Using Claude to hunt down my eczema trigger

I have atopic eczema (neurodermitis). The pattern is the interesting part: when I use the creams my dermatologist prescribed, it clears up completely. Then two or three days after I stop, it comes back. That return is the whole clue. It means something in my daily life is actively setting it off. Find that thing, and I might actually fix it instead of managing it forever.

A patch test appointment was a couple of months out, and I didn't want to just sit and wait. So I did what I now do with most real problems: I opened Claude and started building a plan.

The method

This is the same loop I use for most decisions, pointed at my own skin. It started like this:

I have neurodermitis and started a plan in Claude web to figure out how to find the trigger. It created some files in this folder. Read them and help me build an app on my NAS to track it and find patterns.

The web chat had already turned my rambling into two saved documents: a phased plan for isolating the trigger, and a brief for the tracking app. Those became durable files I could hand to Claude Code as a spec.

The rule I gave it up front was to interview me before doing anything:

Ask me questions wherever you need. Use the ask-user-question tool to finetune the direction before you start. Full build, but check with me on every item (I dont even remember what INCI means).

The plan itself is built on one boring scientific idea: change only one variable at a time, and give the skin a day or three to react before you conclude anything. Mark the days I'm on cortisone, because those mask everything.

Then I moved to Claude Code and we built the tracking app in one evening. Plain PHP and SQLite, running on my own NAS, private. The thing that makes it actually useful is how much context it captures per day, so a one-to-three-day lag has a chance of showing up:

per-area severity + itch (0–10)   lips / eyes / hands / face / arms
products used, split by person     with the ingredient list per product
meals                              auto-synced from my recipe app
sleep, stress, showered            daily
weather + pollen                   auto-pulled, location-aware
cortisone days                     flagged (they mask everything)
sport                              sweat-in-eyes, clothing fabric

It exports its data so I can feed it back to Claude to hunt for patterns. Build the tool, collect the data, analyze it with AI, refine.

What surprised me

The useful part wasn't a magic answer. It was that the process kept overturning my own confident guesses. I was sure about a couple of suspects (a deodorant, the laundry detergent). Reading the actual ingredient lists with Claude mostly cleared both.

And it surfaced things I'd never have reached on my own. The best one:

Dishwasher is something that came to me last night, would have never thought about it.

Rinse-aid residue left on the dishes and glasses that touch my mouth all day. It fits the pattern (my lips flare first) and it's exactly the kind of invisible daily contact you'd never suspect. It even flagged that one of the products I was using to treat the skin might be quietly keeping it going, which is a special kind of annoying.

The part I keep thinking about

Here's the beat that made this worth writing about. After the app was built, I pointed a crowd of agents at my own tool:

Spawn 7–10 analysis agents with different backgrounds, plus 5 data and statistics experts, and have them pressure-test the tool.

I expected a pat on the back. Instead they pushed back, hard and unanimously. Their verdict: the neat little correlations the app produces can badly mislead you (things that drift together, effects that run backwards, skin that was going to calm down anyway). The only real evidence is the controlled experiment, changing one thing at a time and watching. The tracking just organizes the guessing until then.

So the AI helped me build the tool and then talked me out of over-trusting it. I had it rewrite the analysis page to be honest about small sample sizes and shaky signals. That's the whole thing I care about with AI in one story: it's great for structure and for suspects you'd never reach, and it still needs something keeping it honest.

There was a nice side effect too. I showed the app at work, and a couple of colleagues who also have eczema asked if they could use it. So I had Claude generalize it, strip my personal data out, and make it something other people could run. A tiny tool nobody asked me to build that a few people then asked for. That doesn't happen to me often, and it's a big part of why this site exists.

Where it stands

Honestly: still running. No confirmed trigger yet. I'm mid-way through a reset, with a vacation coming up that doubles as a natural experiment (different place, same products travel with me), and the careful reintroduction phase is still weeks out. AI didn't diagnose me and it definitely didn't cure me. What it did was turn "my skin keeps flaring and I don't know why" into an actual experiment I can run.

One honest note, since this touches health: this is my own experiment, not medical advice. I'm doing all of it alongside my dermatologist, and I'd tell anyone with the same problem to do the same :)