Nora Celeste

Nora Celeste

Facility Manager

Forums

I did 100 calls to build the AI interviewer I wanted. Try it free

First, why we build an AI interviewer?

Image

To ease the onboarding process.

After our Product Hunt Launch, many people signed up but didn't test the platform because they need someone to do a call with, and if we lose that momentum, the user is lost.

Why does your recovery score say 58% today?

I wear a WHOOP. I've coached people on movement and sleep for many years and I still can't answer that question for myself. The algorithm is locked. You get a number, you trust it, you stop there.

When we built Open Wearables, we decided the scoring layer should work differently. Sleep Score and Resilience Score shipped in v0.5 - every coefficient, every threshold, every weighting is in the repo and you can fork them, tune for endurance athletes or elder care or clinical populations. Moreover, you run them on your own infrastructure and the same algorithms feed the MCP layer so AI coaching can cite the actual data behind a recommendation instead of approximating.

Clawdi — a shared environment for all your AI agents. AMA before we launch.

Hey Product Hunt community

I'm Marvin, co-founder of Clawdi. We launch tomorrow and I wanted to start a conversation before the big day.