Where this fits

What this sits alongside

Whether, when and how to stop is entirely your prescriber's territory, and stopping is a decision with real consequences that deserves that conversation. What a log offers is the months afterwards, which are the least documented part of this whole experience.

Why this is hard to keep track of

  • The changes are gradual, so nobody can tell when anything actually started
  • It's the most anxious period and the least recorded one
  • Every app in the category loses interest the moment the medication stops
  • Portion sense drifts back invisibly, exactly as it drifted down

Worth recording

  • Meals in a sentence, lightly. This is a long stretch, not a project
  • Appetite, roughly, because this is the thing that's changing
  • Photos occasionally, since portions move before anyone notices
  • How you're feeling about it, in your own words

Cadence

Much lighter than while you were on it. A few entries a week is plenty

In practice

Say it once, or photograph it

The entries most worth having are the ones made at the exact moment nobody wants to fill in a form. A sentence — typed, dictated, or replaced entirely by a photo of the plate — is a much lower bar, and it carries the context a calorie field would have thrown away.

Coming Off Chat

Six weeks since I stopped. Definitely hungrier in the evenings than I was, and finishing plates again.

Called 4 tools

  • log_note(text: "hungrier in the evenings, finishing plates")
  • log_hunger(before: 6)
  • compare_periods(around: "2026-07-05", window: "6w")
  • get_trend(metric: "portion_finished", window: "12w")

Logged. Comparing the six weeks either side of the date you stopped: eating occasions are up from 2.1 a day to 3.4, and you're finishing the plate on 24 of 31 recent dinners against nine of 28 before. Evening entries have gone from four a fortnight to eleven. It started moving in week three, not week one.

Every figure here was counted from entries you made. The model chose which tools to call — it doesn't score the meal, estimate calories from a photo, or decide what any of it says about you.

And then ask

The question the log can answer

Months of entries hold real answers to the things you've been guessing at, and reading them properly has always meant a spreadsheet and a free evening — which is exactly what nobody has.

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

Asking about the pattern Chat

Is this going back to exactly how it was before?

Called 3 tools

  • get_history(topic: "coming-off", window: "6m")
  • find_pattern(group_by: "context")
  • compare_periods(metric: "entries")

Partly, and not entirely — which is the more common finding. Eating occasions are at 3.4 a day against 3.9 in your original baseline. Evening entries are back to about 80% of where they were. But breakfast has stayed: you're eating it on 25 of 31 days, against nine of 30 before you ever started. Portion photos are between the two. That's three different answers in one log, which is why "back to how it was" rarely survives contact with the record.

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.

What it does

Set up around coming off

The same mechanics as everything else here, pointed at what actually matters for this one.

An entry survives a bad week

A sentence, or a tick that a meal happened at all. On the weeks when eating is genuinely hard, the log has to cost less than the meal did — otherwise the record stops exactly when it gets interesting.

Photos, for the thing descriptions miss

Portion sense recalibrates within weeks and nobody can see it happening. Two photographs eight weeks apart settle it instantly.

Mark the date something changed

Your prescriber decides what changes; the log just notes when, so the fortnight either side can be counted against each other instead of recalled.

Side effects with the meal before them

Nausea on its own is a complaint. Nausea with what you'd eaten, how long it lasted and where it fell in the week is something a clinician can work with.

Watching for eating too little

The risk here is rarely eating too much. Missed meals and meals without a protein source are counted and shown to you, because appetite has stopped being the thing that would have told you.

Formatted for the review

Export the window you were asked about, photos included, and take it in. It's the answer to the first question at every appointment.

The reason a lot of people start

Something to actually bring to the appointment

You get fifteen minutes, and the first question is always some version of "so what does a normal week look like?" — which nobody on earth can answer accurately from memory.

What this gives you: A record of the months afterwards, which almost nobody has and every clinician would like to see — including if you go back on.

  • Export the date range you were asked about, as a file you can print
  • Photos alongside the entries, which say more than any description
  • Counts and timings rather than an impression of the worst week
  • Nothing shared anywhere unless you choose to share it

What it won't do

  • Score a meal, or sort food into good and bad
  • Estimate calories from a photo and present the guess as a number
  • Set you a calorie target, a macro target, or a weight
  • Run a streak you can break, or tell you that you've fallen behind
  • Comment on your body. The photos here are of food
  • Diagnose anything, or suggest that a pattern is a diagnosis

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 notification designed to make you feel behind
  • Export everything you've logged, photos included, 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.