More in Family history.
Build a searchable family archive of 1942–43 letters with Google AI Studio and Replit
WorkedEvidence: Described by posterPosted Last checked
Keith Weinberger used Google AI Studio and Replit to make a relative's 1942–43 handwritten letters searchable through AI chat.
How to use this
- Tap Copy prompt.
- Open the tool the case used (or a similar one) and paste the prompt; results may differ from the original.
- Paste it into the message box.
- 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.
Help me build a family archive website for scanned handwritten letters and photos from the 1940s. Add an upload workflow that extracts the text from each letter PDF, splits large files into chunks, and builds a search index so family members can search the letters and ask questions about them through a chat.
Try this in:
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.
The source used Google AI Studio and Replit, which can take actions in a browser or app. These are general chat tools, so results may differ, and a normal chat may only give you a plan.
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: Put a family's scanned letters and photos online where relatives can search them and ask questions. Questions to ask me first: - How many letters and photos are there, and in what format? - Who should be able to see the site? - Do you want the transcriptions checked by a person? Inputs (fill in or confirm): - Scans: [PDFS AND PHOTOS, ROUGH COUNT] - Date range and people: [E.G. 1942–43, NAMES] - Who gets access: [FAMILY ONLY / PUBLIC] - Hosting: [E.G. REPLIT, FIREBASE] Rules: - Keep the original scans unchanged and show them next to each transcription. - Mark words the text extraction couldn't read as [illegible] instead of guessing. - Chat answers must quote the letter and date they come from. - Keep the site private unless I say otherwise. Checkpoint: Transcribe three letters first so I can check the accuracy before processing the rest. If you get stuck: If handwriting extraction is poor, suggest a manual-correction step rather than hiding it. Verify before you finish: Search for a name you know is in a letter and confirm that letter comes up. Output: A working site with upload, search and chat, plus notes on how to add more scans. Done when: Relatives can find any letter by name, place or date and read the original.
AI tools
Outcome
Keith Weinberger built a family archive website for the handwritten letters and photos from a relative's 1942–43 stint in basic training, doing everything through prompts. The site was designed in Google AI Studio, then moved to Replit for the build-out and hosting, with Firebase storing the PDFs and photos and indexing users and data. An upload workflow extracts the text from the handwritten letters, splits the large PDFs into chunks for faster retrieval, and builds a search index and vector database, with server APIs to avoid CORS issues. The result is a site where the letters and photos can be searched and asked questions through AI chat.
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Source
- Posted
- by Keith Weinberger (The Rundown community)
- Last checked
- Method:
- How we verify
https://app.therundown.ai/community/posts/7bc1be34-8f6c-41c8-ad96-9b2038849451
Context: Posted to The Rundown community (date from the post's UTC timestamp). The post doesn't say how accurate the handwriting extraction was.
More in Family history
Find leads on an 1800s Edinburgh ancestor's parents with ChatGPT
ChatGPT gave Janice Wellard new places to search for an ancestor's parents, but it read burgess roll dates wrong and repeated itself.
PartialChatGPTEvidence: Described by posterView CaseMatch census tick marks to family names with ChatGPT
ChatGPT matched 1790 and 1800 census tick marks to the Reed family's children for a genealogy blogger in a few prompts.
WorkedChatGPTEvidence: Screenshots or logsView CaseTranslate old Norwegian and German records with Gemini, Claude and ChatGPT
Gemini did the best job translating Kitty Cooper's old records, but Claude gave a partial and ChatGPT made stuff up.
PartialGemini +2Evidence: Screenshots or logsView CaseCatch a wrong birthplace in a family tree with a NotebookLM Audio Overview
A NotebookLM Audio Overview made a genealogist notice that an ancestor's recorded birthplace didn't match the records.
WorkedNotebookLMEvidence: Described by posterBeginner-friendlyView CaseSearch 40+ sources on a brick wall ancestor's FAN Club with NotebookLM
NotebookLM searched 40+ sources at once with citations and helped Lisa Rex confirm a migration pattern from Ohio to Illinois.
WorkedNotebookLMEvidence: Described by posterBeginner-friendlyView CaseTranscribe an 1829 handwritten deed with Claude and check it against a manual copy
Claude 3.5 Sonnet transcribed an 1829 deed almost perfectly for genealogist Nicole Dyer, but misread the key surname Peerson.
WorkedClaudeEvidence: Screenshots or logsBeginner-friendlyView Case

