Ella Reyes

For our first cohort, we encouraged early testers to send short async audio notes or screen clips whenever they hit a smooth or confusing moment. Hearing their tone and seeing their screen made it incredibly easy to fix small details fast while creating a very warm, personal relationship between founders and users.

what personalized communication formats have given you the highest quality insights from early adopters?

API costs can get surprisingly high as an app grows so self-hosting open-source models starts to look attractive. But cheaper inference doesn't always mean cheaper overall. You still have to think about GPU costs server maintenance traffic spikes and whether the model gives users the same quality of results. For a small app paying per request feels easier. But once usage grows I wonder if managing your own infrastructure becomes the better option or just creates another problem to maintain. For those who have tried both what made you switch and did self-hosting actually reduce your total costs?

Something I keep running into with vibe coding: the agent loses context mid-task and rebuilds a helper that already exists, under a new name, a couple of folders away.

Everything compiles and tests pass. But now half the app uses version A and half uses version B, and the two slowly drift apart. Each version passes review on its own, so nothing looks broken.

The symptoms can be small, like inconsistent date formatting across pages. They can also be serious. If only one copy got the auth check or input validation, part of your app is protected and part isn t, with no visible sign.

One cheap guardrail I ve seen: at the end of each session, ask the agent to list every new function it created, then check for near-duplicates before release.