Digitize Your Recipe Book: AI Import from Excel, CSV and Notes

The Real Barrier Is Migration, Not Software

Every pastry chef already owns recipe software’s real competitor: a battle-worn Excel costing sheet, a notes app full of half-structured formulas, a binder from three kitchens ago. The recipe manager you evaluated last year lost not because it was worse than the spreadsheet — but because retyping a hundred recipes into a hundred forms was never going to happen between production days.

Formul.io removes that step. Its AI bulk import reads the files you already have — no template, no cleanup pass, no fixed column order — and turns them into structured, calculable recipes. The trade it is designed around: you spend judgment, not data entry.

From Messy Rows to Structured Recipes

One upload starts a planning job that reads the file the way a person would — then does the tedious part at machine speed. Only the extraction stage is generative; matching, enrichment, and plan assembly are retrieval and arithmetic, which is why the result can be inspected line by line and replayed exactly.

The plan is the contract. The AI runs once, during planning; the commit step later replays that frozen plan deterministically. What you approve in the preview is exactly what lands — the model cannot quietly change its mind between review and commit.

Matching is deliberately conservative. Exact and high-confidence semantic matches resolve automatically; anything borderline — a house abbreviation, a brand name, a typo — becomes a flagged item for your decision, never a silent guess.

The Preview Is the Quality Guarantee

Bulk import earns trust by refusing to be silent. Before anything is written, the dry-run preview shows a reconciliation report in which every source line is accounted for — matched, flagged, or skipped with a stated reason — plus computed metrics for each recipe in the plan.

The flagged queue is where the afternoon is saved: you review the short list of genuinely ambiguous ingredients, not every row of every recipe.

The per-recipe metrics deserve a second look before you commit. A ganache that previews at a suspiciously high water activity usually means a quantity landed in the wrong unit somewhere in the source file — caught in the preview, that is a one-line fix instead of a corrupted library.

Committing is just as deliberate. Nothing lands until you commit the previewed plan, and the commit is idempotent: re-importing the same file does not create duplicates, so an interrupted migration can simply be run again.

What the review looks like

The preview is not a document you read once — it is a workbench you work in. Every planned import lands on a page headed “Review recipes”, subtitled “Fix only what needs attention, then import the ready recipes”, and the import page keeps it under “Recent imports” until you are finished with it. A migration started before service is still waiting after it.

A status strip sorts the whole file for you before you read a single line: “All”, “Needs attention”, “Ready”, “Imported” and “Excluded”, each carrying its own count. “Needs attention” is the working queue — the recipes with an unresolved ingredient, an unconvertible quantity, or a section the reader could not classify. Selecting a recipe opens it beside the list: its ingredient lines with quantities and total weight, its calculator, and a status badge. Resolve the last issue on a recipe and the workbench moves you to the next one that still needs attention, so the queue empties without you hunting for the next card.

When one ambiguous name runs through several recipes, the page splits into two tabs: Decisions and Recipes. The Decisions queue is where a shared correction belongs, because it states its true scope — “Used in 7 recipes” — before you answer it. Answer once and every one of those recipes updates. The Recipes tab is for anything local to a single formula.

Matches the importer made on its own are labelled, not hidden. A line resolved automatically says so — “Matched automatically to …. Change it if that is not what the source meant.” — so a confident-but-wrong match is visible rather than buried among the lines you never inspected. When a decision is one you will face again, tick “Remember this match for future imports” and the next file resolves it without asking.

“Open source file” in the page header reopens the document you uploaded. Comparing a suspicious line against the row it came from is the fastest way to settle whether the file said 1.5 kg or 1,5 kg — and you should not have to go and find the file yourself.

Best of all, the review does not have to be finished in one sitting. The commit button imports only the ready recipes — “Import 12 ready recipes” — and says plainly what it is leaving behind: “4 recipes will stay here for later review”. Those four keep their place in the queue, the twelve are live formulations in your library, and you come back to the remainder when you have the supplier sheet in front of you.

Four Migration Scenarios

The speed claim needs no magic. Extraction, matching, and enrichment are machine time; your time goes only where judgment is required — the flagged matches. For a typical costing sheet that is a handful of supplier-specific names, not a hundred forms.

Free-text import deserves its own mention because it clears the guilt pile: the recipes that never made it into any spreadsheet. Paste them as they are — quantities buried in sentences, ingredients in shorthand — and they go through the same extraction, matching, and preview as everything else.

After Import, Your Library Has Physics

A digitized recipe in a generic notes tool is still just text. A committed Formul.io recipe is a live formulation: the calculation engine computes water activity, shelf life, composition, and nutrition from real ingredient data, and the recipe can be analyzed, scored, and simulated like anything built in the app from scratch.

That changes what “archive” means. The ganache your predecessor left in row 47 can now be diagnosed — run the analysis, read its quality score, see why it never lasted the claimed three weeks — and rebalanced in simulation before anyone weighs a gram.

The payoff compounds across the platform: the same digitized library feeds costing, scaling, PDF data sheets, and the AI development workflow. One migration, every downstream feature.

Questions Confectioners Ask