Applied AI • Open Standard

Real Time Recipe Cooking in Your Kitchen

From recipe to executable cooking plan — authenticated JSON-LD files that cook alongside you

Broadbase Ai Cookpit v3.2 · CC0 public domain Starters · Mains · Desserts

Cookpit: "shaped in large part by AI, instructed by broadbaseai.com" · Hero image: AGA in a cottage kitchen, by simonsimages [Flickr, CC BY 2.0]

Executive Summary

A recipe is prose; a kitchen is real time. The written recipe cannot tell you that the sauce needs stirring now, that the oven should have been preheating ten minutes ago, or that if the starter is to land while the main rests, three tasks must run in parallel. Cookpit closes that gap: it turns a recipe into an executable cooking plan — a JSON-LD file with ingredients, equipment, phases, timed tasks on parallel lanes, sensory completion cues and a pre-start checklist — validated against a published rulebook and cryptographically signed before your cooking app is allowed to run it.

The result, for the cook, chef, hobbyist or baker: starters, main courses and desserts orchestrated live in your kitchen, each step arriving at the optimal moment an expert chef would commit to it — with the file's authenticity guaranteed by mathematics, not by trust in whoever generated it.

60+

Published Recipes

Searchable by course, cuisine, skill level and serving size

10

Publication Lanes

Parallel workstreams so multiple dishes cook at once

4

Lifecycle Stages

Generate → Validate → Attest → Consume, one actor each

Anatomy of a Cooking File

A Cookpit file is JSON-LD — JSON with linked-data context, grounded in the schema.org/Recipe vocabulary and extended by the published Cookpit v3.2 schema. Machine-readable and human-auditable at once, every file declares the same structural blocks:

  • Identity & metadata — the recipe's name, author, source, course, cuisine, servings and skill level, with deterministic identifiers computed from the content itself.
  • Ingredients & equipment — closed, declared lists. Every quantity carries the value the source recipe states; every pan, whisk and oven the plan will touch is declared up front.
  • Phases — the plan's chapters (prep, cook, finish), each with a nominal duration from which alarms are derived mechanically.
  • Timed tasks on ten lanes — the heart of real time. A global alarm lane (A0) plus primary, secondary and tertiary lanes for each course (S1–S3, M1–M3, D1–D3) — ten in all. Each task carries its optimal execution time and states the basis for that time: an exact source duration, a range minimum, a "meanwhile" cue, or a professional estimate with a one-line rationale.
  • Processes with sensory cues — completion is defined by what you can see, smell or feel: "golden brown and pulling from the pan's edge", never "cook for a little while".
  • Pre-start checklist — prerequisites confirmed once before the clock starts, so the plan never stalls mid-service.
The attestation block is the load-bearing trust signal — the filename's authenticated flag is decorative.
Download the real file

Creamy Garlic Salmon and Shrimp by Julie Maestre — main course, 4 servings, 25 minutes. A genuine authenticated .A.jsonld file (23 KB): open it in any text editor to audit every timing basis, or load it into CookChow and cook it tonight.

The Rules That Make It Trustworthy

Anyone — or any AI — can generate a plausible-looking recipe file. Cookpit's discipline is what turns an untrusted AI draft into a trusted artefact. Every rule has an identifier and a sentence, published immutably and dedicated to the public domain under CC0.

A1 · Optimal

"Every task time is the optimal moment an expert chef would commit to that action." No random, cosmetic or filler times — ever.

A2 · Closed

"The plan is bounded by the resources declared in this file." An undeclared pan is a hard validation failure, not a warning.

A3 · Static

"The plan does not adapt at runtime." Execution and the clock belong to the app and the cook — never to the file.

K1 · No Silent Changes

Every quantity, duration and temperature in the source must appear with the value the source states, bound by a SHA-256 fingerprint the validator recomputes.

Provenance on every decision

No task may carry a time without a stated basis drawn from a closed set of evidence types — an exact source duration, a range target, an endpoint of the cook time, a "meanwhile" cue, an implied deadline worked backwards from a downstream consumer, or a professional estimate with a one-line rationale. Each basis names the specific source line that justifies it. A model that quietly rounds a temperature or drops a range fails validation, however plausible its output reads. Where the source is ambiguous, an explicit priority order resolves it — ambiguity is never resolved silently.

Authenticated, Not Just Downloaded

Four lifecycle stages, one actor at each — so the entity that drafts a file is never the entity that vouches for it.

