Why this is hard to keep track of

  • Reactions can lag the food by two or three days, which defeats memory entirely
  • Full food diaries get abandoned in week two, and week two is when the data starts to matter
  • The reintroduction ladder is a schedule, and it gets improvised the moment life happens
  • One bad week confounds everything, and there is always a bad week

Worth recording

  • What you ate, roughly — this is not a weighing exercise
  • Symptoms, when they started relative to the meal, and how bad
  • Which phase you're in and what has been reintroduced so far
  • Sleep, stress and cycle, which move symptoms as much as food does

Cadence

A sentence after meals, and whenever something changes

In practice

Say it once, in whatever words you have

The moments most worth recording are the ones where filling in a form is the least realistic thing in the world. A sentence, typed or dictated afterwards, is a much lower bar — and it carries the context a checkbox would have lost.

Elimination Diets Chat

Reintroduced dairy at lunch, a latte and some yoghurt. Bloating started around nine last night and it's still there this morning.

Called 4 tools

  • log_food(items: ["latte", "yoghurt"], phase: "reintroduction", challenge: "dairy")
  • log_symptom(type: "bloating", onset_hours: 20, severity: 3)
  • get_phase(protocol: "elimination")
  • compare_challenges(food: "dairy")

Logged at about 20 hours after exposure. That's the second dairy trial, and both produced bloating in the 18–22 hour window. Wheat, trialled twice, produced nothing at any interval. Day three of the dairy window is tomorrow, so it's worth holding before calling it.

Every figure here was counted from entries you made. The model picked which tools to call — it doesn't interpret, diagnose, or decide what anything means about anyone.

And then ask

The question the log can answer

Months of entries hold real answers to the questions you've been guessing at, and reading them properly has always meant a spreadsheet and a free evening — which is not a thing anyone in this situation has.

Ask in plain language. The answers come back with the numbers behind them, including when those numbers are too thin to mean anything yet — which is the more useful answer more often than people expect.

Asking about the pattern Chat

Is it dairy, or was that just a bad week?

Called 3 tools

  • get_history(topic: "elimination-diet", window: "6m")
  • find_pattern(group_by: "antecedent")
  • compare_periods(metric: "events")

Leaning dairy, but not settled. Across both trials symptoms appeared 18–22 hours after and cleared inside 48. You logged high stress during the first trial week and not the second, and the pattern held in both — which is the part that makes it interesting. A third trial would decide it.

Counts and averages over your own entries, nothing more. Where the data is confounded or too thin, the answer says so instead of rounding it into a conclusion.

The reason most people start

Something to actually bring to the appointment

You get fifteen minutes, once, after waiting months for it. The questions are specific and the honest answers are all some version of "I don't know, it's hard to say".

What this gives you: A structured record of the elimination and every reintroduction, with symptom timings attached — which is what a dietitian needs in order to read the result at all.

  • Export the date range you were asked about, as a file you can print
  • Counts and timings rather than an impression of the worst week
  • Your own notes kept alongside the numbers, in your words
  • Nothing shared anywhere unless you choose to share it

What it won't do

  • Diagnose anything, or suggest that it could
  • Score a person, or rank them against anyone else
  • Set a target for fewer events, or a streak of good days
  • Recommend a treatment, a therapy, a diet or a medication change
  • Share your record with a school, a clinician or anyone else on its own

It's a notebook that can do arithmetic and answer questions about itself. Deciding what any of it means is a job for you and the people advising you.

Early access

Start with what you're already trying to hold in your head

Tell us what you've been trying to keep track of and we'll set it up with you — recording the thing that's actually useful, at a cadence that survives a bad week.

  • Founding accounts lock their price for life
  • No card, no trial clock, no notifications designed to make you feel behind
  • Export everything you've logged whenever you want

No card required. Unsubscribe any time.

Keep the record without it becoming another job

Founding pricing is locked for accounts opened during early access.

Founding accounts lock their price for life. No card required.