Why we made the choices we made. How Ezra works under the hood. Small things that turn out to matter a lot.
The inbox-and-dashboard pattern is older than most of us realize. We chose iMessage because it's already where you are — and because the friction of "another app" was the thing we kept watching kill products like ours.
Every product decision Ezra makes runs through one filter: would my mom feel dumb here? It sounds glib, but it's the most honest design constraint we've found. Here's how it actually shapes the product.
Most AI products try to do too much, too fast, too eagerly. Ezra is built around the opposite instinct — the kind of restraint that makes a friend feel like a friend instead of a notification.
Memory is what makes Ezra useful over time. Memory is also a privacy risk. Here's the architecture, the trade-offs, and why we built it the way we did — in language anyone can follow.
The default failure mode of personal AI products is "tell me about yourself for twenty minutes." We did the opposite. Here's what your first minute with Ezra actually looks like.