← All projects
Predictive Sensing: Catch Failures Before They Happenbeginner · ~150 min

The Dew-Point Margin — Catch the Cold Wall That's Going to Grow Mold, Weeks Before It Does

Mold on a bedroom wall never arrives as a surprise — it arrives after weeks of conditions that were measurable the whole time, on a surface nobody was measuring. What would you do differently if you knew, five weeks out, that one cold corner of your home was on its way there?

🤝 Want this built for you? Start a request — our AI scopes it, estimates a price range, and matches you with a vetted AI Advisor.
Share this:
The Dew-Point Margin — Catch the Cold Wall That's Going to Grow Mold, Weeks Before It Does
Unlock this walkthrough

Two ways to open it

Just this build
$10 one-time

Unlocks this full walkthrough on your account — no subscription, and no account needed until you check out.

Best value Over 160 projects + the full course
$99 / year

Over 160 project walkthroughs, the 6-week course, and your certificate.

🔒 Secure checkout by Stripe · Already a member? Sign in

What you'll do

A two-sensor watcher on the coldest surface in one room that Claude Code built with you — a Raspberry Pi Pico W reading the room's air temperature and humidity with an SHT4x and the surface's own temperature with a DS18B20 probe, computing the dew point and the surface relative humidity from the Magnus equation on the board itself, alerting your phone when that surface comes within a degree and a half of sweating, logging a row every fifteen minutes to a file you pull down over your own network, and a report Claude Code regenerates on demand that scores the surface against the three running-average mold criteria in ASHRAE Standard 160, projects the week the 30-day average crosses 80 percent, and refuses to project anything when the clock was unsynced or the data is too thin to support it.