Why this is hard to keep track of

  • A plate is invisible to itself; only two plates side by side mean anything
  • Weighing food works and almost nobody sustains it past a fortnight
  • Restaurant and takeaway portions are unknowable and are most of the variance
  • "A serving" on a packet rarely resembles what anyone actually serves

Worth recording

  • A photo of the plate before you start, which takes a second
  • How you felt about half an hour later — the only honest verdict available
  • Whether it was served to you or served by you
  • Whether you went back for more, which almost never gets recorded

Cadence

A photo when it's a proper plate of food. Not every snack

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.

Portion Sizes Chat

"[photo] Dinner — chicken, rice, roasted veg. Went back for a bit more rice."

Called 4 tools

  • log_meal(items: ["chicken", "rice", "roast vegetables"], photo: true, at: "19:20")
  • log_portion(seconds: true, served_by: "self")
  • log_fullness(after_min: 30, level: 8)
  • compare_photos(meal: "rice-based", window: "3m")

Photo saved against the entry. Compared with your other eleven rice dinners, this plate is on the larger end. Worth knowing: on the four where you went back for seconds, you logged feeling over-full afterwards on three. On the seven where you didn't, that happened once.

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

Which of my usual dinners leaves me uncomfortable afterwards?

Called 3 tools

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

Two stand out from 34 dinners with a fullness note. Pasta dinners: over-full on six of nine. Takeaway curry: five of seven. Everything else sits under 20%. Portion photos for both are visibly larger than your other plates, which is the more likely explanation than the food itself.

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 portion sizes

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

An entry is a sentence

Type it or say it. No item lookup, no portion field, nothing to complete before the entry counts — which is the whole reason this one survives past week three.

Or just a photo

A picture of the plate takes a second and records the thing descriptions are worst at. We store it against the entry; we don't estimate a calorie count from it and hand you the guess.

Context, not just food

Where you were, who with, what had just happened. In almost every log on this site the pattern turns out to live in the context rather than in what was eaten.

No streak to break

A gap in the record is a gap in the record. Nothing resets, nothing is lost, and nothing tells you that four missed days undid the month before them.

Readable across months

One rough fortnight reads as one rough fortnight when it sits on a six-month line — which is the view that changes what people believe about themselves, and the one a daily score can't draw.

Yours, and exportable

Everything you've written and every photo, out in one file whenever you want it — including the date range a dietitian or therapist asked you about.

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: Actual photographs of what you eat, which is worth more to a dietitian than any description you could write and removes the guesswork from both sides.

  • 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.