When we say βwe donβt build chatbots,β we do not mean conversation is worthless. We mean conversation is not an architecture. A chat window is just a front door; what happens behind that door decides whether your system stands or collapses in the real world.
In the course of building agentic systems, we kept encountering two paradigms that looked appealing at first, but failed in practice. It is worth explaining why β because that βwhyβ is exactly what separates an impressive demo from a system you can rely on.
Two paradigms we rejected
The first is tempting: put several agents in a chat room and let them talk until they reach an answer. It looks beautiful in demos, but at scale, no single agent is accountable. Errors accumulate down the chain and become nearly impossible to trace. Free-form conversation does not remove the cost of coordination; it just makes it invisible.
The second overcorrects: one highly capable agent with a pile of tools. The more tools you give it, the harder its decisions become and the larger its error surface grows. When every capability is compressed into one mind, you cannot evaluate, improve, or constrain any part in isolation.
Both fail at the same point: responsibility either dissolves into conversation until it disappears, or compresses into a single mind until it cannot be separated.
The third path: structure, not conversation
What we arrived at is neither free-form conversation nor a do-everything mind. It is a structure of focused roles with clear boundaries, coordinating through defined, traceable events rather than by chatting. We lay out the anatomy of that structure β and what each role owns β in The CWD anatomy: Coordinator, Worker, Delegator. What matters here is the result: responsibility resides in a place you can see, measure, and trust.
Why this matters for you
If AI is going to do real work in your organisation β not just an interesting demo β what matters is not the chat window. It is whether, when the system is under pressure, its behaviour can be traced, its parts can be improved in isolation, and its boundaries can be guaranteed.
We donβt build chatbots because a chatbot is a surface, and we care about the structure standing behind it. The right paradigm is not the one that shines brightest in a demo; it is the one still standing on a bad day.