Why this is hard to keep track of

  • The topic attracts moralising, and moralising is how people end up lying to a log
  • The definition is genuinely fuzzy at the edges, so any score is false precision
  • Convenience food clusters in specific slots, and nobody knows which without data
  • Cooking from scratch fails at exactly the moments a week gets hard, unrecorded

Worth recording

  • What you ate, in plain words. Packet or not is usually obvious
  • Whether it was cooked, assembled, bought ready, or delivered
  • Which days it clusters on, which is nearly always the tired ones
  • What the week was like, since that predicts more than intention does

Cadence

A sentence a meal. The categorising is not your job

What progress looks like

A truthful proportion across a normal few weeks, and the two or three slots where nearly all of it actually sits.

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.

Cutting Ultra-Processed Food Chat

Cereal, a supermarket sandwich, and a ready meal for dinner. Long day, no energy to cook.

Called 4 tools

  • log_meal(items: ["cereal"], meal: "breakfast")
  • log_meal(items: ["supermarket sandwich"], meal: "lunch")
  • log_meal(items: ["ready meal"], meal: "dinner", prep: "reheated")
  • compare_periods(group_by: "weekday", tag: "convenience")

Logged, no scoring applied. Across three weeks, your meals split roughly 60/40 cooked to bought. The bought ones are concentrated: 19 of 26 were weekday lunches or Thursday and Friday dinners.

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 meals would I need to change to move this most, with the least effort?

Called 3 tools

  • get_history(topic: "less-ultra-processed", window: "6m")
  • find_pattern(group_by: "context")
  • compare_periods(metric: "entries")

Two slots hold 19 of your 26 bought meals: weekday lunch, and dinner on Thursday and Friday. Every other slot is already mostly cooked. Your notes mention being too tired to cook on nine of the 11 late-week evenings, which suggests the constraint is the evening rather than the intention.

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 cutting ultra-processed food

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

A sentence or a photo per meal

No database lookup and no calorie box. The log that gets kept beats the log that was more precise for eleven days.

Trends, not days

Weight moves a couple of kilos on water alone. Everything here is read as a weekly trend, because the daily number is mostly noise and reads as failure on a perfectly good week.

What the good weeks had in common

The useful question isn't what you ate on Tuesday, it's what was different about the months that went somewhere. That's a query against your own record, and it's the one worth asking.

Your goal, not one we set

We don't calculate a target for you. Any number an app produces here is a population average wearing your name, and it will be wrong by enough to matter.

A bad week is a data point

Nothing resets and nothing is undone. A week off is information about what makes a week hard, which is considerably more useful than a broken chain.

Exportable from day one

Everything you've logged, photos included, out in a file you can take to a dietitian, a GP, or somewhere else entirely.

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 realistic picture of a normal week, which is more useful to anyone advising you than a description of how you eat when you're doing well.

  • 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.