AI does, you experience it as a conversation in a sidebar your team can't see. And users expect AI to be just as good as a human. In the context of a multiplayer collaborative canvas, the AI in Miro had not met that bar until this year's October 2026 releases, which were presented at major keynote events in San Francisco, London, Tokyo and Sydney. That was our first step towards the vision, but the AI was still not Miro-native. Our AI design team has explored many concepts to achieve the vision, and I have especially invested my time in testing a radical approach, where there are no chat panels, just the canvas, to see where it gets me. This is the story of us exploring all these concepts and what I learned along the way. ## Experiment 1: a multiplayer chat panel The first instinct was to keep the chat panel but make it multiplayer. In July we built it in our Miro prototype: a multiplayer chat panel with thread-based conversations that several people could have with other human or agent collaborators on the same board. It had controls to switch between private and shared conversations, because users would naturally expect them. It basically felt like bringing Slack to Miro. Conceptually, it felt quite close to Figma's recent AI chat release too. And that made it smell fishy. It felt like entering the vicious cycle of copying OpenAI and Anthropic again (oh, I have spent enough time in AI to really know when it happens, and I can assure you, it never ends well). AI was still stuck in a narrow panel, while 80% of the product surface was still the "old Miro experience". ![The multiplayer chat panel in the Miro prototype: threaded conversations several people and their agents share on one board](/assets/writing/multiplayer-chat.v2.mp4) So I ran a couple of user tests. No big reactions. Mostly scepticism, or surprise that Miro even has a chat: "I don't come to Miro to chat." It wasn't surprising, but it was necessary for us to really validate it and move on. A multiplayer chat panel asks people to adopt a new chat tool inside a canvas tool, and the experiment showed it wasn't an ask they wanted. ## Experiment 2: agents in comments If people don't come to Miro to chat, where do they already talk? In comments. Comments are like a chat, and they're already multiplayer. They're attached to a specific thing on the board, so they carry its context, and (fun fact) comment usage is one of the features that help drive adoption. So the thinking evolved from "bring humans to AI" to "bring AI to humans" - conceptually much closer to our product DNA, and to making agents feel like equal collaborators to humans. ![A comment on a frame, tagged to the agent: its cursor arrives at the thread and does the work](/assets/writing/ai-jamming-with-you.v2.mp4) Comments aren't the whole answer, though. On big boards, finding the right comment thread becomes a scavenger hunt. Comments are right for work that should stay attached to the board, but we might also need something lighter. ## Experiment 3: cursor chat for agents ![Cursor chat on the canvas: Marco and Amara talking beside their own cursors while the agent adds an ice breaker behind them](/assets/writing/ai-multiplayer-cursor-chat.v2.mp4) In October, Miro introduced cursor chat for people: press a key, type a short line, and it floats next to your cursor for your collaborators, then disappears. It was built for humans talking to humans: quick, ephemeral, right here, right now. At the same time, decision models started popping up, so I started experimenting with them for this. The ephemeral cursor chat felt like the perfect use case: when does AI react to these messages (and when doesn't it - surprisingly, that's much easier to define)? In a "quiet cursor chat" concept I compared three triggers: say its name, let a small decision model decide whether you're talking to it, or both. Naming alone is predictable but misses implicit asks. A model alone catches those, but then naming the agent isn't guaranteed to work. In the prototype the agent stays quiet on a low score, offers to help above about a third, and only acts when the model is very confident, around 0.86. ![Quiet cursor chat: the agent stays quiet on a low score, offers to help above about a third, and acts only when the model is very confident](/assets/writing/quiet-cursor-chat-15.html) ## Experiment 4: Cursor Town ![You write the goal on the board, and a team of agents breaks it down](/assets/writing/ai-boardroom-1-goal.v2.mp4) ![When they need you, they ask on the canvas: questions as sticky notes to pick from](/assets/writing/ai-boardroom-2-input-build.mp4) ![Agents answer in objects on the board, not in text](/assets/writing/ai-boardroom-3-build-map.mp4) ![An agent draws with the pen tool, in ink - not a generated image](/assets/writing/ai-boardroom-4-drawings.mp4) Quiet cursor chat left me with a question. If a small decision model can tell when you're talking to the agent, why does the human still have to start every exchange? All of these experiments still assumed it. So I took the decision models further and tested the radical opposite: no chat at all. You communicate through the canvas itself, the agents act on their own, and you just align with them. I called it Cursor Town: an infinite canvas where a team of agents works with you towards your goal. You write the goal on the board, and the agents break it down, work on it, and show their thinking as content on the canvas. When they need you, they ask on the canvas too. You communicate like human collaborators do, using the shared canvas and its widgets. No new interaction patterns to learn. "I tell you, you do" becomes "we work towards a shared goal." In this version, the agents are predefined and each has its own role (a next iteration would let you define your own, or bring your own third-party agents). For example, the Devil's Advocate raises risks, and the Chief Drawing Officer defines the visual layout for the other agents to respond to (no chat-like walls of text to review, but canvas-native visualisations that are easier to consume). But the personas aren't the important part. What matters is what cursor chat taught me, taken all the way: the agents react to everything that lands on the canvas, and fast. A small decision model picks what each agent should do next (approach the user? respond? keep working? delegate a subtask?), in a fraction of the time a full model would need to read the whole board. That speed is what makes it feel like collaborating with humans and agents, rather than prompting a tool. The best part is that none of this needs new building blocks in Miro. It's a remix of functionalities that Miro already has. I recently heard of a user who already works with their Claude this way: prompts on sticky notes, which Claude picks up via MCP. For them, the canvas is already the prompt. ## Reflections and what's next **What to build is still the hard decision.** AI makes it easy to build things fast, but building the wrong solution efficiently is still building the wrong solution. The multiplayer chat panel worked, and we could have spent months polishing it. A couple of user tests told us nobody needed it. **Multiplayer AI is a context problem, and the canvas already solves it.** As soon as other people join the interaction with AI, it explodes in complexity: "Will my private chat leak into the shared one?", "I don't want others to see how I prompt." Nobody seems to have cracked adoption for multiplayer AI yet. But if the canvas is the "chat", Miro has already solved it: I see what you see, and I know what you know. Want a private AI session? Don't share the board. Want AI in your jam session? Get the humans in! I stay in control through the sharing settings I already know, and lack of control is exactly the biggest adoption barrier for AI. **Start from the radical solution.** As a designer who thinks a lot about product vision, I've learned that the biggest constraint is often the product itself: its limitations, existing solutions and dependencies. Design with all of those in mind and you soon end up just improving the system instead of thinking big. So start from scratch, question everything, and be radical. Don't try to build the bridge before you even know where you want it to lead. Don't dilute your ideas, don't shoot them down in your head, just build. Build and see where they take you. And they will take you places! It's also the way out of the vicious cycle of chasing the big AI players (though let's be honest, you'll always be chasing a bit). Copying them was never the reason your product succeeded, so it won't suddenly bring more growth. Make AI native to your product's DNA instead. Experiments 3 and 4 haven't been tested with users yet, so even though I'm excited about them, they might turn out to be wrong too. That's fine: the point is to find out quickly. I remain a strong believer in multiplayer AI and in the power of infinite canvases to accommodate this interaction. Special thanks to the design team I've been exploring this with: Kasper Marx Andersen, Mark Boyes-Smith, Josh Kriese and Robert Kortenoeven. And to Tilo Krueger and Bhavika's team, who brought cursor chat for humans to life.