← The Graveyard
Pantry Chef

Snap a photo of your fridge; get dinner ideas you can actually make tonight — plus a short shopping list for the one or two things you are missing.

Idea Mockup (writeup + images)

Next to-dos

  • Prototype the fridge-photo → ingredient list step (make-or-break)
  • Decide: detect quantities or just presence? (lean presence for v1)
  • Write the "minimize extra ingredients" recipe prompt and test it
  • Dietary constraints — up front or post-filter?
  • Test whether a whole-fridge photo detects reliably vs shelf-at-a-time

Recent activity

  • Created project · 4 hours ago
  • To-do added — Prototype the fridge-photo → ingredient list step (make-or-break) · 4 hours ago
  • To-do added — Decide: detect quantities or just presence? (lean presence for v1) · 4 hours ago
  • To-do added — Write the "minimize extra ingredients" recipe prompt and test it · 4 hours ago
  • To-do added — Dietary constraints — up front or post-filter? · 4 hours ago
  • To-do added — Test whether a whole-fridge photo detects reliably vs shelf-at-a-time · 4 hours ago

Design doc

Pantry Chef — design doc

What it is: Point your phone at an open fridge (or pantry shelf), and get 3 dinner ideas you can make right now with what you have — ranked by how few extra ingredients they need.

The problem it solves

"What's for dinner?" with a full fridge and zero ideas. Recipe apps assume you'll shop first. This starts from what you already own and minimizes the trip to the store.

How it would work

  1. Photo of the fridge → a vision model lists detected ingredients (editable — it will miss the ketchup behind the milk).
  2. You confirm/correct the list.
  3. An LLM proposes 3 recipes, each tagged with "you have everything" or "missing: X, Y".
  4. Tap a recipe → full steps + a tiny shopping list for the gaps.

Approach

  • Vision: a hosted vision model for ingredient detection; let the user edit (don't trust the model).
  • Recipes: LLM with a "use what's listed, minimize additions, be realistic about a weeknight" prompt.
  • No accounts for v1 — it's a single-screen utility.

Open questions

  1. Detect quantities, or just presence? (Presence is probably enough for v1.)
  2. Handle dietary constraints up front, or as a filter after?
  3. Is a fridge photo too cluttered for reliable detection — do we need a "shelf at a time" mode?

Status

Pure idea so far. The fridge-photo demo is the make-or-break: if detection is junk, the whole thing is.