The Threshold Should Be Invisible
In most web applications, navigating between pages is a hard cut. I treat it as a threshold. The transition between two screens is a small but consequential surface in its own right.
What Your AI Cannot See
When an AI system produces the wrong output, the instinct is to add more instructions. But the problem is usually not that the model ignored the rule. It is that the model could not see the information it needed to follow it.
Why I Do Not Build Dark Mode
Dark mode is the most-requested feature I have refused to build. The reason is not aesthetic. It is structural. A second canon doubles the design surface and halves the precision of every decision.
Building Alone, Shipping Fast
Cleo is built by one person. I say that not as a badge of honour but as a fact that shapes every decision. There is no backend team. No design team. No DevOps. No QA. One person, a code editor, and AI tools that have fundamentally changed what "one person" means.
The Energy Model
Most SaaS pricing is simple. You pay per seat, per month. Maybe there is a usage component for storage or API calls. The model is well understood and investors like it because it scales linearly with headcount.
One Agent, Not Ten
The multi-agent pattern is having a moment. Every AI product demo shows a fleet of specialised agents handing off tasks like a relay team. An "analyst agent" passes findings to a "writer agent" who passes copy to a "publisher agent." It looks elegant on a slide.
Rules as Codebase
The quality of AI output is determined less by the model and more by the constraints you give it. Building a rule system is building a second codebase - one that governs behaviour instead of functionality.
The Click That Speaks Back
A click is a contract. When the acknowledgement is missing or delayed, the user clicks again. The right unit for interface responsiveness is not the millisecond, it is the frame.
The Empty State Is the First Impression
Most products optimise for the experience of an active user. But the first thing every user sees is emptiness. How you handle that moment determines whether they become an active user at all.
Empty States Should Teach, Not Gate
Most empty states are an afterthought. I treat them as a primary surface. The empty state is where the product teaches itself to a user who has not yet learned its conventions.
What We Mean by Marketing OS
Cleo is not a marketing tool. It is a marketing operating system. The distinction is not semantic - it reflects a fundamentally different architectural philosophy about how AI should serve businesses.
Closing the Loop
The difference between a static AI tool and a learning marketing system is whether it can close the feedback loop - measuring results, extracting patterns, and applying them to future decisions.