More in Hobbies, Fitness & Learning.
Turn a trading card collection into a searchable inventory from photos with ChatGPT
WorkedEvidence: Described by posterPosted Last checked
ChatGPT read Fien De Waele's card photos in batches and built a searchable inventory, marking uncertain cards rather than guessing.
How to use this
- Tap Copy prompt.
- Open ChatGPT.
- Paste it into the message box.
- Replace anything in [CAPITAL LETTERS IN BRACKETS] with your own details.
- 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.
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.
Work through this folder of trading card photos in batches of [NUMBER]. For each card, record the name, set code, series, edition, rarity, language, quantity, approximate year, condition notes, your confidence level and the source image file. If you can't identify a card with confidence, mark it as uncertain instead of guessing, and confirm every image was processed.
Try this in:
This prompt has blanks to fill in, like [NUMBER]. We'll copy it instead of filling it in, so you can edit it before you send.
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: A complete, searchable inventory of a physical card collection. Questions to ask me first: - Which game or series are the cards from? - How are the photos organized? - What will you use the inventory for? Inputs (fill in or confirm): - Card series: [NAME] - Photo folders: [GOOGLE DRIVE LINK OR UPLOADS] - Fields to record: [NAME, SET, RARITY, CONDITION] - Purpose: [VALUATION, SELLING, INSURANCE] Rules: - Process one batch at a time and account for every image. - Record uncertainty instead of guessing. - Note visible damage such as scratches, edge wear or folds. - Don't estimate prices unless I ask. Checkpoint: Show the results for the first batch so I can check accuracy. If you get stuck: If a photo shows several overlapping cards, ask for a better photo. Verify before you finish: The number of cards recorded matches the photos processed. Output: One spreadsheet with one row per card and a duplicates summary. Done when: I know exactly what's in the boxes.
AI tool
Outcome
Fien De Waele used ChatGPT to turn a physical Yu-Gi-Oh! trading card collection into a structured digital inventory. De Waele photographed the cards, stored the images in Google Drive subfolders by group, and had ChatGPT work through the folders in manageable batches, using OCR and visual recognition to record each card's name, set code, series, edition, rarity, language, quantity, approximate year, condition notes, a confidence level and the source image. Batch limits, a check that every image was accounted for and one central card per photo where identification was ambiguous kept errors down, and uncertain cards were recorded as uncertain rather than guessed. The batches were then merged into one central inventory to check duplicates, quantities and inconsistencies, giving a searchable overview that can be used for valuation, selling, insurance or cataloging; De Waele plans to reuse the process for a Harry Potter card collection.
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Source
- Posted
- by Fien De Waele (The Rundown community)
- Last checked
- Method:
- How we verify
https://app.therundown.ai/community/posts/3d010bde-8daa-43a1-bcdd-45a1e18053c5
Context: Posted to The Rundown community (date from the post's UTC timestamp). The post doesn't give the number of cards or an accuracy figure. A physical card collection, not a video game.
More in Hobbies, Fitness & Learning
Run a character-guessing game for a book club discussion with ChatGPT
ChatGPT picked five characters, wrote five clues for each and added discussion questions for Susan Young's book club.
WorkedChatGPTEvidence: Described by posterBeginner-friendlyView CaseRank the next 50 books on a Goodreads to-read list by season with Claude
Claude profiled Melina Panitsidis's Goodreads ratings and ranked the next 50 to-read books into seasonal blocks.
WorkedClaudeEvidence: Described by posterBeginner-friendlyView CaseFix a sweater knitting pattern 30 rows after a mistake with ChatGPT
ChatGPT revised Johannah Ross's sweater pattern so the stripes still lined up, avoiding undoing 30 rows of knitting.
WorkedChatGPTEvidence: Described by posterBeginner-friendlyView CaseTurn a gym class schedule into a weekly workout plan with 10 free AIs
Daniel Costa tested 10 free AIs on a gym schedule; four couldn't read the site, and only Qwen made no mistakes.
PartialChatGPT +9Evidence: Described by posterView CaseWrite a 60-stitch sock knitting pattern with ChatGPT
ChatGPT wrote a wearable 60-stitch sock pattern for Lanja Khon-Engheim, but the cable cuff and toe length came out wrong.
PartialChatGPTEvidence: Described by posterView CaseTurn Claude into a blunt running coach with Garmin data and markdown files
Claude coached from per-lap Garmin data and showed an 'easy' run averaging 130 bpm had drifted to 146, with a third in Zone 3.
WorkedClaudeEvidence: Described by posterView Case
Similar cases
Get a 62-year-old retiree using ChatGPT voice for everyday paperwork and repairs
After a 45-minute setup, Jake Read's retired dad used ChatGPT to decode an insurance letter and get a late contractor to show up.
WorkedChatGPTEvidence: Described by posterBeginner-friendlyView CaseKnit doll socks from a ChatGPT pattern, then find one that works
ChatGPT's own doll sock pattern had a heel error and came out too small. Asking it to find a free Ravelry pattern worked.
PartialChatGPTEvidence: Described by posterView CaseResearch a Victorian-born grandfather's life with Claude, ChatGPT and Gemini deep research (partial)
Three AIs researched a grandfather who died in 1960; ChatGPT found new family facts, but Gemini's maps were wrong.
PartialClaude +2Evidence: Article or interviewView CaseTrain for a first half marathon on a day-by-day plan built by ChatGPT
ChatGPT built a day-by-day half marathon plan from current mileage; the runner finished on it and set a record about a year later.
WorkedChatGPTEvidence: Described by posterView CaseWrite a crochet pattern from a photo with ChatGPT and Claude (gave up)
ChatGPT and Claude couldn't turn a photo into a usable crochet pattern; Claude missed the tail and ears, so the maker gave up.
FailureChatGPT +1Evidence: Described by posterView Case

