Every website peaks on launch day and slowly drifts from there, not because it breaks, but because nobody has time to keep it current. Autonomous websites, continuously optimized by agents after launch, aim to change that. But take the idea seriously, and you quickly run into a problem that has nothing to do with technology: almost nobody wants a website that changes entirely on its own. Pierre Burgy shares what they learned building for full website autonomy and the deeper design problem they uncovered along the way.
This article has been kindly supported by our dear friends at Fimo, the infrastructure that keeps a website improving after launch. It runs over your real code, lets your team edit anything visually, and puts agents to work on content, accessibility, and the maintenance you never get to. Incubated at Strapi. Thank you!
Every website is at its best the day it ships. The final branch merges, the site goes live exactly as designed, and it is briefly perfect. It will never be this good again.
Not because anything breaks. The site keeps working. But the market moves, the messaging shifts, a competitor launches something, and the careful thing you built slowly stops matching the company it represents. A year later, it is a period piece. Not broken, just behind. Every team knows this decay, and almost everyone treats it as a law of nature.
It doesn’t have to be that way. A website could keep improving after launch instead of drifting away from its best day, quietly optimizing itself while the team that built it works on something else.
Picture it working: while you sleep, an agent catches that last week’s design-system change never propagated to the pricing page, and fixes it. Another finds a set of images shipped uncompressed in a rushed release and optimizes them. A third flags an accessibility regression a new component introduced, and either fixes it or leaves it for you to check. You wake up to a site that is measurably better than the one you left, and a short list of the few decisions the agents wanted your eyes on. That is the version worth wanting.
And the moment you take that promise seriously, you run into a problem thathas nothing to do with the technology:
Almost nobody actually wants a website that changes entirely on its own.
Why “Just Make It Autonomous” Is The Wrong Goal #
The obvious move, once you have capable agents, is to hand them the whole site. Let them write, edit, optimize, and publish, and get out of the way. It sounds like the natural endpoint, and it is the first thing most people picture when they hear “autonomous website.”
It is also the thing almost nobody wants once it is real in front of them.
We learned this the way you learn most things worth knowing: by building the opposite first. Building Fimo, an autonomous website platform, we set out to make websites fully autonomous, assumed that was the goal, and then watched what people actually did with it. What they did was hesitate. Not because they distrusted the agents, but because a website has no single owner. Different parts belong to different people, and each one wants a different amount of autonomy. So the question was never whether to trust the agents. It was where to draw the line, and for whom.
Once you ask it that way, the work splits cleanly into three kinds.
