For Humans & Their Machines
User-centred design in a world with AI agents.
For a long time, user-centred design meant designing for a person. Someone with eyes, hands, a moment of patience, a bias for the familiar. The whole craft sat on top of that assumption.
That assumption is fraying. A growing share of the people using software today are agents acting on someone's behalf. Many of them are, from the product's point of view, indistinguishable from a human user.
If we cannot tell the difference between a person and an agent on the other side of the screen, what does it mean to be user-centred in design?
This blog hopes to capture, question, share, and learn what works and how design is evolving in this new world.
Keep reading
- 9 min
Your Users may not be Human
In June 2026 Cloudflare confirmed machines now generate more web traffic than people. Every one of those visits is a user nobody has watched, and nobody can ask why. What does user-centred mean in this new age of AI?
- 3 min
What Is MCP and Why It Matters for Product Teams
The Model Context Protocol lets AI assistants call tools in external services. For product teams, that means testing, feedback, and issue tracking without leaving your editor.
- 4 min
Building with Supabase
How we run a multi-tenant AI agent platform on Supabase: row level security for tenant isolation, OAuth and passkeys for humans and machines, pgvector for agent RAG, read replicas for global reads, and preview branches for every pull request.