1

Generation

An AI drafts the cooking file from your recipe — and must mark its output unauthenticated. The AI contract is explicit: it "MUST NOT claim status authenticated under any circumstance" and "is not trust authority".

2

Validation

A browser validator — which never uploads your file — checks every rule: closure, identifiers, timing bases, fingerprints. A failing file is returned unmodified with a report; the validator never repairs it.

3

Attestation

The validator — and only it — signs a passing file with an Ed25519 key and flips its status. The signed file downloads as .A.jsonld: authenticated, tamper-evident, portable.

4

Consumption

Your cooking app verifies the signature against a pinned public key before it runs the plan. A tampered file — even one edited after signing — fails the fingerprint check and never reaches your kitchen.

Real Time at the Stove

Load an authenticated file into a live cooking app such as CookChow — "Live (Real-Time) Recipe Home Cooking" — and the plan becomes a running kitchen. The ten publication lanes are parallel workstreams: while the tart base blind-bakes on one lane, the filling reduces on another and the garnish preps on a third. Alarms are derived mechanically from each phase's declared window, so nothing depends on the cook remembering to set a timer.

Instructions arrive in a controlled register — imperative and exact, enforced by lint, with "a little while" forbidden. Every completion cue names a sensory fact, because a kitchen is judged by eyes, nose and fingertips, not by the clock alone. When the plan says the sauce is done, it tells you what done looks like.

And because each dish is a bounded, validated plan, courses compose: run the starter, main and dessert together and their lanes interleave, each step surfacing at its optimal moment so the starter lands as guests sit, the main follows as plates clear, and the dessert finishes as the coffee brews. That is the real-time promise — the coordination a head chef carries in their head, made available to the hobbyist on a Tuesday night.

Who it serves

The cook — dinner for the family with the timing handled, and no step forgotten at the school-run hour.

The chef — training plans and service prep expressed as validated files a brigade can run identically, shift after shift.

The hobbyist — ambitious multi-course menus that would otherwise demand a second pair of hands.

The baker — where minutes and grams are chemistry: exact times, faithful quantities, and proof the file matches its source.

The Ecosystem

cookpit.org — the standard

The open cooking file format itself: the v3.2 specification, governing rules, lexicon, AI prompt bundle, browser validator and attestation service. Dedicated to the public domain under CC0 1.0; every versioned address is immutable forever.

cookpit.recipes — the library

The public recipe repository: 60+ published recipes across British, French, Italian, Indian, Turkish, Japanese, Thai and more — searchable by name, author or ingredient, filterable by course (starter, main, dessert), cuisine, skill level and servings, each downloadable as a Cookpit JSON-LD file.

cookpit.net — the corpus

A companion recipe corpus with the same search, filtering and assist features — demonstrating that anyone can publish a conformant Cookpit collection, because the format belongs to everyone.

cookchow.com — the kitchen

Live (real-time) recipe home cooking: the consumer app that verifies a file's signature, then runs the plan — lanes, alarms, phases and sensory cues — as you cook.

Get Started

Cook tonight — three steps

Browse cookpit.recipes and pick your starter, main or dessert.

Download the authenticated .jsonld file.

Open it in CookChow and cook in real time.

Convert your own recipe

Give your recipe (even a PDF) to a capable AI chatbot with the standard prompt from cookpit.org — it fetches the spec, computes the deterministic ids and the source fingerprint.

Drop the generated file into the browser validator — your recipe never leaves your machine.

Have the passing file signed, and it's ready for any Cookpit-compatible app — yours to keep, share or publish.

Conclusion

Cookpit shows what applied AI looks like when it is done with discipline: the AI drafts, an independent validator checks, a key-holder signs, and the app verifies before anything runs — with the whole standard published openly and dedicated to the public domain. It is a small thing about kitchens, and that is the point. The same validate-then-attest method that gets your lemon tart to the table on time is the method our Project Icarus work proposes for AI safety itself: trust that lives in the signature, not in the machine's word.

Real Time, For Real Kitchens

Ten lanes, mechanical alarms and sensory cues put a head chef's coordination in every home.

Provably Faithful Files

Fingerprints and signatures guarantee every quantity and timing matches the source recipe.

Sources and Further Reading

The Cookpit v3.2 JSON-LD schema/format is dedicated to the public domain under CC0 1.0 Universal. Recipe content itself is not covered by that licence. The JSON excerpt on this page is illustrative; cookpit.org/v3.2 is the authoritative schema.