Skip to content
TriedPrompts

More in Meals & Cooking.

Turn a recipe app library into a meal-planning notebook with Claude and NotebookLM

PartialEvidence: Described by posterPosted Last checked

Lucy Gray had Claude Cowork merge Paprika exports into one PDF for NotebookLM, but Claude couldn't take more than 20 files at a time.

How to use this

  1. Tap Copy prompt.
  2. Open the tool the case used (or a similar one) and paste the prompt; results may differ from the original.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

I've attached recipe files exported from my recipe app as HTML. Combine all of these recipes into one clean PDF, with each recipe's title, ingredients and steps, so I can upload it to NotebookLM.

Try this in:

ChatGPT Gemini Used in sourceGrok Claude

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Combine my exported recipe files into one tidy document I can use for meal planning.

Questions to ask me first:
- Which app did the recipes come from, and in what file format?
- How many recipes are there?
- What do you want to do with them next (meal plans, nutrition, sharing)?

Inputs (fill in or confirm):
- Exported recipe files: [FILES]
- Format: [HTML / PDF / TEXT]
- Household size and diet needs: [HOUSEHOLD / DIET]

Rules:
- Keep each recipe's title, servings, ingredients and steps exactly as written; don't rewrite or 'improve' them.
- Add a table of contents grouped by main ingredient or meal type.
- List any file you couldn't read instead of skipping it silently.
- If there are too many files at once, tell me the batch size to use.

Checkpoint: Do the first batch and show me two recipes so I can check the formatting before doing the rest.

If you get stuck: If a recipe comes through garbled, include it at the end under 'needs checking' with the file name.

Verify before you finish: Count recipes in versus recipes in the PDF and report any mismatch.

Output: One PDF with a table of contents and a short list of problem files.

Done when: All my recipes are in one document I can upload to a notebook tool.

AI tools

Claude CoworkNotebookLM

Outcome

Lucy Gray and a spouse plan meals in the Paprika 3 recipe app, which can bulk-export only HTML files or its own format. Gray imported the HTML recipe files into Claude Cowork, which combined them into one PDF, and then added that PDF to Google NotebookLM. There Gray could ask for a recipe's nutritional analysis, a weekly meal plan or chicken recipe ideas, and generated two study-style assets from the recipes. Claude could only handle 20 HTML files at a time, so Gray had to pick recipes and work in small batches. Gray isn't sure the generated assets were that useful but sees potential.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Known limitations

PartialThe source says it only partly worked, or had a significant problem a person had to deal with.

What went wrong: The pipeline worked in batches of 20 files, but Gray wasn't sure the generated assets were that useful.

Source

Posted
by Lucy Gray (Lucy's Daily Dispatch)
Last checked
Method:
How we verify

https://elemenous.substack.com/p/google-notebooklm-for-meal-planning

Context: AI nutrition estimates are approximate. Check medical diets with a dietitian.

More in Meals & Cooking

Similar cases